JP2023034695A - Display controller, display control method and program - Google Patents

Abstract

To provide a display controller, a method, and a program for a product information providing system that can reduce the processing burden by facilitating the filtering of a desired product to be selected from among products.SOLUTION: A display controller comprises: a first extraction unit that extracts products with a manufacturing condition the magnitude of a first character of which is within a first range and the magnitude of the other character is within a predetermined range based on a prediction result by a predictor that predicts a product with a manufacturing condition meeting the dedicated character; a calculation unit that sorts the products with the manufacturing condition extracted by the first extraction unit by a unit range of the magnitude of the first character to calculate the number of products with the sorted manufacturing condition by the unit range of the magnitude of the first character, and sorts the products with the manufacturing condition extracted by the first extraction unit by a unit range of the magnitude of the other character to calculate the number of products with the sorted manufacturing condition by the unit range of the magnitude of the other character; and a display control unit that displays the number of the products by the unit range of the magnitude of the first character and the number of the products by the unit range of the magnitude of the other character.SELECTED DRAWING: Figure 3

Description

The present invention relates to a display control device, a display control method, and a program.

In Patent Document 1, ``Using a machine-learned prediction module, a plurality of combinations are created using the combination of raw material mixtures as design variables so that the feature value becomes the target value, and the feature value at that time is the target value. We will explore combinations of raw material formulations so that
[Prior art documents]
[Patent Literature]
[Patent Document 1] JP-A-2020-30683

A display control device according to an aspect of the present invention is a prediction device that performs machine learning using a combination of product manufacturing conditions and a plurality of product characteristics as teacher data, and predicts products with manufacturing conditions that satisfy specified characteristics. A first extraction unit that extracts products under manufacturing conditions in which the magnitude of the first characteristic is in the first range and the magnitude of at least one other characteristic is in the predetermined range, based on the prediction result by Be prepared. The display control device classifies the products under the manufacturing conditions extracted by the first extracting unit for each unit range of the magnitude of the first characteristic, and calculates the number of classified products under the manufacturing conditions according to the magnitude of the first characteristic. and classifying the products under the manufacturing conditions extracted by the first extraction unit into unit ranges of at least one other characteristic size, and the number of classified products under the manufacturing conditions for each unit range of magnitude of at least one other characteristic. The display control unit causes the display unit to display a screen showing the number of products per unit range of magnitude of the first characteristic and the number of products per unit range of magnitude of at least one other characteristic. may be provided.

The display control device may include a designating unit that designates at least one first unit range among the plurality of unit ranges of the magnitude of the first characteristic. The display control device extracts products under manufacturing conditions in which the magnitude of the first characteristic is within at least one first unit range and the magnitude of at least one other characteristic is within a predetermined range. You may have a department. The calculating unit classifies the products under the manufacturing conditions extracted by the second extracting unit for each unit range of the magnitude of the first characteristic, and calculates the number of classified products under the manufacturing conditions based on the magnitude of the first characteristic. The products with manufacturing conditions calculated for each unit range and extracted by the second extraction unit are classified by unit range of at least one other characteristic size, and the number of classified products with manufacturing conditions is calculated. It may be calculated for each unit range of magnitude of at least one other characteristic. The display control unit, in response to the specification of at least one first unit range by the specifying unit, selects products for each unit range of the size of the first characteristic displayed on the screen based on the calculation result of the calculation unit. and the number of products per unit range of magnitude of at least one other characteristic.

The specifying unit may specify at least one first unit range by selecting at least one first unit range from a plurality of unit ranges of the magnitude of the first characteristic displayed on the screen.

The specifying unit may further specify at least one second unit range among a plurality of unit ranges of magnitude of at least one other characteristic. The second extraction unit further extracts products under manufacturing conditions in which the magnitude of the first characteristic is in at least one first unit range and the magnitude of at least one other characteristic is in at least one second unit range. You can The calculating unit classifies the products under the manufacturing conditions extracted by the second extracting unit for each unit range of the magnitude of the first characteristic, and calculates the number of classified products under the manufacturing conditions based on the magnitude of the first characteristic. The products with manufacturing conditions calculated for each unit range and extracted by the second extraction unit are classified by unit range of at least one other characteristic size, and the number of classified products with manufacturing conditions is calculated. It may be further calculated for each unit range of magnitude of at least one other characteristic. In response to the specification of at least one second unit range by the specification unit, the display control unit selects products for each unit range of the size of the first characteristic displayed on the screen based on the calculation result of the calculation unit. and the number of products per unit range of magnitude of at least one other characteristic may be further updated.

