Manufacturing data analysis device, system, method and program

Abstract

To support a user in monitoring of manufacturing data.SOLUTION: A manufacturing data analysis device is provided with a first acquisition unit, an acquisition condition determination unit, a second acquisition unit, an analysis unit, and an output data generation unit. The first acquisition unit acquires, from manufacturing data related to a plurality of products, in a first acquisition condition, first manufacturing data including manufacturing condition data related to values indicating manufacturing conditions for the products and quality data related to values indicating quality of each of the products. The acquisition condition determination unit determines a second acquisition condition different from the first acquisition condition on the basis of the first manufacturing data. The second acquisition unit acquires, from the manufacturing data, in the second acquisition condition, second manufacturing data including the manufacturing condition data and the quality data. The analysis unit analyzes the second manufacturing data to calculate an analysis result related to a relationship between the manufacturing condition data and the quality data. The output data generation unit generates output data including the analysis result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] FIELD Embodiments of the present invention relate to a manufacturing data analysis device, system, method, and program. [Background technology]

[0002] In the manufacturing industry, it is important to quickly identify the cause of a product entering a specific state. For example, if a product enters an abnormal state that differs from its normal state, identifying the cause early on will lead to maintaining and improving yield. Many manufacturing industries detect product anomalies and identify the cause by monitoring various data (manufacturing data) acquired during the product manufacturing process.

[0003] The content of manufacturing data varies. For example, data on the manufacturing conditions of a product (manufacturing condition data) includes the names of materials and equipment used in manufacturing the product. Data on the quality of the product (quality data) includes the size, physical characteristics, and appearance quality of the product.

[0004] By monitoring product quality data, it is possible to detect abnormalities in products or manufacturing equipment. For example, if the quality data values ​​for some products among a group of products manufactured during a certain period are different from normal, then those products are suspected to be abnormal. Furthermore, if it is determined that those products were manufactured using a specific piece of equipment based on the manufacturing condition data for those products, then that equipment may be the cause of the abnormality.

[0005] The more processes and devices required to complete a product, the greater the amount of data that needs to be monitored. Furthermore, with the recent development of IoT (Internet of Things) technology, various types of manufacturing data can be easily acquired. As a result, the amount of manufacturing data has increased significantly, making it difficult to monitor the data manually. Therefore, there is a demand for a device that can assist users in monitoring manufacturing data.

[0006] For example, when analyzing the relationship between a product's manufacturing condition data and quality data, a manufacturing data analysis device must specify the acquisition conditions for the manufacturing data to be analyzed. Here, if the number of data (samples) containing some of the multiple values ​​that the manufacturing condition data can take is relatively small in the manufacturing data acquired under the acquisition conditions specified by the user, the reliability of the analysis results regarding the relationship will be reduced. In this case, the user will need to modify the acquisition conditions for the manufacturing data themselves, which will be time-consuming for the user. Furthermore, the analysis device may fail to detect or overdetect the relationship between the manufacturing condition data and the quality data. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Patent Publication No. 2021-071896 Summary of the Invention [Problem to be solved by the invention]

[0008] The problem that the present invention aims to solve is to assist users in monitoring manufacturing data. [Means for solving the problem]

[0009] A manufacturing data analysis device according to an embodiment includes a first acquisition unit, an acquisition condition determination unit, a second acquisition unit, an analysis unit, and an output data generation unit. The first acquisition unit acquires, under first acquisition conditions, first manufacturing data from manufacturing data related to a plurality of products, the first manufacturing data including manufacturing condition data related to values ​​indicating the manufacturing conditions for each of the products and quality data related to values ​​indicating the quality of each of the products. The acquisition condition determination unit determines second acquisition conditions different from the first acquisition conditions based on the first manufacturing data. The second acquisition unit acquires, under the second acquisition conditions, second manufacturing data from the manufacturing data, including the manufacturing condition data and the quality data. The analysis unit analyzes the second manufacturing data to calculate an analysis result related to the relationship between the manufacturing condition data and the quality data. The output data generation unit generates output data including the analysis result. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a block diagram showing an example of the functional configuration of a manufacturing data analysis system according to a first embodiment. [Figure 2] FIG. 3 is a flowchart showing a first operation example of the manufacturing data analysis device according to the first embodiment. [Figure 3] FIG. 3 is a diagram showing an example of manufacturing data according to the first embodiment. [Figure 4] FIG. 6 is a flowchart showing a second operation example of the manufacturing data analysis device according to the first embodiment. [Figure 5] FIG. 10 is a flowchart showing a third operation example of the manufacturing data analysis device according to the first embodiment. [Figure 6] FIG. 10 is a block diagram showing an example of the functional configuration of a manufacturing data analysis system according to a second embodiment. [Figure 7] FIG. 10 is a flowchart showing an example of the operation of the manufacturing data analysis device according to the second embodiment. [Figure 8] FIG. 11 is a view showing an example of the display of an entire image based on output data according to the second embodiment. [Figure 9] FIG. 11 is a view showing a display example of a part of an image based on output data according to the second embodiment. [Figure 10] FIG. 10 is a block diagram showing an example of the functional configuration of a manufacturing data analysis system according to a third embodiment. [Figure 11] FIG. 11 is a block diagram showing an example of the operation of the manufacturing data analysis device according to the third embodiment. [Figure 12] FIG. 11 is a block diagram showing an example of manufacturing data analysis processing according to the third embodiment. [Figure 13] FIG. 11 is a view showing a first display example of an image based on output data according to the third embodiment. [Figure 14] FIG. 11 is a view showing a second display example of an image based on output data according to the third embodiment. [Figure 15] FIG. 11 is a view showing a third display example of an image based on output data according to the third embodiment. [Figure 16] FIG. 1 is a block diagram showing an example of the hardware configuration of a manufacturing data analysis system according to first to third embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, a manufacturing data analysis device, system, method, and program according to an embodiment will be described with reference to the drawings. In the following embodiments, parts with the same reference numerals perform similar operations, and redundant description will be omitted as appropriate.

[0012] (First embodiment) FIG. 1 is a block diagram showing an example of the functional configuration of a manufacturing data analysis system 1 according to a first embodiment. The manufacturing data analysis system 1 is a system that performs product quality control by analyzing various data (hereinafter referred to as "manufacturing data") acquired during the product manufacturing process. For example, the manufacturing data analysis system 1 analyzes the manufacturing data to detect product abnormalities and identify the causes of the abnormalities. The manufacturing data analysis system 1 includes a manufacturing DB 100, a manufacturing data analysis device 200, and a display device 300.

[0013] The manufacturing DB 100 is, for example, a relational database management system (RDBMS) that stores manufacturing data 110 provided by a manufacturing factory. The manufacturing DB 100 may be, for example, a NoSQL database or a file in a predetermined format (e.g., CSV). The manufacturing data 110 stored in the manufacturing DB 100 may include, for example, several thousand or more items. Note that "DB" means "database."

[0014] For example, when manufacturing data 110 is provided by a manufacturing factory, the manufacturing DB 100 updates the stored manufacturing data 110. Furthermore, in response to a request from the manufacturing data analysis device 200, the manufacturing DB 100 outputs a part or all of the stored manufacturing data 110 to the manufacturing data analysis device 200 as analytical manufacturing data 130 or additional analytical manufacturing data 140.

[0015] The manufacturing data 110 includes information that can identify each individual product or group of products (e.g., ID, serial number), data related to the manufacturing conditions of the product (hereinafter referred to as "manufacturing condition data"), and data related to the quality of the product (hereinafter referred to as "quality data"). These pieces of information or data may include continuous or discrete numerical values, or categorical values.

[0016] Information that can identify each individual product or group of products includes, for example, a product number, the time when the product was processed or inspected, or a number or character string (e.g., lot number or lot ID) that indicates a certain period or a certain number of product units. Note that "lot" can be alternatively referred to as "batch." This identification information may be associated with manufacturing condition data and quality data.

[0017] The manufacturing condition data includes multiple items, such as the names of materials used in the product and the names of the equipment used to process and assemble the product. More generally, the manufacturing condition data may be information related to the 5M1E (Man, Machine, Material, Method, Measurement, Environment), which are known as the six factors for manufacturing process management. Specifically, the manufacturing condition data may include the name of the person processing the product (Man), the name of the equipment, the name of the production line, and the state of the equipment during processing (temperature, pressure, etc.) (Machine), the ID and name of the material or part (Material), the processing method or type of processing program (Method), the name of the equipment used for measurement and the measurement location (Measurement), the building name, temperature, and humidity (Environment). The manufacturing condition data may also include other data that the user deems useful for analysis and visualization.

[0018] Quality data includes multiple items, such as measurement values ​​relating to product size (dimensions), weight, electrical characteristics, and physical characteristics. Some or all of the quality data measurement values ​​are measurement values ​​relating to inspection items used to determine product release. Furthermore, quality data is not limited to the measurement values ​​themselves, but may also be the results of some kind of judgment. Specifically, quality data may be an integer value on a five-point scale indicating the quality of a product, or a binary flag indicating pass / fail (e.g., bad / good). Quality data may also be anything else that the user deems useful for analysis or visualization. Of course, quality data may also be the results of a judgment made using a predetermined judgment method (e.g., threshold processing) based on data such as product size, weight, and characteristics.

[0019] The parameters 120 are parameters that control the operation of the manufacturing data analysis device 200. The parameters 120 are specified, for example, by a user of the manufacturing data analysis device 200 or an external system, and are input to the manufacturing data analysis device 200 as a file in a predetermined format (e.g., CSV). The parameters 120 may be data names in the manufacturing data 110. In particular, if the manufacturing data 110 is data in a table format, the parameters 120 may be column names in this table. The parameters 120 include a first data acquisition condition AC1, target manufacturing condition data x, and target quality data y.

[0020] The first data acquisition condition AC1 is a condition under which the manufacturing data analysis device 200 acquires analytical manufacturing data 130 from the manufacturing data 110 stored in the manufacturing DB 100. That is, the manufacturing data analysis device 200 acquires specific data that meets the first data acquisition condition AC1 from the manufacturing data 110 as analytical manufacturing data 130. The first data acquisition condition AC1 is, for example, a specific value or a range of values ​​related to the identification information, manufacturing condition data, or quality data included in the manufacturing data 110. That is, the first data acquisition condition AC1 may be at least one value included in at least one of the identification information, manufacturing condition data, and quality data. The first data acquisition condition AC1 may also be referred to as a first analysis range.