The display control unit may cause the display unit to display a screen further showing a list of products having the manufacturing conditions extracted by the second extraction unit.

The display control device may further include a derivation unit that derives the reliability of the product under the manufacturing conditions extracted by the second extraction unit. The display control unit may cause the display unit to display a screen showing the reliability of the product under the manufacturing conditions extracted by the second extraction unit.

The derivation unit compares the manufacturing conditions of the product extracted by the second extraction unit with the manufacturing conditions of the product indicated by the training data, thereby obtaining the reliability of the product of the manufacturing conditions extracted by the second extraction unit. can be derived.

The derivation unit may derive the reliability based on the degree of similarity between the manufacturing conditions indicated in the teaching data and the manufacturing conditions extracted by the second extraction unit.

The display control unit may cause the display unit to display a screen showing the yield of the product, which is one of the characteristics of the product predicted by the prediction device.

Products with manufacturing conditions extracted by the first extraction unit may include products with manufacturing conditions indicated in the teaching data.

The first extraction unit selects, from among the products under the manufacturing conditions indicated by the teaching data, the magnitude of the first characteristic being within the first range and the magnitude of at least one other characteristic being within the predetermined range. Products with manufacturing conditions may be extracted. The first extraction unit extracts at least one unit range of the first range of the first characteristic or at least one unit of the predetermined range of at least one other characteristic from among the products under the manufacturing conditions indicated in the training data At least one unit range of the first range of the first characteristic or at least one unit range of the predetermined range of at least one other characteristic based on the prediction result when a product with manufacturing conditions that satisfy the range cannot be extracted You may extract products with manufacturing conditions that satisfy

The manufacturing conditions may include at least one of the raw materials that make up the product, the mixing ratio of the raw materials, and the manufacturing method of the product.

A product can be a compound or composition.

A manufacturing method according to an aspect of the present invention is a prediction device that performs machine learning using a combination of product manufacturing conditions and a plurality of product characteristics as teacher data, and predicts products under manufacturing conditions that satisfy specified characteristics. a first extraction step of extracting products under manufacturing conditions in which the magnitude of the first characteristic is within a first range and the magnitude of at least one other characteristic is within a predetermined range, based on the prediction results; you can In the manufacturing method, the products under the manufacturing conditions extracted in the first extraction step are classified by unit range of the magnitude of the first characteristic, and the number of classified products under the manufacturing conditions is calculated by the magnitude of the first characteristic. Calculated for each unit range, and classifying the products under the manufacturing conditions extracted in the first extraction step into at least one other characteristic size unit range, and calculating the number of classified products under the manufacturing conditions A calculating step may be provided for calculating for each unit range of magnitudes of the at least one other characteristic. The manufacturing method includes a display control step of causing the display to display a screen showing the number of products per unit range of magnitude of the first characteristic and the number of products per unit range of magnitude of at least one other characteristic. Be prepared.

A program according to an aspect of the present invention performs machine learning using a combination of product manufacturing conditions and a plurality of product characteristics as teacher data, and prediction by a prediction device that predicts products with manufacturing conditions that satisfy the specified characteristics. Based on the results, the computer performs a first extraction step of extracting products under manufacturing conditions in which the magnitude of the first characteristic is within a first range and the magnitude of at least one other characteristic is within a predetermined range. You can let it run. The program classifies the products under the manufacturing conditions extracted in the first extraction step by unit range of the size of the first characteristic, and calculates the number of the classified products under the manufacturing conditions by the unit of the size of the first characteristic. The products under the manufacturing conditions calculated for each range and extracted in the first extraction stage are classified into unit ranges of the size of at least one other characteristic, and the number of classified products under the manufacturing conditions is at least A computer may be caused to perform a calculation step of calculating for each unit range of magnitudes of one of the other properties. The program causes the display unit to display a screen showing the number of products per unit range of magnitude of the first characteristic and the number of products per unit range of magnitude of at least one other characteristic. can be executed.

It should be noted that the above summary of the invention does not list all the features of the invention. Subcombinations of these feature groups can also be inventions.

It is a figure which shows an example of the functional block of a product information provision system. It is a figure which shows an example of the screen displayed on a display part. FIG. 10 is a diagram showing an example of how at least one first unit range is selected from a plurality of unit ranges of magnitude of a second characteristic as at least one other characteristic displayed on the screen; FIG. 10 is a diagram showing an example of a case where the candidate product list information indicates the reliability of each candidate product. 4 is a flow chart showing an example of a screen display procedure; FIG. 10 is a diagram showing an example of a screen showing the number of products for each unit range for each characteristic; FIG. 10 is a diagram showing an example of a screen showing the number of products for each unit range for each characteristic; It is a figure which shows an example of a hardware configuration.

Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential for the solution of the invention.

Conventionally, material search is performed to search for new materials or alternative materials. Materials search based on computer analysis called materials informatics is also being carried out. Materials informatics is a method of applying information science and technology to the field of materials to develop new materials or search for alternative materials.

FIG. 1 shows an example of functional blocks of a product information providing system 10 utilizing materials informatics. The product information providing system 10 derives correlations between multiple pieces of input data using artificial intelligence such as machine learning, and provides information on products that satisfy characteristics such as desired functions or performance.

When there are a large number of candidate products provided by the product information providing system 10, it may not be easy to select a desired product from among those candidate products. Then, the processing load of the product information providing system 10 may increase when narrowing down the desired products. Therefore, in the present embodiment, narrowing down of desired products to be selected from among a plurality of products is facilitated, and the processing load of the product information providing system 10 is reduced.

A product information providing system 10 includes a prediction device 100 and a display control device 200 . The prediction device 100 and the display control device 200 may be configured by one or more computers. The product information providing system 10 provides an electronic catalog showing information on products with manufacturing conditions that satisfy desired characteristics.

The prediction device 100 includes a data collection unit 102 , a model generation unit 104 , a prediction unit 106 and a storage unit 110 . The prediction device 100 performs machine learning using combinations of product manufacturing conditions and a plurality of product characteristics as teacher data, and predicts products with manufacturing conditions that satisfy desired characteristics. One or more computers may function as the data collection unit 102, the model generation unit 104, and the prediction unit 106 by executing a machine learning program.

The data collection unit 102 collects combinations of product manufacturing conditions and a plurality of product characteristics as training data, and stores the training data in the storage unit 110 . The product manufacturing conditions may include at least one of raw materials constituting the product, a mixing ratio of the raw materials constituting the product, and a manufacturing method of the product. The compounding ratio may be a composition ratio or a mass percentage. The production method includes all conditions related to experiments and production such as reaction rate, reaction time, reaction pressure, and stirring conditions. A product may be a chemical product, drug, machine part, or food. A product can be a compound or composition. A product is a concept that includes not only an actual product that can be actually manufactured, but also a virtual product that cannot be actually manufactured, and a test product (sample product) that has not yet reached the stage of being an actual product.

Product characteristics may include appearance (glossiness of the surface), flame resistance, oil resistance, hardness, cold resistance temperature, heat resistance temperature, oxygen index, tensile strength, elongation, and yield. The product characteristics may be any value as long as it is a value that serves as an index characterizing the product.

The model generation unit 104 performs machine learning according to a supervised learning algorithm using the product manufacturing conditions as explanatory variables and the product characteristics as objective variables, thereby predicting products with manufacturing conditions that satisfy desired characteristics. A model is generated and the trained model is stored in the storage unit 110 . The trained model shows the relationship between the manufacturing conditions of the product and multiple properties of the product. The algorithm can be any type of algorithm such as neural network, support vector machine, multiple regression analysis, decision tree, and the like. The prediction unit 106 uses the learned model to predict products with manufacturing conditions in which a plurality of characteristics are within desired ranges.