[0021] First, if the first data acquisition condition AC1 is identification information, the first data acquisition condition AC1 may be, for example, a specific product number, a list of specific product numbers, a specific time or time period when the product was processed or inspected, or a specific lot number. Second, if the first data acquisition condition AC1 is manufacturing condition data, the first data acquisition condition AC1 may be, for example, a specific material name or equipment name, or a list of material names or equipment names. Third, if the first data acquisition condition AC1 is quality data, the first data acquisition condition AC1 may be, for example, a specific value or range related to the size, weight, electrical characteristics, or physical characteristics of the product. Of course, the first data acquisition condition AC may be a combination of these pieces of information or data. For example, the first data acquisition condition AC1 may be a specific lot number and a specific material name.

[0022] The target manufacturing condition data x is manufacturing condition data that the user pays attention to, and is also manufacturing condition data that is to be analyzed by the manufacturing data analysis device 200. The target manufacturing condition data x is designated, for example, from a plurality of manufacturing condition data included in the manufacturing data 110. Note that each time the manufacturing data analysis device 200 performs an analysis process, each of the manufacturing condition data included in the manufacturing data 110 may be designated sequentially as the target manufacturing condition data x.

[0023] The target quality data y is quality data that the user pays attention to, and is also quality data that is to be analyzed by the manufacturing data analysis device 200. The target quality data y is designated, for example, as one of the multiple quality data included in the manufacturing data 110. Note that each time the manufacturing data analysis device 200 performs an analysis process, each of the quality data included in the manufacturing data 110 may be designated sequentially as the target quality data y.

[0024] The first data acquisition condition AC1 may be a specific value among multiple values ​​included in the target manufacturing condition data x. For example, if the target manufacturing condition data x is data related to a specific material name (e.g., gear), this data includes multiple values ​​(e.g., gear A, gear B, gear C) that differ in manufacturer, manufacturing time, processing conditions, characteristics, etc. In this case, the first data acquisition condition AC1 may be one or more specific values ​​(e.g., gear A, gear C) among the multiple values. Such first data acquisition condition AC1 is suitable for the manufacturing data analysis device 200 to investigate the degree to which a difference in a specific value affects the target quality data y.

[0025] Similarly, the first data acquisition condition AC1 may be a specific range of values ​​among multiple values ​​included in the target quality data y. For example, if the target quality data y is data related to the size of a product, this data includes a predetermined range of values ​​(e.g., 1 cm-20 cm). In this case, the first data acquisition condition AC1 may be a specific range of values ​​among the predetermined range of values ​​(e.g., 5 cm-10 cm).

[0026] The manufacturing data analysis device 200 is a device that analyzes manufacturing data to generate output data 250 including various analysis results. For example, the manufacturing data analysis device 200 outputs the output data 250 including the results of analyzing the analytical manufacturing data 130 and the additional analytical manufacturing data 140 acquired from the manufacturing DB 100 to the display device 300. The manufacturing data analysis device 200 includes an acquisition unit 211, an acquisition condition determination unit 212, an analysis unit 213, and an output data generation unit 214.

[0027] The acquisition unit 211 acquires analytical manufacturing data 130 including target manufacturing condition data x and target quality data y from the manufacturing data 110 included in the manufacturing DB 100 based on the parameters 120 input from outside, under first data acquisition conditions AC1. At this time, in order to identify the product group included in the analysis range, the acquisition unit 211 may include information capable of identifying each individual product or product group in the analytical manufacturing data 130. The acquisition unit 211 outputs the analytical manufacturing data 130 to the acquisition condition determination unit 212 and the analysis unit 213. The acquisition unit 211 is an example of a first acquisition unit.

[0028] The acquisition condition determination unit 212 determines acquisition conditions (second data acquisition conditions AC2) for the manufacturing data 110 so as to reduce bias in multiple values ​​included in the target manufacturing condition data x or the target quality data y in the analytical manufacturing data 130 input from the acquisition unit 211. Here, the second data acquisition conditions AC2 are conditions different from the first data acquisition conditions AC1. For example, the second data acquisition conditions AC2 are a range that includes part or all of the first data acquisition conditions AC1. Furthermore, the second data acquisition conditions AC2 may be conditions that acquire a larger number of data items from the manufacturing data 110 than the first data acquisition conditions AC1. The acquisition condition determination unit 212 outputs the second data acquisition conditions AC2 to the acquisition unit 211.

[0029] The acquisition unit 211 acquires additional analysis manufacturing data 140 including target manufacturing condition data x and target quality data y from the manufacturing data 110 included in the manufacturing DB 100 under the second data acquisition conditions AC2 input from the acquisition condition determination unit 212. At this time, in order to identify the product group included in the analysis range, the acquisition unit 211 may include information capable of identifying each individual product or product group in the additional analysis manufacturing data 140. The acquisition unit 211 outputs the additional analysis manufacturing data 140 to the analysis unit 213. The acquisition unit 211 is an example of a second acquisition unit.

[0030] The analysis unit 213 analyzes at least one of the analytical manufacturing data 130 and the additional analytical manufacturing data 140 input from the acquisition unit 211, and calculates an analysis result regarding the relationship between the target manufacturing condition data x and the target quality data y. For example, the analysis unit 213 calculates an index value S(y, x) that represents the strength of the relationship between the target manufacturing condition data x and the target quality data y. The index value S(y, x) is a value that represents, for example, the possibility that the target manufacturing condition data x is the cause of the variation in the target quality data y (likelihood of being the cause). The analysis unit 213 outputs the index value S(y, x) to the output data generation unit 214 as the analysis result.

[0031] The output data generation unit 214 generates output data 250 based on the analysis results input from the analysis unit 213. For example, the output data generation unit 214 generates output data 250 including at least one of the analysis results of the analytical manufacturing data 130 and the analysis results of the additional analytical manufacturing data 140. The output data generation unit 214 may include, as the analysis results, the data names of the target manufacturing condition data x and the target quality data y and the index value S(y, x) in the output data 250. In addition, the output data generation unit 214 may include values, representative values, statistical values, histograms, scatter diagrams, etc. of the target manufacturing condition data x and the target quality data y in the output data 250. The output data generation unit 214 outputs the output data 250 to the display device 300.

[0032] The output data 250 is data including the analysis results of the manufacturing data analysis device 200. The output data 250 may be data in a format (e.g., CSV, HTML, XML, JSON) that can be displayed on the display device 300. That is, the output data 250 may be various types of text data, text files, image data, or image files. Alternatively, the output data 250 may be stored in a dedicated database.

[0033] The display device 300 is a device that displays an image based on the output data 250 input from the manufacturing data analysis device 200. For example, if the output data 250 is text data or a text file, the display device 300 may display the data on a text editor. On the other hand, if the output data 250 is image data or an image file, the display device 300 may display the data on a browser or an image viewer. The display device 300 may also retrieve the output data 250 stored in a dedicated database from the database and display it. Furthermore, the display device 300 may convert structured text data (e.g., CSV, JSON) into HTML data or image data using a predetermined method and display it.

[0034] 2 is a flow diagram showing a first operation example of the manufacturing data analyzing apparatus 200 according to the first embodiment. This operation example can be started when a user of the manufacturing data analyzing apparatus 200 or an external system inputs parameters 120 into the manufacturing data analyzing apparatus 200.

[0035] (Step S101) First, the manufacturing data analyzing device 200 acquires, as parameters 120, the first data acquisition condition AC1, the target manufacturing condition data x, and the target quality data y by the acquisition unit 211.

[0036] (Step S102) Next, the manufacturing data analysis device 200 acquires, by the acquisition unit 211, the analytical manufacturing data 130 from the manufacturing data 110 included in the manufacturing DB 100 based on the parameters 120.

[0037] FIG. 3 is a diagram showing an example of manufacturing data 110 according to the first embodiment. In this example, the manufacturing data 110 is shown as table-format data. Here, the vertical direction of the manufacturing data 110 is called columns, and the horizontal direction is called rows. In this case, the columns of the manufacturing data 110 indicate data items (types). Meanwhile, the rows of the manufacturing data 110 represent individual products. In other words, the values ​​of the individual cells of the manufacturing data 110 represent the values ​​of various data for each product.

[0038] Specifically, the first to third columns from the left of the manufacturing data 110 contain product identification information (product number, processing / inspection time, lot number). The fourth to eighth columns from the left of the manufacturing data 110 contain manufacturing condition data (C1-C5). The ninth and tenth columns of the manufacturing data 110 contain quality data (C6-C7). Here, each of the multiple values ​​contained in the manufacturing condition data or quality data is associated with each of the multiple values ​​contained in the product identification information. For example, if manufacturing condition data C1 is specified as target manufacturing condition data x and quality data C6 is specified as target quality data y in the manufacturing data 110, the analytical manufacturing data 130 will contain the manufacturing condition data C1 and the quality data C6.

[0039] The manufacturing data 110 includes various data related to D products. For example, the target manufacturing condition data x and the target quality data y are lists (vectors) with a length of D. In this example, D=17.

[0040] (Step S103) Next, the manufacturing data analysis device 200 determines the second data acquisition conditions AC2 based on the analytical manufacturing data 130 using the acquisition condition determination unit 212.

[0041] First, when the first data acquisition condition AC1 is a condition related to a period or date and time, the acquisition condition determination unit 212 may set a period or date and time before or after the period or date and time as the second data acquisition condition AC2. For example, when the first data acquisition condition AC1 is "a product whose processing time is within a predetermined one hour (e.g., 12:00-13:00)," the acquisition condition determination unit 212 may set a time including one hour before and after the predetermined one hour (e.g., 11:00-14:00) as the second data acquisition condition AC2. Of course, the acquisition condition determination unit 212 may set a time including one hour before or after the predetermined one hour (e.g., 11:00-13:00, 12:00-14:00) as the second data acquisition condition AC2.

[0042] Furthermore, the second data acquisition condition AC2 does not have to be temporally consecutive with the period or date and time of the first data acquisition condition AC1. For example, if the first data acquisition condition AC1 is "products whose processing time is within a specified one day (e.g., March 3, 2022)," the acquisition condition determination unit 212 may set the second data acquisition condition AC2 to a past period that is not temporally consecutive with the specified one day (e.g., February 28 to March 1, 2022). Alternatively, the second data acquisition condition AC2 may be a period with an interval such as every other week, every other month, or every other year. Of course, the second data acquisition condition AC2 may be any other condition.