The display control device 200 causes the display unit to display an image showing information about the product with manufacturing conditions predicted by the prediction device 100 . The display control device 200 causes the display unit to display images of products with manufacturing conditions predicted by the prediction device 100 and images of existing products as an electronic product catalog. The user refers to the image displayed on the display unit and selects a product that satisfies desired characteristics.

The display control device 200 includes a first extraction section 202 , a calculation section 204 , a second extraction section 206 , a specification section 210 , a derivation section 212 , a display control section 214 and a display section 250 . One or more computers function as a first extraction unit 202, a calculation unit 204, a second extraction unit 206, a specification unit 210, a derivation unit 212, and a display control unit 214 by executing a display control program. you can

Based on the prediction result by the prediction device 100, the first extraction unit 202 determines that the magnitude of the first characteristic is within the first range and that at least one second characteristic (hereinafter also referred to as "second characteristic") is selected as another characteristic. ) is within a predetermined range (hereinafter also referred to as “second range”). The first range and the second range may be specified in advance by the user. The first range and the second range may be defined as ranges from the minimum value to the maximum value allowed as the values of the first property and the second property of the product. Although the first extraction unit 202 extracts products that satisfy ranges of two characteristics, the number of characteristics is not limited to two. The first extraction unit 202 may extract products that satisfy all ranges of the plurality of characteristics.

Products with manufacturing conditions extracted by the first extraction unit 202 may include products with manufacturing conditions indicated in the teaching data. That is, the products under the manufacturing conditions extracted by the first extraction unit 202 are not only the products predicted by the prediction device 100, but also the already existing products shown as teacher data, that is, the products that are already manufacturable. may include products that are

First, the first extraction unit 202 first extracts from the teacher data, that is, from the existing products, the magnitude of the first characteristic is in the first range and the magnitude of the second characteristic is in the second range. Products with manufacturing conditions may be extracted. In this case, the first extraction unit 202 satisfies at least one unit range of the first range of the first characteristic or at least one unit range of the second range of the second characteristic in the extracted existing products. Determine if the product does not exist. That is, the first extraction unit 202 determines whether or not there is teacher data that satisfies the conditions for part of the first range or the second range. Then, if an existing product that satisfies at least one unit range of the first range of the first characteristic or at least one unit range of the second range of the second characteristic is not extracted, the prediction unit 106 determines that the first characteristic or at least one unit range of the second range of the second characteristic. Based on the prediction result of the prediction unit 106, the first extraction unit 202 selects a manufacturing condition that satisfies at least one unit range of the first range of the first characteristic or at least one unit range of the second range of the second characteristic. extract the product of

In other words, if the first extraction unit 202 fails to extract, from the existing products, a product with manufacturing conditions that satisfy the conditions for a partial range of the desired characteristics, the first extraction unit 202 extracts the conditions for the partial range of the characteristics. Products with manufacturing conditions based on prediction results may be extracted only for products with satisfying manufacturing conditions.

The calculation unit 204 classifies the products under the manufacturing conditions extracted by the first extracting unit 202 for each unit range of the magnitude of the first characteristic, and calculates the number of classified products under the manufacturing conditions by the magnitude of the first characteristic. Calculated for each unit range of height. The unit range may be a range obtained by dividing the characteristic range by a predetermined width. The unit range may be the width of a predetermined numerical range such as a width of one digit, a width of two digits, a width of three digits, or the like. The calculation unit 204 classifies the products under the manufacturing conditions extracted by the first extracting unit 202 for each unit range of the size of the second characteristic, and calculates the number of classified products under the manufacturing conditions by the size of the second characteristic. Calculated for each unit range of height.

The display control unit 214 causes the display unit 250 to display a screen showing the number of products per unit range of magnitude of the first characteristic and the number of products per unit range of magnitude of the second characteristic. The display control unit 214 displays the number of products for each unit range of the size of the first characteristic and the unit of the size of the second characteristic in a predetermined format such as a bar graph (histogram), a pie chart, or a line graph. A screen showing the number of products for each range may be displayed on the display unit 250 . The display control unit 214 may cause the display unit 250 to display a screen showing an N-dimensional scatter diagram in which each of the plurality of characteristics is associated with each dimension. The display control unit 214 causes the display unit 250 to display a screen showing a two-dimensional scatter diagram showing the number of products per unit range of magnitude of the first characteristic and the number of products per unit range of magnitude of the second characteristic. can be displayed in The display control section 214 may cause the display section 250 to display a screen showing a map showing the production sites and the characteristics of the product for each production site. The display control unit 214 may cause the display unit 250 to display a screen showing an image diagram of an electron microscopic image obtained by imaging the product with an electron microscope as a characteristic of the product. Since the number of products per unit range is shown for each characteristic, for example, the amount of candidate products exhibiting the desired characteristic can be immediately grasped.