[0043] Second, if the first data acquisition condition AC1 is a condition related to the identification information of a product, the acquisition condition determination unit 212 may set product identification information different from the identification information as the second data acquisition condition AC2. For example, if the first data acquisition condition AC1 is a predetermined lot number, the acquisition condition determination unit 212 may set a lot number different from the predetermined lot number as the second data acquisition condition AC2. For example, if the order of each product is specified by lot number in the manufacturing data 110, the acquisition condition determination unit 212 may set as the second data acquisition condition AC2 a condition including lot numbers (e.g., XXXX-1, XXXX-3) that are one or more lot numbers earlier or later than the predetermined lot number (e.g., XXXX-2).

[0044] Furthermore, the acquisition condition determination unit 212 may determine the second data acquisition conditions AC2 based on possible values ​​of the target manufacturing condition data x or the target quality data y included in the analytical manufacturing data 130 acquired under the first data acquisition conditions AC1. For example, if the possible values ​​of the target manufacturing condition data x in the analytical manufacturing data 130 are A1, A2, or A3, the acquisition condition determination unit 212 may determine the second data acquisition conditions AC2 as conditions for acquiring a larger number of data items related to any of the values ​​A1, A2, or A3 than when the first data acquisition conditions AC1 were used. Alternatively, the acquisition condition determination unit 212 may determine the second data acquisition conditions AC2 as conditions for acquiring all data items related to any of the values ​​A1, A2, or A3.

[0045] Furthermore, when the target manufacturing condition data x or the target quality data y is qualitative data, the acquisition condition determination unit 212 may determine the second data acquisition condition AC2 so that the number of data for each type of value included in the qualitative data is equal to or greater than a predetermined threshold. This threshold can be set to any value by the user. This allows the acquisition condition determination unit 212 to reduce bias in the distribution of multiple values ​​included in the target manufacturing condition data x or the target quality data y.

[0046] Furthermore, when the target manufacturing condition data x or the target quality data y is a continuous value, the acquisition condition determination unit 212 may determine the second data acquisition condition AC2 based on a plurality of values ​​included in the target manufacturing condition data x or the target quality data y or the distribution of the plurality of values. Specifically, the acquisition condition determination unit 212 may generate a histogram of the plurality of values ​​and determine, as the second data acquisition condition AC2, a condition including a value whose frequency for each class in the histogram is relatively low.

[0047] Furthermore, when the target manufacturing condition data x or the target quality data y is quantitative data, the acquisition condition determination unit 212 may determine the second data acquisition condition AC2 so that the frequency of each class of values ​​included in the quantitative data is equal to or greater than a predetermined threshold. This threshold can be set to any value by the user. This allows the acquisition condition determination unit 212 to reduce bias in the distribution of multiple values ​​included in the target manufacturing condition data x or the target quality data y.

[0048] Furthermore, the acquisition condition determination unit 212 may determine the second data acquisition conditions AC2 when the analytical manufacturing data 130 satisfies a predetermined condition. For example, when the number of data items included in the analytical manufacturing data 130 is less than a predetermined threshold, the acquisition condition determination unit 212 may determine the second data acquisition conditions AC2 so as to increase the number of data items. Alternatively, when the number or proportion of missing values ​​or abnormal values ​​included in the analytical manufacturing data 130 is greater than a predetermined threshold, the acquisition condition determination unit 212 may determine the second data acquisition conditions AC2 so as to reduce the number or proportion.

[0049] Alternatively, when the number or proportion of data having a specific value in the analytical manufacturing data 130 is smaller than a predetermined threshold, the acquisition condition determination unit 212 may determine the second data acquisition condition AC2 so as to increase the number of data having the specific value. Specifically, when the number or proportion of data belonging to a specific category of the target manufacturing condition data x is smaller than a predetermined threshold, the acquisition condition determination unit 212 may determine the second data acquisition condition AC2 so as to increase the number or proportion.

[0050] Alternatively, the acquisition condition determination unit 212 may exploratory determine the second data acquisition condition AC2 so that the second data acquisition condition AC2 satisfies a predetermined condition. For example, if the first data acquisition condition AC1 is a condition related to a period or date and time, the acquisition condition determination unit 212 may use the period or date and time as a reference to expand the target period for analysis in the forward and backward directions, and determine the target period that satisfies the predetermined condition as the second data acquisition condition AC2.

[0051] The acquisition condition determination unit 212 may determine whether or not analysis under the second data acquisition conditions AC2 is necessary, and may determine the second data acquisition conditions AC2 if it is determined that analysis under the second data acquisition conditions AC2 is necessary. For example, the acquisition condition determination unit 212 may determine that analysis under the second data acquisition conditions AC2 is necessary if the analytical manufacturing data 130 does not satisfy a predetermined condition. On the other hand, if it is determined that this analysis is unnecessary, the acquisition condition determination unit 212 may set the second data acquisition conditions AC2 to be the same as the first data acquisition conditions AC1. Alternatively, the acquisition condition determination unit 212 may set the second data acquisition conditions AC2 to an empty set or the like, and control the manufacturing data analysis device 200 so that the additional analytical manufacturing data 140 is not acquired or generated under the second data acquisition conditions AC2.

[0052] (Step S104) Next, the manufacturing data analysis device 200 causes the acquisition unit 211 to acquire the additional analysis manufacturing data 140 from the manufacturing data 110 included in the manufacturing DB 100 based on the second data acquisition condition AC2.

[0053] (Step S105) Next, the manufacturing data analysis device 200 calculates an analysis result for each data by analyzing the analytical manufacturing data 130 and the additional analytical manufacturing data 140 using the analysis unit 213. As a result, the analysis unit 213 calculates an analysis result for the analytical manufacturing data 130 and an analysis result for the additional analytical manufacturing data 140. As described above, the analysis result includes an index value S(y, x) that indicates the strength of the relationship between the target manufacturing condition data x and the target quality data y. The index value S(y, x) indicates, for example, the possibility that the target manufacturing condition data x is the cause of the variation in the target quality data y (likelihood of being the cause). Conversely, the index value S(y, x) may also indicate the possibility that the target quality data y is the cause of the variation in the target manufacturing condition data x.

[0054] The index value S(y,x) may be a correlation coefficient (e.g., Pearson's product-moment correlation coefficient, Spearman's rank correlation coefficient, Kendall's rank correlation coefficient, or MIC (Maximal Information Coefficient)) between the target manufacturing condition data x and the target quality data y. In particular, when the target manufacturing condition data x and the target quality data y both contain categorical values, the index value S(y,x) may be a correlation coefficient (e.g., Goodman-Kruskal's tau or Cramer's V). When Goodman-Kruskal's tau is used for the index value S(yi,x), the smaller of the two values ​​calculated from the two data items may be used. In other words, the index value S(y,x) may be the similarity between the two data items.

[0055] In this embodiment, the analysis unit 213 may calculate the index value S(y, x) using a statistical testing method (e.g., chi-square test or G test). For example, the analysis unit 213 may use the p-value when testing the null hypothesis that "the target manufacturing condition data x is not related to the fluctuation of the target quality data y" as the index value S(y, x). In this case, the smaller the index value S(y, x), the stronger the relationship between the target manufacturing condition data x and the target quality data y. Alternatively, the analysis unit 213 may use the 1-p value or the 1 / p value as the index value S(y, x). Note that the analysis unit 213 may use other likelihood ratio test frameworks.

[0056] In this embodiment, the analysis unit 213 may set the regression error obtained by regression analysis of the target manufacturing condition data x and the target quality data y as the index value S(y, x). When a regression model with a small regression error (e.g., least square error) or a high likelihood is obtained from the target manufacturing condition data x and the target quality data y, the analysis unit 213 may determine that the target manufacturing condition data x has influenced the target quality data y, i.e., that there is a strong relationship.

[0057] Examples of regression analysis methods that can be used include linear regression, generalized linear regression (e.g., logistic regression, Poisson regression), basis linear regression, kernel regression, support vector regression, multilayer perceptron, regression tree, and random forest. When the target manufacturing condition data x and the target quality data y include categorical values, the analysis unit 213 may perform one-hot encoding on the categorical values ​​before performing regression analysis.

[0058] Furthermore, the analysis unit 213 may estimate the causal factors related to the factors that cause changes in the target quality data y using an index other than the regression error. Generally, the regression error of a model in which a data element with a large number of levels or a combination of a large number of data elements is used as an explanatory variable tends to be small. In order to avoid relying on such a tendency, the analysis unit 213 may estimate the causal factors using a model comparison index value that takes into account the model's compatibility (fit) as well as the model's complexity (e.g., the number of explanatory variables, the regularization strength in nonlinear regression).

[0059] Examples of model comparison indices include Akaike's Information Criterion (AIC), Bayesian Information Criterion (BIC), Widely Applicable Information Criterion (WAIC), and Mallows' Cp. Alternatively, cross-validation (e.g., leave-one-out cross-validation, K-fold cross-validation) error may be used.

[0060] In this embodiment, the analysis unit 213 may calculate the index value S(y, x) using a model trained by machine learning. Of course, the analysis unit 213 may use other calculation methods, testing methods, and methods for calculating the index value S(y, x).

[0061] In this embodiment, the index value S(y,x) is a continuous value, and the larger the value, the stronger the relationship between the target manufacturing condition data x and the target quality data y. Conversely, if the smaller the value of the index value S(y,x), the stronger the relationship, the analysis unit 213 may reverse the sign of the index value S(y,x) in the condition determination. Of course, the index value S(y,x) may also be a discrete value.

[0062] (Step S106) Next, the manufacturing data analysis device 200 generates output data 250 including the analysis results using the output data generation unit 214. Specifically, the output data generation unit 214 generates output data 250 including at least one of the analysis results (first analysis results) for the analytical manufacturing data 130 and the analysis results (second analysis results) for the additional-analysis manufacturing data 140. After this process, the manufacturing data analysis device 200 ends the series of processes.

[0063] Here, the output data generation unit 214 may select at least one of the first analysis result and the second analysis result, and include the selected analysis result in the output data 250. For example, the output data generation unit 214 may compare the index value S(y, x) included in the first analysis result with the index value S(y, x) included in the second analysis result, and select the analysis result associated with the larger index value S(y, x). Furthermore, when including both analysis results in the output data 250, the output data generation unit 214 may sort the first analysis result and the second analysis result in descending or descending order of the index value S(y, x).

[0064] The output data generation unit 214 may set at least one condition for the index value S(y, x) and change the content to be included in the output data 250 depending on the determination result of each condition. Here, it is assumed that the index value S(y, x) ranges from 0 to 1, and the closer to 1 the index value S(y, x) is, the stronger the relationship between the target manufacturing condition data x and the target quality data y is. For example, the output data generation unit 214 may set a first threshold value of 0.9 as the first condition and a second threshold value of 0.7 as the second condition. In this case, the output data generation unit 214 may change the information to be included in the output data 250 depending on whether the index value S(y, x) is (i) equal to or greater than the first threshold value, (ii) less than the first threshold value and equal to or greater than the second threshold value, or (iii) less than the second threshold value. Specifically, the output data generation unit 214 may include, in the output data 250, information or a flag indicating a classification of "Warning" in the case of (i), "Caution" in the case of (ii), or "No abnormality" in the case of (iii).