Designating unit 210 designates at least one first unit range among a plurality of unit ranges of the magnitude of the first characteristic. The specifying unit 210 may specify at least one first unit range by selecting at least one first unit range from a plurality of unit ranges of the magnitude of the first characteristic displayed on the screen.

The second extraction unit 206 extracts products under manufacturing conditions in which the magnitude of the first characteristic is within at least one first unit range and the magnitude of the second characteristic is within the second range. The calculation unit 204 classifies the products under the manufacturing conditions extracted by the second extracting unit 206 for each unit range of the magnitude of the first characteristic, and calculates the number of classified products under the manufacturing conditions according to the magnitude of the first characteristic. Calculated for each unit range of height. Further, the calculating unit 204 classifies the products under the manufacturing conditions extracted by the second extracting unit 206 for each unit range of the size of the second characteristic, and calculates the number of classified products under the manufacturing conditions according to the second characteristic. It is calculated for each unit range of size.

In this embodiment, the first extraction unit 202 extracts manufacturing conditions in which the magnitude of the first characteristic is in the first range and the magnitude of the second characteristic is in the second range, based on the prediction result of the prediction device 100. An example of extracting the products of is explained. However, the first extraction unit 202 may extract products with manufacturing conditions in which the magnitudes of three or more characteristics are each within a predetermined range, based on the prediction results of the prediction device 100 . The first extraction unit 202 extracts a manufacturing condition in which the magnitude of the first characteristic is within a first range and the magnitude of at least one other characteristic is within a predetermined range, based on the prediction result by the prediction device 100. of products may be extracted. The second characteristic is an example of at least one other characteristic. Also, the second range is an example of a predetermined range. The first extraction unit 202 may extract products with manufacturing conditions in which the magnitudes of the first characteristic to the Nth characteristic (N is a positive integer) are each within a predetermined range. A manufacturing condition in which the magnitude of the first characteristic is in a first range and the magnitude of at least one other characteristic is in a predetermined range, based on the prediction result by the prediction device 100, by the first extraction unit 202 , the second extracting unit 206 selects a manufacturing product in which the magnitude of the first characteristic is in at least one first unit range and the magnitude of at least one other characteristic is in a predetermined range Conditional products may be extracted. When the first extraction unit 202 extracts products with manufacturing conditions in which the magnitudes of the first to N-th characteristics (N is a positive integer) are each within a predetermined range, the second extraction unit 206 extracts products under manufacturing conditions in which the magnitude of the first characteristic is in at least one first unit range and the specific magnitudes of the second to Nth characteristics are each in a predetermined range You can

In response to the designation of at least one first unit range by the designation unit 210, the display control unit 214 determines the unit range of the magnitude of the first characteristic displayed on the screen based on the calculation result of the calculation unit 204. Update the number of products per range and the number of products per unit range of magnitude of the second characteristic.

The specifying unit 210 may further specify at least one second unit range among the plurality of unit ranges of magnitude of the second characteristic. The second extraction unit 206 further extracts products under manufacturing conditions in which the magnitude of the first characteristic is in at least one first unit range and the magnitude of the second characteristic is in at least one second unit range. good. The calculation unit 204 classifies the products under the manufacturing conditions extracted by the second extracting unit 206 for each unit range of the magnitude of the first characteristic, and calculates the number of classified products under the manufacturing conditions according to the magnitude of the first characteristic. It may be calculated for each unit range of height. Further, the calculation unit 204 classifies the products under the manufacturing conditions extracted by the second extraction unit for each unit range of the size of the second characteristic, and calculates the number of classified products under the manufacturing conditions according to the second characteristic. Further calculations may be made for each size unit range. In response to the designation of at least one second unit range by the designation unit 210, the display control unit 214 determines the unit range of the magnitude of the first characteristic displayed on the screen based on the calculation result of the calculation unit 204. The number of products per range and the number of products per unit range of magnitudes of the second characteristic may be further updated.

The display control unit 214 may cause the display unit 250 to display a screen further showing a list of products with manufacturing conditions extracted by the second extraction unit 206 .

The derivation unit 212 derives the product reliability of the manufacturing conditions extracted by the second extraction unit 206 . Reliability indicates the probability that the product can actually be manufactured. The method of deriving the reliability is the first method of judging from the relationship between the output result and the teacher data, and the second method of judging based on what kind of behavior was shown inside the artificial intelligence at the time of output of the prediction device 100. 2 methods. In the first method, it is determined that the more similar the output result (prediction result) of the prediction device 100 and the teacher data, the higher the reliability. There are various similarity criteria, and for example, the distance between the output result and the most similar teacher data may be used. In the second method, reliability is based on how much information inside the AI is used and whether the result does not fluctuate greatly due to small fluctuations. For example, the percentage of neurons used in the neural network may be used as reliability.

The derivation unit 212 may derive the reliability according to a predetermined algorithm from the relationship between the product under the manufacturing conditions extracted by the second extraction unit 206 and the teacher data. The derivation unit 212 may derive the reliability from the behavior of the prediction device 100 according to a predetermined algorithm. The derivation unit 212 may derive the reliability according to a predetermined algorithm from the usage rate of information inside the artificial intelligence of the prediction device 100 . The derivation unit 212 may derive the reliability based on the degree of variation in the objective variable according to the variation in the explanatory variable. If the variation of the explanatory variable is small, but the variation of the objective variable is large, the reliability decreases. The derivation unit 212 may derive the reliability based on the usage ratio of neurons in the neural network used in the prediction device 100 .

The deriving unit 212 compares the manufacturing conditions of the product extracted by the second extracting unit 206 with the manufacturing conditions of the product indicated in the teaching data, thereby obtaining the manufacturing conditions of the product extracted by the second extracting unit 206. Confidence may be derived. The derivation unit 212 may derive the reliability based on the degree of similarity between the manufacturing conditions indicated in the training data and the manufacturing conditions extracted by the second extraction unit 206 . The display control unit 214 may cause the display unit 250 to display a screen showing the reliability of the product under the manufacturing conditions extracted by the second extraction unit 206 . The display control unit 214 may cause the display unit 250 to display a screen showing a list of products including the reliability of the products extracted by the second extraction unit 206 .

The derivation unit 212 calculates the Eugrid distance between the variable (characteristic value) indicated in the manufacturing conditions indicated in the teaching data and the variable (characteristic value) indicated in the manufacturing conditions extracted by the second extraction unit 206. , the Manhattan distance may be used to derive the confidence. The derivation unit 212 uses the prediction device 100 to determine the highest reliability among the respective reliability of the product with the manufacturing conditions predicted by the prediction device 100 and the product with the manufacturing conditions indicated in each of the plurality of teacher data. It may be derived as the reliability of the product under the predicted manufacturing conditions. Variables shown in the manufacturing conditions may be values such as the mixing ratio of raw materials, the temperature in the manufacturing method, and the time. Products with manufacturing conditions indicated in the training data are actually existing products. If the product with the manufacturing conditions predicted by the prediction device 100 is similar to the product with the manufacturing conditions indicated in the training data, there is a high possibility that the product with the manufacturing conditions predicted by the prediction device 100 can actually be manufactured. In other words, if the product with the manufacturing conditions predicted by the prediction device 100 is similar to the product with the manufacturing conditions indicated in the training data, the reliability of the product is high. By displaying the reliability of the product, additional judgment criteria can be presented to the user, making it easier for the user to select a desired product from among a plurality of candidate products. Thereby, the processing load on the product information providing system 10 can also be reduced.