[0065] 4 is a flow diagram showing a second operation example of the manufacturing data analyzing apparatus 200 according to the first embodiment. Similar to the operation example of FIG. 2, this operation example can be started when a user of the manufacturing data analyzing apparatus 200 or an external system inputs parameters 120 into the manufacturing data analyzing apparatus 200.

[0066] (Step S201) First, the manufacturing data analyzing device 200 acquires the first data acquisition condition AC1, the target manufacturing condition data x, and the target quality data y as the parameters 120 through the acquisition unit 211. Step S201 is the same as step S101.

[0067] (Step S202) Next, the manufacturing data analysis device 200 acquires analytical manufacturing data 130 from the manufacturing data 110 included in the manufacturing DB 100 based on the parameters 120 using the acquisition unit 211. Step S202 is similar to step S102.

[0068] (Step S203) Next, the manufacturing data analyzing device 200 calculates the reliability (first reliability) of the analytical manufacturing data 130 by the acquisition condition determining unit 212.

[0069] For example, the acquisition condition determination unit 212 calculates the reliability from the number of data included in the analytical manufacturing data 130. Specifically, the acquisition condition determination unit 212 may set a predetermined threshold for the number of data, and set the reliability to "1" if the number of data is greater than this threshold, and set the reliability to "0" if the number of data is less than this threshold. Alternatively, the acquisition condition determination unit 212 may set the reliability to "1" if the number of data is equal to or greater than a predetermined threshold, and calculate the reliability using the formula: (number of data) / (threshold) if the number of data is less than the predetermined threshold. In this calculation formula, when the number of data is half the threshold, the reliability is calculated to be "0.5."

[0070] Alternatively, the acquisition condition determination unit 212 may calculate the reliability based on the number or ratio of missing values ​​or abnormal values ​​to the number of data included in the analytical manufacturing data 130. For example, if 20% of the number of data are missing values ​​or abnormal values, the acquisition condition determination unit 212 may set the reliability to "0.8" based on the remaining number of data (80%) that are not missing values ​​or abnormal values.

[0071] Furthermore, the acquisition condition determination unit 212 may calculate the reliability based on the number or proportion of data having a specific value in the analytical manufacturing data 130. Specifically, the acquisition condition determination unit 212 may calculate a lower reliability when the number or proportion of data belonging to a specific category of the target manufacturing condition data x in the analytical manufacturing data 130 is less than a predetermined threshold.

[0072] Here, it is assumed that the target manufacturing condition data x can take on any of the values ​​A1, A2, and A3. If the target manufacturing condition data x contains each value at an equal ratio, the ratio is approximately 33% (= 1 / 3). On the other hand, if the ratio of A2 included in the target manufacturing condition data x is relatively low, for example, approximately 2%, the acquisition condition determination unit 212 calculates the reliability to be lower. Specifically, the acquisition condition determination unit 212 may calculate the reliability using the formula: 2[%] / 33[%]≒0.06, with the equal ratio of 33% as the maximum value.

[0073] Alternatively, the acquisition condition determination unit 212 may calculate the reliability based on the degree of variation (bias) in the proportion of each value. Alternatively, the acquisition condition determination unit 212 may set the same or different thresholds for the minimum number of each value of A1, A2, and A3 and calculate the first reliability. For example, the acquisition condition determination unit 212 may set the same threshold for the minimum number of data for each of A1, A2, and A3.

[0074] (Step S204) Here, the manufacturing data analysis device 200 determines, via the acquisition condition determination unit 212, whether the reliability of the analytical manufacturing data 130 is equal to or less than a predetermined threshold. This threshold can be set to any value by the user of the manufacturing data analysis device 200. If this determination condition is met (YES in step S204), the process proceeds to step S205. On the other hand, if this determination condition is not met (NO in step S204), the process proceeds to step S207.

[0075] (Step S205) In this case, the manufacturing data analyzing device 200 determines the second data acquisition conditions AC2 using the acquisition condition determination unit 212 based on the analytical manufacturing data 130. Step S205 is similar to step S103.

[0076] The acquisition condition determination unit 212 may calculate the reliability (second reliability) of the additional analytical manufacturing data 140 using a method similar to the method for calculating the reliability (first reliability) of the analytical manufacturing data 130 described above. The acquisition condition determination unit 212 may exploratory determine the second data acquisition conditions AC2 so that the second reliability satisfies a predetermined condition. For example, the acquisition condition determination unit 212 may exploratory determine the second data acquisition conditions AC2 so that the second reliability is greater than the first reliability.

[0077] (Step S206) Next, the manufacturing data analysis device 200 acquires the additional analysis manufacturing data 140 from the manufacturing data 110 included in the manufacturing DB 100 based on the second data acquisition condition AC2 using the acquisition unit 211. Step S206 is similar to step S104.

[0078] (Step S207) Subsequently, the manufacturing data analysis device 200 calculates an analysis result for each piece of data by analyzing the analytical manufacturing data 130 and the additional analytical manufacturing data 140 using the analysis unit 213. Step S207 is similar to step S105.

[0079] (Step S208) Next, the manufacturing data analysis device 200 generates output data 250 including the analysis results using the output data generation unit 214. Step S208 is similar to step S106. Note that the output data generation unit 214 may include a reliability (first reliability) in the analysis results (first analysis results) of the analytical manufacturing data 130 and a reliability (second reliability) in the analysis results (second analysis results) of the additional-analysis manufacturing data 140. After this process, the manufacturing data analysis device 200 ends the series of processes.

[0080] 5 is a flow diagram showing a third operation example of the manufacturing data analyzing apparatus 200 according to the first embodiment. Similar to the operation example of FIG. 2, this operation example can be started when a user of the manufacturing data analyzing apparatus 200 or an external system inputs parameters 120 into the manufacturing data analyzing apparatus 200.

[0081] (Step S301) First, the manufacturing data analyzing device 200 acquires the first data acquisition condition AC1, the target manufacturing condition data x, and the target quality data y as the parameters 120 through the acquisition unit 211. Step S301 is the same as step S101.

[0082] (Step S302) Next, the manufacturing data analyzing device 200 acquires, through the acquiring unit 211, analytical manufacturing data 130 from the manufacturing data 110 included in the manufacturing DB 100 based on the parameters 120. Step S302 is similar to step S102.

[0083] (Step S303) Next, the manufacturing data analysis device 200 causes the analysis unit 213 to analyze the analytical manufacturing data 130 and calculate an analysis result (first analysis result) for the analytical manufacturing data 130. The analysis unit 213 outputs the first analysis result to the acquisition condition determination unit 212 and the output data generation unit 214.

[0084] (Step S304) Next, the manufacturing data analyzing device 200 causes the acquisition condition determining unit 212 to calculate the reliability (first reliability) of the analytical manufacturing data 130 based on the first analysis result.

[0085] For example, when the analysis unit 213 calculates the correlation coefficient between the target manufacturing condition data x and the target quality data y as the index value S(y, x), the acquisition condition determination unit 212 may calculate the reliability based on a p-value that indicates the significance of the correlation coefficient. Alternatively, the acquisition condition determination unit 212 may use the p-value itself as the reliability. In other words, the reliability can be calculated based on various indexes calculated by the analysis unit 213 from the analytical manufacturing data 130.

[0086] Furthermore, when the analysis unit 213 calculates the BIC by regression analysis as the index value S(y, x), the acquisition condition determination unit 212 may calculate the reliability based on the difference ΔBIC from the BIC by the null model. Alternatively, the acquisition condition determination unit 212 may use ΔBIC itself as the reliability.

[0087] Alternatively, when the analysis unit 213 artificially increases the number of data items in the analytical manufacturing data 130 by using a bootstrap method or the like and calculates multiple index values ​​S(y, x), the acquisition condition determination unit 212 may calculate the reliability based on the variation (bias) of the multiple index values ​​S(y, x). Alternatively, the acquisition condition determination unit 212 may use the variation itself as the reliability.

[0088] The acquisition condition determination unit 212 may use any method for calculating the reliability, significance, variance, etc. of the analysis results by the analysis unit 213 to calculate a predetermined value from the analysis results, and then calculate the reliability based on the predetermined value, or may use the predetermined value itself as the reliability.

[0089] (Step S305) Here, the manufacturing data analysis device 200 determines, via the acquisition condition determination unit 212, whether the reliability of the analytical manufacturing data 130 is equal to or less than a predetermined threshold. This threshold can be set to any value by the user of the manufacturing data analysis device 200. If this determination condition is met (YES in step S305), the process proceeds to step S306. On the other hand, if this determination condition is not met (NO in step S305), the process proceeds to step S309.

[0090] (Step S306) In this case, the manufacturing data analyzing device 200 determines the second data acquisition conditions AC2 using the acquisition condition determination unit 212 based on the analytical manufacturing data 130. Step S306 is similar to step S103.

[0091] (Step S307) Next, the manufacturing data analysis device 200 acquires the additional analysis manufacturing data 140 from the manufacturing data 110 included in the manufacturing DB 100 based on the second data acquisition condition AC2 using the acquisition unit 211. Step S307 is similar to step S104.

[0092] (Step S308) Next, the manufacturing data analysis device 200 analyzes the additional analysis manufacturing data 140 using the analysis unit 213, and calculates an analysis result (second analysis result) for the additional analysis manufacturing data 140. The calculation method for the second analysis result is the same as the calculation method for the first analysis result. The analysis unit 213 outputs the second analysis result to the output data generation unit 214.

[0093] (Step S309) Next, manufacturing data analysis device 200 generates output data 250 including the analysis results using output data generation unit 214. Step S309 is similar to step S106. After this process, manufacturing data analysis device 200 ends the series of processes.

[0094] The manufacturing data analysis system 1 according to the first embodiment has been described above. According to the first embodiment, the manufacturing data analysis device 200 outputs an analysis result based on the second data acquisition conditions AC2 instead of the first data acquisition conditions AC1 input by the user. This allows the manufacturing data analysis device 200 to improve the reliability of the analysis result regarding the relationship between the target manufacturing condition data x and the target quality data y, for example, when the number of data items having some of the possible values ​​of the target manufacturing condition data x is relatively small.

[0095] Furthermore, according to the first embodiment, the manufacturing data analysis device 200 determines second data acquisition conditions AC2 for first data acquisition conditions AC1 input by the user, selects one or both of the first and second analysis results, and generates output data 250. This allows the manufacturing data analysis device 200 to present both analysis results with different reliability regarding the relationship between the target manufacturing condition data x and the target quality data y, for example, when the number of data having some of the possible values ​​of the target manufacturing condition data x is relatively small. Alternatively, the manufacturing data analysis device 200 can selectively present an analysis result with a higher reliability.

[0096] Furthermore, according to the first embodiment, the manufacturing data analysis device 200 calculates the reliability (first reliability) of the analytical manufacturing data 130 acquired under the first data acquisition conditions AC1 and determines the second data acquisition conditions AC2 based on this reliability. The manufacturing data analysis device 200 also calculates the reliability (second reliability) of the additional analytical manufacturing data 140 acquired under the second data acquisition conditions AC2. This allows the manufacturing data analysis device 200 to quantify the difference between the analysis result (first analysis result) of the analytical manufacturing data 130 and the analysis result (second analysis result) of the additional analytical manufacturing data 140 as reliability and present the reliability to the user. This allows the user to objectively evaluate the reliability of each of the first analysis result and the second analysis result. As described above, the manufacturing data analysis device 200 can assist the user in monitoring manufacturing data.

[0097] (Second embodiment) 6 is a block diagram showing an example of the functional configuration of a manufacturing data analysis system 1 according to the second embodiment. Unlike the first embodiment, a manufacturing data analysis device 200 according to the second embodiment acquires a first data acquisition condition AC1, a manufacturing condition data group X, and a quality data group Y as parameters 120. The configuration of the manufacturing data analysis system 1 according to the second embodiment is the same as that of the first embodiment.

[0098] 7 is a flow diagram showing an example of the operation of the manufacturing data analyzing apparatus 200 according to the second embodiment. Similar to the example of the operation of FIG. 2, this example of the operation can be started when a user of the manufacturing data analyzing apparatus 200 or an external system inputs parameters 120 into the manufacturing data analyzing apparatus 200.

[0099] (Step S401) First, the manufacturing data analyzing device 200 acquires, via the acquiring unit 211, the first data acquisition condition AC1, the manufacturing condition data group X, and the quality data group Y as the parameters 120.

[0100] The manufacturing condition data group X is a group (set) including one or more pieces of manufacturing condition data. For ease of explanation, the number of manufacturing condition data (number of items) included in the manufacturing condition data group X will be represented as "M". Furthermore, each piece of manufacturing condition data included in the manufacturing condition data group X will be represented as "xj" (variable j=1...M; j is an integer).

[0101] The quality data group Y is a group (set) containing one or more quality data. For ease of explanation, the number of quality data (number of items) contained in the quality data group Y will be represented as "N". Furthermore, each quality data item contained in the quality data group Y will be represented as "yi" (variable i = 1...N; i is an integer).

[0102] (Step S402) Next, the manufacturing data analyzing device 200 sets the variable i to 1 (i=1) by the analysis unit 213. Specifically, the analysis unit 213 sets the variable i to 1 for the quality data yi included in the quality data group Y.

[0103] (Step S403) Subsequently, the manufacturing data analyzing device 200 sets the variable j to 1 (j=1) by the analysis unit 213. Specifically, the analysis unit 213 sets the variable j to 1 for the manufacturing condition data xj included in the manufacturing condition data group X.

[0104] (Step S404) Next, the manufacturing data analysis device 200 acquires analytical manufacturing data 130 from the manufacturing data 110 included in the manufacturing DB 100 based on the first data acquisition condition AC1 using the acquisition unit 211. When this step is executed for the first time, the acquisition unit 211 acquires analytical manufacturing data 130 for analyzing the target, targeting the manufacturing condition data x1 and the quality data y1.

[0105] (Step S405) Next, the manufacturing data analyzing device 200 causes the acquisition condition determination unit 212 to determine the second data acquisition conditions AC2 based on the manufacturing condition data xj included in the analytical manufacturing data 130. At this time, the acquisition condition determination unit 212 may determine the second data acquisition conditions AC2 based on the values ​​that the manufacturing condition data xj can take, as described above.

[0106] (Step S406) Next, the manufacturing data analysis device 200 acquires the additional analysis manufacturing data 140 from the manufacturing data 110 included in the manufacturing DB 100 based on the second data acquisition condition AC2 using the acquisition unit 211. When this step is executed for the first time, the acquisition unit 211 acquires the additional analysis manufacturing data 140 for analyzing the target, targeting the manufacturing condition data x1 and the quality data y1.

[0107] (Step S407) Next, the manufacturing data analysis device 200 calculates a first analysis result (index value S1(yi, xj)) from the analytical manufacturing data 130 using the analysis unit 213. The index value S1(yi, xj) represents, for example, the strength of the relationship between the manufacturing condition data xj and the quality data yi. The index value S1(yi, xj) is also referred to as a first index value. The analysis process in step S407 is similar to the analysis process in step S105.

[0108] (Step S408) Next, the manufacturing data analysis device 200 calculates a second analysis result (index value S2(yi, xj)) from the additional analysis manufacturing data 140 using the analysis unit 213. The index value S2(yi, xj) represents, for example, the strength of the relationship between the manufacturing condition data xj and the quality data yi. The index value S2(yi, xj) is also referred to as a second index value. The analysis process in step S408 is similar to the analysis process in step S105.

[0109] (Step S409) Subsequently, the manufacturing data analyzing device 200 causes the output data generating unit 214 to select either or both of the first analysis result and the second analysis result, and includes the selected analysis result in the output data 250. The selection process in step S409 is similar to the selection process in step S106.

[0110] (Step S410) Next, the manufacturing data analyzing device 200 controls the amount of information and display priority of the selected analysis result using the output data generating unit 214. Specifically, the analyzing unit 213 may change the amount of information and display priority of the selected analysis result based on the index values ​​S1(yi, xj) and S2(yi, xj) related to the analysis result. This changes the display mode of the image displaying each analysis result (analysis result display image).

[0111] (Step S411) Next, the analysis unit 213 of the manufacturing data analysis device 200 increments the variable j by 1 (j=j+1).

[0112] (Step S412) Here, the manufacturing data analyzing device 200 determines, via the analysis unit 213, whether the variable j is greater than M (j>M?). If this determination condition is met (YES in step S412), the process proceeds to step S413. On the other hand, if this determination condition is not met (NO in step S412), the process returns to step S404.

[0113] (Step S413) In this case, the analysis unit 213 of the manufacturing data analysis device 200 increments the variable i by 1 (i=i+1).

[0114] (Step S414) Here, the manufacturing data analyzing device 200 determines, via the analysis unit 213, whether the variable i is greater than N (i>N?). If this determination condition is met (YES in step S414), the process proceeds to step S415. On the other hand, if this determination condition is not met (NO in step S414), the process returns to step S403.

[0115] (Step S415) In this case, manufacturing data analysis device 200 generates output data 250 including the analysis results using output data generation unit 214. After this process, manufacturing data analysis device 200 ends the series of processes.

[0116] 8 is a diagram showing an example of the overall display of an image based on output data 250 according to the second embodiment. Here, an analysis target image 400 that identifies an analysis target is displayed within the entire display area 350 of the display device 300. First analysis result display images 410, 420, 430, and 440 that include first analysis results for each piece of quality data yi are displayed below the analysis target image 400. Preferably, these first analysis result display images 410, 420, 430, and 440 are arranged side by side in the entire display area 350 so that the user can easily compare the first analysis results for each piece of quality data yi.

[0117] An area 411 containing the name of the specific quality data yi (test item Y7) that was the subject of analysis is displayed in the upper left corner of the first analysis result display image 410. A first analysis information image 412 containing first analysis information is displayed on the left side of the first analysis result display image 410. The first analysis information is, for example, numerical values ​​or a chart relating to the degree of abnormality of the quality data yi. An area 413 containing a first index value (0.1) is displayed in the upper right corner of the first analysis result display image 410.

[0118] First analysis result display images 510, 520, and 530 including the first analysis results for each piece of manufacturing condition data xj for the specific quality data yi (inspection item Y7) that was the analysis target are displayed on the right side of first analysis result display image 410. Preferably, these first analysis result display images 510, 520, and 530 are arranged in parallel in first analysis result display image 410 so that the user can easily compare the first analysis results for each piece of manufacturing condition data xj.

[0119] An area 511 containing the name of the specific manufacturing condition data xj that was the subject of analysis (factor C5) is displayed in the upper left corner of the first analysis result display image 510. A second analysis information image 512 containing second analysis information is displayed on the left side of the first analysis result display image 510. The second analysis information is, for example, numerical values ​​or a chart regarding the likelihood that the manufacturing condition data xj is the cause of an abnormality in the quality data yi. An area 513 containing a first index value (0.8) is displayed in the upper right corner of the first analysis result display image 510.

[0120] A second analysis result display image 610 including the second analysis results relating to the specific quality data yi (inspection item Y7) and specific manufacturing condition data xj (factor C5) that were the subject of analysis is displayed on the right side of the first analysis result display image 510. In this example, the second analysis result display image 610 is in the shape of a speech bubble that refers to the second analysis information image 512.

[0121] An additional analysis information image 611 containing information (additional analysis information) relating to the results of additional analysis of the second analysis information using the additional analysis manufacturing data 140 is displayed in the center of the second analysis result display image 610. An area 612 containing a second index value (0.7) is displayed in the upper right corner of the second analysis result display image 610.

[0122] Note that different amounts of information and display priorities are set for each of the first analysis result display images 410, 420, 430, and 440. First, the first analysis result display image 410 is set to "large amount of information, high display priority." Second, the first analysis result display image 420 is set to "medium amount of information, medium display priority." Third, the first analysis result display image 430 is set to "medium amount of information, low display priority." Fourth, the first analysis result display image 440 is set to "small amount of information, low display priority." The display manner of each of these first analysis result display images 410, 420, 430, and 440 is changed based on the amount of information and display priority set for each.

[0123] Similarly, different amounts of information and display priorities are set for each of the first analysis result display images 510, 520, and 530. First, the first analysis result display image 510 is set to "large amount of information, display priority: high." Second, the first analysis result display image 520 is set to "small amount of information, display priority: medium." Third, the first analysis result display image 530 is set to "none amount of information, display priority: low." The display manner of each of these first analysis result display images 510, 520, and 530 is changed based on the display priority and amount of information set for each.