Cost is also one of the criteria for selecting a desired product from candidate products. Yield is one of the cost criteria. The prediction device 100 also predicts the yield as a product characteristic of the manufacturing conditions using the learned model. Therefore, the display control section 214 may cause the display section 250 to display a screen showing the yield of the product extracted by the second extraction section 206 . The display control unit 214 may cause the display unit 250 to display a screen showing a list of products including the yield of the products extracted by the second extraction unit 206 .

FIG. 2 is an example of a screen 500 displayed on the display unit 250. As shown in FIG. Screen 500 includes a bar graph 502 showing the number of products per unit range of a first characteristic and a bar graph 504 showing the number of products per unit range of a second characteristic. Further, the screen 500 includes list information 506 of candidate products showing the range of the first characteristic indicated by the bar graph 502 and the range of the second characteristic indicated by the bar graph 504, and the total number of candidate products included in the list information 506. 508. If all the products cannot be displayed on one screen in the list information 506, the display control unit 214 may display all the products by scrolling using the scroll bar 512. FIG.

FIG. 3 shows an example of selecting at least one unit range 510 from a plurality of unit ranges of magnitude of the second characteristic displayed on the screen 500 . A user may select at least one unit area 510 on the screen 500 by dragging the area of the desired property. In response to the designation of at least one unit range 510 by the designation unit 210, the display control unit 214 controls the unit range of the magnitude of the first characteristic displayed on the screen 500 based on the calculation result of the calculation unit 204. The bar graph 502 showing the number of products per range and the bar graph 506 showing the number of products per unit range of magnitude of the second characteristic, the list information 506, and the total number 508 may be updated.

FIG. 4 shows an example of a case where the candidate product list information indicates the reliability of each candidate product. By indicating the reliability for each candidate product, it becomes easier to visually grasp the possibility of actually manufacturing the candidate product.

FIG. 5 is a flow chart showing an example of a screen display procedure. The designation unit 210 designates the range of each characteristic of the desired product (S100). The range of each characteristic may be a predetermined range. The first extraction unit 202 extracts products with manufacturing conditions that satisfy the specified range of each characteristic based on the prediction result of the prediction device 100 (S102). The calculation unit 204 calculates the number of products for each unit range for each characteristic of the products extracted by the first extraction unit 202 (S104). The display control unit 214 causes the display unit 250 to display a screen showing the number of products for each unit range for each characteristic (S106). Products displayed on the screen include products predicted by the prediction device 100 and products provided as training data. The display control unit 214 displays, on the display unit 250, an image in which the unit range corresponding to the product predicted by the prediction device 100 and the unit range corresponding to the product provided as teacher data are identifiable. You may let The display control unit 214 displays an image in which the unit range corresponding to the product predicted by the prediction device 100 and the unit range corresponding to the product provided as training data are indicated by lines of different colors or different thicknesses. You may make it display on the display part 250. FIG.

Next, the designation unit 210 determines whether or not designation of a unit range of characteristics has been accepted on the screen (S108). The specifying unit 210 may receive the specification of the unit range for each of a plurality of characteristics. In other words, when narrowing down the candidate products, the specifying unit 210 may accept a specification for narrowing down the range of each of the plurality of characteristics.

Upon receiving the specification of the characteristic unit range, the second extraction unit 206 limits the characteristic range to the specified unit range, and extracts products with manufacturing conditions that satisfy the specified characteristic range (S110). . The calculation unit 204 calculates the number of products for each unit range for each characteristic of the products extracted by the second extraction unit 206 (S112). The display control unit 214 updates the screen showing the number of products for each unit range for each characteristic and causes the display unit 250 to display it (S114).

As described above, according to the present embodiment, by narrowing down the range of characteristics of a plurality of candidate products predicted by the prediction device 100 on the screen at any time, the candidate products can be easily narrowed down, and product information can be provided. The processing load on the system 10 can be reduced.

6 and 7 show an example screen 600 showing the number of products per unit area for each characteristic. Screen 600 shows the number of products for each application category of the target product. The screen 600 displays appearance (glossiness of the surface), flame resistance, oil resistance, hardness, cold resistance temperature, heat resistance temperature, oxygen index, tensile strength, and elongation for each unit range as the characteristics of the target product. Indicate the number of products.