[0124] In this example, the display area of ​​each of the first analysis result display images 410, 420, 430, 440, 510, 520, and 530 is enlarged so that the more information can be displayed, the greater the amount of information set for each image. For example, the display area of ​​the first analysis result display image 410 is enlarged compared to the other first analysis result display images 420, 430, and 440. Similarly, the display area of ​​the first analysis result display image 510 is enlarged compared to the other first analysis result display images 520 and 530.

[0125] On the other hand, the first analysis result display images 410, 420, 430, 440, 510, 520, and 530 are arranged at a higher level in the entire display area 350 the higher the display priority set for each image, so that the user can view the image preferentially.

[0126] Furthermore, the first analysis result display images 410, 420, 430, 440, 510, 520, and 530 may change the display manner (e.g., type, color, and thickness) of the borders of the areas indicating the names of the quality data yi and the manufacturing condition data xi and the borders of the areas indicating the index values, depending on the magnitude of the index value (S1(yi, xj)) included in each. For example, the colors of the borders of both areas in the first analysis result display images 410, 420, 430, and 440 may be changed, respectively, to red, yellow, black, and gray. Similarly, the colors of the borders of both areas in the first analysis result display images 510, 520, and 530 may be changed, respectively, to red, yellow, and gray.

[0127] Similarly, in the second analysis result display image 610, the display manner of the border of the area 612 indicating the index value (S2(yi,xj)) may be changed according to the size of the index value included in the image 610. For example, the color of the border of the area 612 is changed to red.

[0128] Furthermore, among the first analysis result display images 410, 420, 430, and 440, the index value (<0.001) included in the first analysis result display image 440 is the smallest. Similarly, among the first analysis result display images 510, 520, and 530, the index value (<0.1) included in the first analysis result display image 530 is the smallest. That is, because the first analysis result display images 440 and 530 include relatively insignificant information, the text in each display area may be displayed lightly. That is, the opacity of the text indicating each analysis result may be changed depending on the index value associated with each analysis result.

[0129] 9 is a diagram showing a display example of a part of an image based on the output data 250 according to the second embodiment. Here, the additional analysis information image 611 shown in FIG. 8 is shown in an enlarged form.

[0130] The additional analysis information image 611 is a histogram in which the horizontal axis represents the value of specific manufacturing condition data xj (factor C5) and the vertical axis represents the value of specific quality data yi (inspection item Y7). In the additional analysis information image 611, a predetermined threshold TH1 for the value of the quality data yi and another threshold TH2 smaller than this threshold TH1 are indicated by dashed lines. In this example, if the value of the quality data yi is within the range between the thresholds TH1 and TH2, it is determined to be a normal value. On the other hand, if the value of the quality data yi is outside the range between the thresholds TH1 and TH2, it is determined to be an abnormal value. Each value of the quality data yi corresponds to a circle data point 611A.

[0131] In the histogram shown by the additional analysis information image 611, all data points 611A belonging to classes determined to have no abnormal values ​​are displayed in a predetermined color (e.g., gray). On the other hand, all data points 611A belonging to classes determined to have abnormal values ​​are highlighted in a predetermined color (e.g., red) so that they can be easily identified. This display mode allows a user viewing the additional analysis information image 611 to easily and intuitively recognize classes that have abnormal values.

[0132] The manufacturing data analysis system 1 according to the second embodiment has been described above. According to the second embodiment, the manufacturing data analysis device 200 calculates a first analysis result for the analytical manufacturing data 130 acquired under the first data acquisition conditions AC1 and a second analysis result for the additional analytical manufacturing data 140 acquired under the second data acquisition conditions AC2. The manufacturing data analysis device 200 then selects at least one of the first and second analysis results and generates output data 250 including the selected analysis result. The manufacturing data analysis device 200 then generates output data 250 with the amount of information and display priority of the selected analysis result adjusted based on an index value indicating the strength of the relationship between the manufacturing condition data xj and the quality data yi associated with the selected analysis result.

[0133] Therefore, the manufacturing data analysis device 200 according to the second embodiment can preferentially present a specific analysis result that has a relatively strong correlation between the multiple analysis results obtained by combining multiple manufacturing condition data and multiple quality data. Furthermore, the manufacturing data analysis device 200 can simultaneously present additional analysis results for the specific analysis result. By simultaneously comparing both analysis results, the user can recognize a more accurate analysis result.

[0134] (Third embodiment) 10 is a block diagram showing an example of the functional configuration of a manufacturing data analysis system 1 according to the third embodiment. Unlike the first embodiment, the manufacturing data analysis device 200 according to the third embodiment acquires first data acquisition conditions AC1, target manufacturing condition data x, a comparison manufacturing condition data group X', and a quality data group Y as parameters 120. Furthermore, the manufacturing data analysis device 200 according to the third embodiment includes a determination unit 215.

[0135] The comparative manufacturing condition data group X' is a group (set) including one or more manufacturing condition data to be compared with the target manufacturing condition data x. For example, one or more manufacturing condition data excluding the target manufacturing condition data x is specified in the comparative manufacturing condition data group X' from the plurality of manufacturing condition data included in the manufacturing data 110. For ease of explanation, the number of manufacturing condition data (number of items) included in the comparative manufacturing condition data group X' will be represented as "M" below. Furthermore, each piece of manufacturing condition data (comparison manufacturing condition data) included in the comparative manufacturing condition data group X' will be represented as "x'j" (variable j = 1...M; j is an integer).

[0136] As described above, the target manufacturing condition data x is the manufacturing condition data that the user pays attention to, and is also the manufacturing condition data that is the target of analysis by the manufacturing data analysis device 200. Also, as described above, the quality data group Y is a group (set) that includes one or more quality data. For ease of explanation, the number of quality data (number of items) included in the quality data group Y will be represented as "N" below. Also, each piece of quality data included in the quality data group Y will be represented as "yi" (variable i = 1...N; i is an integer).

[0137] The acquisition unit 211 acquires, based on the parameters 120 input from outside, the manufacturing data 110 included in the manufacturing DB 100 under the first data acquisition conditions AC1, the manufacturing condition data group X including the target manufacturing condition data x and the comparison manufacturing condition data group X', and the analytical manufacturing data 130 including the quality data group Y. The acquisition unit 211 outputs the analytical manufacturing data 130 to the acquisition condition determination unit 212 and the analysis unit 213.

[0138] The analysis unit 213 analyzes the analytical manufacturing data 130 and the additional analytical manufacturing data 140 input from the acquisition unit 211, and calculates the degree of influence S(yi, x) that the target manufacturing condition data x included in the manufacturing condition data group X has on each piece of quality data yi included in the quality data group Y. Similarly, the analysis unit 213 calculates the degree of influence S(yi, x'j) that the comparative manufacturing condition data x'j included in the comparative manufacturing condition data group X' has on each piece of quality data yi included in the quality data group Y. The analysis unit 213 outputs the degrees of influence S(yi, x) and S(yi, x'j) to the determination unit 215 and the output data generation unit 214 as analysis results.

[0139] In this embodiment, the influence S(yi,x) is the same as the index value S(yi,x) described above. That is, the influence S(yi,x) may be an index value representing the strength of the relationship between the target manufacturing condition data x and the target quality data y.

[0140] The determination unit 215 determines that one or more of the influences S(yi,x), S(yi,x'j) input from the analysis unit 213 satisfy a predetermined determination condition when one or more of the influences S(yi,x), S(yi,x'j) is equal to or greater than a predetermined threshold. Conversely, the determination unit 215 determines that none of the influences S(yi,x), S(yi,x'j) satisfy a predetermined determination condition when any of the influences S(yi,x), S(yi,x'j) is less than a predetermined threshold. This determination condition or threshold may be the same for each of the influences S(yi,x) and S(yi,x'j). The determination unit 215 outputs the determination results for each of the influences S(yi, x) and S(yi, x′j) to the output data generation unit 214.

[0141] The output data generation unit 214 generates output data 250 based on the analysis result input from the analysis unit 213 and the judgment result input from the judgment unit 215. For example, when there is one or more quality data yi included in the quality data group Y, for which the target manufacturing condition data x or the comparative manufacturing condition data x'j has given influence levels S(yi,x) or S(yi,x'j) that satisfy a predetermined judgment condition or threshold, the output data generation unit 214 generates output data 250 including content related to at least one of the target manufacturing condition data x or the comparative manufacturing condition data x'j, the quality data yi, and the influence levels S(yi,x) or S(yi,x'j). The judgment condition or threshold may be the same for each of the influence levels S(yi,x) and S(yi,x'j). Specifically, when the analysis result relating to the target manufacturing condition data x and the predetermined quality data yi is associated with a judgment result indicating that “the influence S(yi, x) satisfies the first judgment condition,” the output data generation unit 214 may include the analysis result in the output data 250. Similarly, when the analysis result relating to the comparison manufacturing condition data x′j and the predetermined quality data yi is associated with a judgment result indicating that “the influence S(yi, x′j) satisfies the second judgment condition,” the output data generation unit 214 may include the analysis result in the output data 250. The output data generation unit 214 outputs the output data 250 to the display device 300.

[0142] 11 is a block diagram showing an example of the operation of the manufacturing data analyzing apparatus 200 according to the third embodiment. Similar to the example of the operation of FIG. 2, this example of the operation can be started when a user of the manufacturing data analyzing apparatus 200 or an external system inputs parameters 120 to the manufacturing data analyzing apparatus 200.

[0143] (Step S501) First, the manufacturing data analyzing device 200 acquires, via the acquiring unit 211, the first data acquisition condition AC1, the target manufacturing condition data x, the comparative manufacturing condition data group X', and the quality data group Y as the parameters 120.

[0144] (Step S502) Next, the manufacturing data analysis device 200 causes the acquisition unit 211 to acquire analytical manufacturing data 130 from the manufacturing data 110 included in the manufacturing DB 100 based on the parameters 120.

[0145] (Step S503) Subsequently, the manufacturing data analyzing device 200 sets the variable i to 1 (i=1) by the analysis unit 213. Specifically, the analysis unit 213 sets the variable i to 1 for the quality data yi included in the quality data group Y.

[0146] (Step S504) Subsequently, the manufacturing data analyzing device 200 sets the variable j to 1 (j=1) by the analysis unit 213. Specifically, the analysis unit 213 sets the variable j to 1 for the comparative manufacturing condition data x'j included in the comparative manufacturing condition data group X'.

[0147] (Step SUB1) Next, the manufacturing data analysis device 200 causes the analysis unit 213 to execute an analysis-use manufacturing data analysis process.

[0148] (Step S505) Next, the manufacturing data analysis device 200 determines, via the acquisition condition determination unit 212, second data acquisition conditions AC2 based on the manufacturing condition data xj included in the analytical manufacturing data 130. The "manufacturing condition data xj" refers to the comparative manufacturing condition data x'j included in the comparative manufacturing condition data group X' and the target manufacturing condition data x. In other words, the acquisition condition determination unit 212 may determine the second data acquisition conditions AC2 based on the comparative manufacturing condition data x'j and the target manufacturing condition data x included in the analytical manufacturing data 130.

[0149] (Step S506) Next, the acquisition unit 211 of the manufacturing data analysis device 200 acquires the additional analysis manufacturing data 140 based on the second data acquisition condition AC2.

[0150] (Step SUB2) Next, the manufacturing data analysis device 200 causes the analysis unit 213 to execute an analysis process for the additional analysis manufacturing data.

[0151] (Step S507) Subsequently, the manufacturing data analyzing device 200 causes the output data generating unit 214 to select either or both of the first analysis result and the second analysis result, and includes the selected analysis result in the output data 250.

[0152] (Step S508) Next, the analysis unit 213 of the manufacturing data analyzing device 200 increments the variable j by 1 (j=j+1).

[0153] (Step S509) Here, the manufacturing data analyzing device 200 determines, via the analysis unit 213, whether the variable j is greater than M (j>M?). If this determination condition is met (YES in step S509), the process proceeds to step S510. On the other hand, if this determination condition is not met (NO in step S509), the process returns to step SUB1.

[0154] (Step S510) In this case, the manufacturing data analyzing device 200 causes the analysis unit 213 to increment the variable i by 1 (i=i+1).

[0155] (Step S511) Here, the manufacturing data analyzing device 200 determines, via the analysis unit 213, whether the variable i is greater than N (i>N?). If this determination condition is met (YES in step S511), the process proceeds to step S512. On the other hand, if this determination condition is not met (NO in step S511), the process returns to step S504.

[0156] (Step S512) In this case, manufacturing data analysis device 200 generates output data 250 including the analysis results using output data generation unit 214. After this process, manufacturing data analysis device 200 ends the series of processes.

[0157] 12 is a block diagram showing an example of manufacturing data analysis processing according to the third embodiment. This processing is a subroutine related to steps SUB1 and SUB2 in FIG. 11. That is, the same processing is performed on the analytical manufacturing data 130 and the additional analytical manufacturing data 140.

[0158] (Step S601) First, the analysis unit 213 of the manufacturing data analysis device 200 calculates the influence S(yi, x) of the target manufacturing condition data x on the quality data yi.

[0159] (Step S602) Here, the manufacturing data analyzing device 200 determines, via the determination unit 215, whether or not the influence S(yi,x) satisfies a predetermined determination condition (first determination condition). This determination condition may be a predetermined threshold (first threshold). That is, the determination unit 215 may determine that the influence S(yi,x) satisfies the predetermined determination condition when the influence S(yi,x) is equal to or greater than the predetermined threshold. If this determination condition is satisfied (YES in step S602), the process proceeds to step S603. On the other hand, if this determination condition is not satisfied (NO in step S602), the process proceeds to step S604.

[0160] (Step S603) In this case, the manufacturing data analysis device 200 causes the output data generation unit 214 to include in the output data 250 the contents (ie, analysis results) related to the target manufacturing condition data x, the quality data yi, and the impact S(yi,x).

[0161] (Step S604) Subsequently, the analysis unit 213 of the manufacturing data analysis device 200 calculates the influence S(yi, x'j) of the comparative manufacturing condition data x'j on the quality data yi.

[0162] (Step S605) Here, the manufacturing data analysis device 200 determines, via the determination unit 215, whether or not the influence S(yi, x'j) satisfies a predetermined determination condition (second determination condition). This determination condition may be a predetermined threshold (second threshold). That is, the determination unit 215 may determine that the influence S(yi, x'j) satisfies the predetermined determination condition if the influence S(yi, x'j) is equal to or greater than the predetermined threshold. If this determination condition is met (YES in step S605), the process proceeds to step S606. On the other hand, if this determination condition is not met (NO in step S605), the manufacturing data analysis device 200 ends the manufacturing data analysis process.

[0163] (Step S606) In this case, the manufacturing data analysis device 200 causes the output data generation unit 214 to include the contents (i.e., analysis results) related to the comparative manufacturing condition data x'j, the quality data yi, and the impact S(yi, x'j) in the output data 250. After this step, the manufacturing data analysis device 200 ends the series of processes.

[0164] 13 is a diagram showing a first display example of an image based on output data 250 according to the third embodiment. Here, a first display image 710 including analysis results for certain quality data yi and a second display image 720 including analysis results for another quality data yi are displayed within the entire display area 350 of the display device 300. Preferably, the first display image 710 and the second display image 720 are arranged side by side in the entire display area 350 so that the user can easily compare the analysis results of both.

[0165] The first display image 710 includes an area 711 in the upper left corner and areas 712, 713, 714, and 715 near the center. Area 711 displays the data name (dimension (vertical)) of the predetermined quality data yi that is the subject of analysis (investigation). Area 712 displays the influence S(yi, x) (influence 80) that the target manufacturing condition data x (component 1) that is the subject of analysis has on the predetermined quality data yi.

[0166] In area 713, the data name (Component 1) of the target manufacturing condition data x is displayed in the upper left corner, and a scatter diagram based on the target manufacturing condition data x and the quality data yi is displayed near the center as the analysis results of both data. In this scatter diagram, the horizontal axis represents each value of the target manufacturing condition data x (Component 1G, Component 1R, Component 1Y), and the vertical axis represents each value of the quality data yi. In addition, a first threshold TH1 related to the value of the quality data yi and a second threshold TH2 smaller than the first threshold TH1 are displayed by dashed lines. In particular, for values ​​of the quality data yi that are equal to or greater than the first threshold TH1, the data points representing those values ​​are highlighted by being surrounded by a frame of a predetermined color (e.g., red). This display mode allows the user to easily recognize abnormal values ​​of the quality data yi.

[0167] Area 714 displays the impact S(yi, x'j) (impact 90) that the comparative manufacturing condition data x'j (component 3) has on the predetermined quality data yi. Note that various character modifications (e.g., font, color, size) may be applied so that the characters representing "impact 90" are highlighted.

[0168] In area 715, the data name (component 3) of the comparative manufacturing condition data x'j is displayed in the upper left corner, and a scatter diagram based on the comparative manufacturing condition data x'j and the quality data yi is displayed near the center as the analysis results of both data. In this scatter diagram, the horizontal axis indicates each value of the comparative manufacturing condition data x'j (component 3B, component 3R, component 3G), and the vertical axis indicates each value of the quality data yi.

[0169] A second analysis result display image 810 including the second analysis result relating to the specific quality data yi (dimension (vertical)) and the specific comparative manufacturing condition data x'j (component 3) that were the subject of analysis is displayed on the right side of area 715. In this example, second analysis result display image 810 is in the shape of a speech bubble that refers to area 715.

[0170] The second analysis result display image 810 includes an area 811 at the top and an area 812 near the center. Area 811 displays the influence S(yi, x'j) (influence 50) that the comparative manufacturing condition data x'j (component 3) that was the subject of analysis has on the predetermined quality data yi.

[0171] Area 812 displays the data name (component 3) of the comparative manufacturing condition data x'j in the upper left corner, and displays a scatter plot based on the comparative manufacturing condition data x'j and the quality data yi near the center as the analysis results of both data. Here, the scatter plot in area 812 has an increased number of data points related to the value "3R" compared to the scatter plot in area 715. In other words, as a result of the additional analysis that increased the number of data points, the recalculated value of the impact S(yi, x'j) has changed from "90" to "50."

[0172] On the other hand, the second display image 720 displays the data name (weight) of the quality data yi at the left end, and displays the influence S(yi,x) (influence 50) of the target manufacturing condition data x (component 1) near the center. Here, the user may select the second display image 720 to display detailed analysis results.

[0173] Fig. 14 is a diagram showing a second display example of an image based on output data 250 according to the third embodiment. Unlike the display example of Fig. 13, the display example of Fig. 14 displays the reliability of each analysis result in addition to the values ​​of the influences S(yi,x) and S(yi,x'j). The reliability may be calculated by the method described above in the manufacturing data analysis process described above.

[0174] First, area 712 displays the reliability (70%) of the analysis results of the target manufacturing condition data x and the quality data yi. Second, area 714 displays the reliability (10%) of the analysis results of the comparative manufacturing condition data x'j and the quality data yi. Third, area 811 displays the reliability (80%) of the additional analysis results of the comparative manufacturing condition data x'j and the quality data yi. This display mode allows the user to objectively evaluate the reliability of each analysis result.

[0175] Fig. 15 is a diagram showing a third display example of an image based on output data 250 according to the third embodiment. Unlike the display example of Fig. 13, in the display example of Fig. 15, a second analysis result display image 810 includes areas 813 and 814 in addition to areas 811 and 812.

[0176] Area 813 displays the degree of influence S(yi,x) (degree of influence 80) that the target manufacturing condition data x (component 1) that is the analysis target (survey target) has on the predetermined quality data yi.

[0177] Area 814 displays the data name (component 1) of the target manufacturing condition data x in the upper left corner, and a scatter plot based on the target manufacturing condition data x and the quality data yi as the results of the additional analysis of both data is displayed near the center. This scatter plot shows the respective values ​​of the target manufacturing condition data x (component 1B, component 1G, component 1R, component 1Y), and the vertical axis shows the respective values ​​of the quality data yi. Here, in the scatter plot of area 814, data related to the new value "1B" has been added compared to the scatter plot of area 713. In other words, as a result of the additional analysis with the new data added, the value of the recalculated impact S(yi, x) has not changed from "80."

[0178] The manufacturing data analysis system 1 according to the third embodiment has been described above. According to the third embodiment, the manufacturing data analysis device 200 can detect quality data yi for which the influence S(yi, x), S(yi, x'j) of the target manufacturing condition data x or the comparison manufacturing condition data x'j specified by the user is relatively large, among all quality data yi specified by the user. The manufacturing data analysis device 200 can reduce the number of displayed data by not outputting analysis results for quality data for which the influence of a specific manufacturing condition is relatively small. This allows the manufacturing data analysis device 200 to reduce the time and effort required for the user to investigate the influence of a specific manufacturing condition on all quality data and the time and effort required for interpreting the investigation results. Furthermore, the manufacturing data analysis device 200 according to the third embodiment can achieve the same effects as the first embodiment.

[0179] 16 is a block diagram showing an example of the hardware configuration of the manufacturing data analysis system 1 according to the first to third embodiments. In particular, the manufacturing data analysis device 200 includes a processing circuit 210, a memory 220, an input IF 230, and a communication IF 240 as hardware resources.

[0180] The processing circuitry 210 controls the operation of the manufacturing data analysis device 200. The processing circuitry 210 has processors such as a central processing unit (CPU), a micro processing unit (MPU), and a graphics processing unit (GPU) as hardware resources. For example, the processing circuitry 210 executes each program deployed in the memory 220 via at least one processor, thereby realizing each unit corresponding to each program (acquisition unit 211, acquisition condition determination unit 212, analysis unit 213, output data generation unit 214, and judgment unit 215). Note that each unit can be realized by the processing circuitry 210 consisting of a single processor or by the processing circuitry 210 combining multiple processors.

[0181] The memory 220 stores information such as data and programs used by the processing circuit 210. The memory 220 has a semiconductor memory element such as a random access memory (RAM) as a hardware resource. The memory 220 may be a drive device that reads and writes information from and to an external storage device such as a magnetic disk (floppy disk, hard disk), a magneto-optical disk (MO), an optical disk (CD, DVD, Blu-ray), a flash memory (USB flash memory, memory card, SSD), or a magnetic tape. The storage area of ​​the memory 220 may be located inside the manufacturing data analysis device 200 or in an external storage device. The memory 220 is an example of a storage unit.

[0182] The input IF 230 is an interface that receives input from a user of the manufacturing data analysis device 200, converts the received input into an electrical signal, and outputs the electrical signal to the processing circuit 210. The input IF 230 can be a physical operation part such as a mouse, keyboard, trackball, switch, button, joystick, touchpad, touch panel display, or microphone. The input IF 230 may also be a device that receives input from an external input device separate from the manufacturing data analysis device 200, converts the received input into an electrical signal, and outputs the electrical signal to the processing circuit 210. The input IF 230 may also receive input of parameters 120 by a user. The input IF 230 is an example of an input unit.

[0183] The communication IF 240 is an interface for communicating various types of data between the manufacturing data analysis device 200 and an external device. Any communication standard can be used for this data communication. The communication IF 240 is connected to the manufacturing DB 100 and the display device 300 so as to be able to communicate with them. The communication IF 240 is an example of a communication unit.

[0184] The display device 300 displays data generated by the manufacturing data analysis device 200, data stored in the memory 220, and the like. The display device 300 may be, for example, a cathode ray tube (CRT) display, a liquid crystal display (LCD), a plasma display, an organic electroluminescence display (OLED), or a display such as a tablet terminal. The display device 300 may be included in the manufacturing data analysis device 200. The display device 300 is an example of a display unit.

[0185] 13 to 15, each value (component 1B, component 1G, component 1R, component 1Y) included in the target manufacturing condition data x (component 1) is marked with a "gear" icon, while each value (component 3B, component 3R, component 3G) included in the comparison manufacturing condition data x'j (component 3) is marked with a "spiral" icon. These icons are marked with each value for the convenience of explaining the operation of the manufacturing data analysis device 200 according to the third embodiment. In other words, these icons do not need to be actually displayed.

[0186] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0187] 1... manufacturing data analysis system, 110... manufacturing data, 120... parameters, 130... manufacturing data for analysis, 140... manufacturing data for additional analysis, 200... manufacturing data analysis device, 210... processing circuit, 211... acquisition unit, 212... acquisition condition determination unit, 213... analysis unit, 214... output data generation unit, 215... judgment unit, 220... memory, 250... output data, 300... display device, 350... entire display area, 400... image to be analyzed, 410 ,420,430,440,510,520,530...First analysis result display image, 411,413,511,513,612,711,712,713,714,715,811,812,813,814...Area, 412...First analysis information image, 512...Second analysis information image, 610,810...Second analysis result display image, 611...Additional analysis information image, 611A...Data point, 710...First display image, 720...Second display image

Claims

1. a first acquisition unit that acquires, from manufacturing data related to a plurality of products, first manufacturing data including manufacturing condition data related to values ​​indicating manufacturing conditions for each of the products and quality data related to values ​​indicating quality for each of the products under first acquisition conditions; an acquisition condition determination unit that determines second acquisition conditions different from the first acquisition conditions so as to reduce bias in distribution of a plurality of values ​​included in the manufacturing condition data or the quality data in the first manufacturing data; a second acquisition unit that acquires second manufacturing data including the manufacturing condition data and the quality data from the manufacturing data under the second acquisition conditions; an analysis unit that analyzes the second manufacturing data to calculate an analysis result regarding the relationship between the manufacturing condition data and the quality data; an output data generation unit that generates output data including the analysis result; A manufacturing data analysis device comprising:

2. a first acquisition unit that acquires, from manufacturing data related to a plurality of products, first manufacturing data including manufacturing condition data related to values ​​indicating manufacturing conditions for each of the products and quality data related to values ​​indicating quality for each of the products under first acquisition conditions; an acquisition condition determination unit that determines, when the manufacturing condition data or the quality data is qualitative data, a second acquisition condition different from the first acquisition condition so that the number of data for each type of value included in the qualitative data is equal to or greater than a predetermined threshold; a second acquisition unit that acquires second manufacturing data including the manufacturing condition data and the quality data from the manufacturing data under the second acquisition conditions; an analysis unit that analyzes the second manufacturing data to calculate an analysis result regarding the relationship between the manufacturing condition data and the quality data; an output data generation unit that generates output data including the analysis result; A manufacturing data analysis device comprising:

3. a first acquisition unit that acquires, from manufacturing data related to a plurality of products, first manufacturing data including manufacturing condition data related to values ​​indicating manufacturing conditions for each of the products and quality data related to values ​​indicating quality for each of the products under first acquisition conditions; an acquisition condition determination unit that determines a second acquisition condition different from the first acquisition condition, when the manufacturing condition data or the quality data is quantitative data, so that the frequency of each class of values ​​included in the quantitative data is equal to or greater than a predetermined threshold; a second acquisition unit that acquires second manufacturing data including the manufacturing condition data and the quality data from the manufacturing data under the second acquisition conditions; an analysis unit that analyzes the second manufacturing data to calculate an analysis result regarding the relationship between the manufacturing condition data and the quality data; an output data generation unit that generates output data including the analysis result; A manufacturing data analysis device comprising:

4. a first acquisition unit that acquires, from manufacturing data related to a plurality of products, first manufacturing data including manufacturing condition data related to values ​​indicating manufacturing conditions for each of the products and quality data related to values ​​indicating quality for each of the products under first acquisition conditions; an acquisition condition determination unit that calculates a first reliability for the first manufacturing data and determines a second acquisition condition different from the first acquisition condition based on the first reliability; a second acquisition unit that acquires second manufacturing data including the manufacturing condition data and the quality data from the manufacturing data under the second acquisition conditions; an analysis unit that analyzes the second manufacturing data to calculate an analysis result regarding the relationship between the manufacturing condition data and the quality data; an output data generation unit that generates output data including the analysis result; A manufacturing data analysis device comprising:

5. a first acquisition unit that acquires, from manufacturing data related to a plurality of products, first manufacturing data including manufacturing condition data related to values ​​indicating manufacturing conditions for each of the products and quality data related to values ​​indicating quality for each of the products under first acquisition conditions; an acquisition condition determination unit that determines a second acquisition condition different from the first acquisition condition based on the first manufacturing data; a second acquisition unit that acquires second manufacturing data including the manufacturing condition data and the quality data from the manufacturing data under the second acquisition conditions; an analysis unit that analyzes the second manufacturing data to calculate an analysis result regarding the relationship between the manufacturing condition data and the quality data; an output data generation unit that generates output data including the analysis result; the acquisition condition determination unit calculates a first reliability for the first manufacturing data, calculates a second reliability for the second manufacturing data, and determines the second acquisition conditions so that the second reliability is greater than the first reliability. Manufacturing data analysis equipment.

6. the analysis unit analyzes the first manufacturing data to calculate an analysis result regarding a relationship between the manufacturing data and the quality data; the output data generation unit generates the output data further including the analysis result for the first manufacturing data. The manufacturing data analysis device according to any one of claims 1 to 5.

7. A manufacturing data analysis system comprising a manufacturing data analysis device and a display device, The manufacturing data analysis device a first acquisition unit that acquires, from manufacturing data related to a plurality of products, first manufacturing data including manufacturing condition data related to values ​​indicating manufacturing conditions for each of the products and quality data related to values ​​indicating quality for each of the products under first acquisition conditions; an acquisition condition determination unit that determines second acquisition conditions different from the first acquisition conditions so as to reduce bias in distribution of a plurality of values ​​included in the manufacturing condition data or the quality data in the first manufacturing data; a second acquisition unit that acquires second manufacturing data including the manufacturing condition data and the quality data from the manufacturing data under the second acquisition conditions; an analysis unit that analyzes the second manufacturing data to calculate an analysis result regarding the relationship between the manufacturing condition data and the quality data; an output data generation unit that generates output data including the analysis result; The display device includes: displaying an image based on the output data generated by the manufacturing data analysis device; Manufacturing data analysis system.

8. A computer comprising: acquiring, from manufacturing data relating to a plurality of products, first manufacturing data including manufacturing condition data relating to a value indicating a manufacturing condition for each of the products and quality data relating to a value indicating a quality for each of the products under first acquisition conditions; determining second acquisition conditions different from the first acquisition conditions so as to reduce bias in distribution of a plurality of values ​​included in the manufacturing condition data or the quality data in the first manufacturing data; acquiring second manufacturing data including the manufacturing condition data and the quality data from the manufacturing data under the second acquisition conditions; calculating an analysis result regarding a relationship between the manufacturing condition data and the quality data by analyzing the second manufacturing data; generating output data including the analysis results; Manufacturing data analysis methods.

9. On the computer, a first acquisition function that acquires, from manufacturing data related to a plurality of products, first manufacturing data including manufacturing condition data related to values ​​indicating manufacturing conditions for each of the products and quality data related to values ​​indicating quality for each of the products under first acquisition conditions; an acquisition condition determination function that determines a second acquisition condition different from the first acquisition condition so as to reduce bias in the distribution of a plurality of values ​​included in the manufacturing condition data or the quality data in the first manufacturing data; a second acquisition function for acquiring second manufacturing data including the manufacturing condition data and the quality data from the manufacturing data under the second acquisition condition; an analysis function that calculates an analysis result regarding the relationship between the manufacturing condition data and the quality data by analyzing the second manufacturing data; an output data generation function for generating output data including the analysis results; A manufacturing data analysis program that makes this possible.

Images