Screen 600 shown in FIG. 7 shows the screen 600 shown in FIG. shows the screen updated from .

FIG. 8 illustrates an example computer 1200 in which aspects of the invention may be implemented in whole or in part. Programs installed on computer 1200 may cause computer 1200 to act as one or more "parts" of or operations associated with apparatus according to embodiments of the present invention. Alternatively, the program may cause computer 1200 to perform the operation or the one or more "parts." The program may cause the computer 1200 to perform a process or steps of the process according to embodiments of the invention. Such programs may be executed by CPU 1212 to cause computer 1200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

Computer 1200 according to this embodiment includes CPU 1212 and RAM 1214 , which are interconnected by host controller 1210 . Computer 1200 also includes a communication interface 1222 and an input/output unit, which are connected to host controller 1210 via input/output controller 1220 . Computer 1200 also includes ROM 1230 . The CPU 1212 operates according to programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit.

Communication interface 1222 communicates with other electronic devices over a network. A hard disk drive may store programs and data used by CPU 1212 in computer 1200 . ROM 1230 stores therein programs that are dependent on the hardware of computer 1200, such as a boot program that is executed by computer 1200 upon activation. The program is provided via a computer-readable recording medium such as CR-ROM, USB memory or IC card or network. The program is installed in RAM 1214 or ROM 1230 , which are also examples of computer-readable recording media, and executed by CPU 1212 . The information processing described within these programs is read by computer 1200 to provide coordination between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing information operations or processing according to the use of computer 1200 .

For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 executes a communication program loaded into the RAM 1214 and sends communication processing to the communication interface 1222 based on the processing described in the communication program. you can command. The communication interface 1222, under the control of the CPU 1212, reads the transmission data stored in the transmission buffer area provided in the RAM 1214 or a recording medium such as a USB memory, transmits the read transmission data to the network, or Received data received from a network is written in a receive buffer area or the like provided on a recording medium.

The CPU 1212 also causes the RAM 1214 to read all or a necessary portion of a file or database stored in an external storage medium such as a USB memory, and performs various types of processing on the data on the RAM 1214. good. CPU 1212 may then write back the processed data to an external recording medium.

Various types of information, such as various types of programs, data, tables, and databases, may be stored on recording media and subjected to information processing. CPU 1212 performs various types of operations on data read from RAM 1214, information processing, conditional decisions, conditional branching, unconditional branching, and information retrieval, which are described throughout this disclosure and are specified by instruction sequences of programs. Various types of processing may be performed, including /replace, etc., and the results written back to RAM 1214 . In addition, the CPU 1212 may search for information in a file in a recording medium, a database, or the like. For example, if a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 determines that the attribute value of the first attribute is specified. search the plurality of entries for an entry that matches the condition, read the attribute value of the second attribute stored in the entry, and thereby associate it with the first attribute that satisfies the predetermined condition. an attribute value of the second attribute obtained.

The programs or software modules described above may be stored in a computer-readable storage medium on or near computer 1200 . Also, a recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, whereby the program can be transferred to the computer 1200 via the network. offer.

A computer-readable medium may include any tangible device capable of storing instructions for execution by a suitable device. As a result, a computer-readable medium having instructions stored thereon provides an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowchart or block diagram. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer readable media include floppy disks, diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), Electrically Erasable Programmable Read Only Memory (EEPROM), Static Random Access Memory (SRAM), Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD), Blu-ray (RTM) Disc, Memory Stick, Integration Circuit cards and the like may be included.

The computer readable instructions may comprise either source code or object code written in any combination of one or more programming languages. Source code or object code includes conventional procedural programming languages. Traditional procedural programming languages include assembler instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, or Smalltalk, JAVA, C++. etc., and the "C" programming language or similar programming languages. Computer readable instructions may be transferred to a processor or programmable circuitry of a general purpose computer, special purpose computer, or other programmable data processing apparatus, either locally or over a wide area network (WAN), such as a local area network (LAN), the Internet, or the like. ) may be provided via A processor or programmable circuit may execute computer readable instructions to produce means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is obvious to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the description of the scope of claims that forms with such modifications or improvements can also be included in the technical scope of the present invention.

The execution order of each process such as actions, procedures, steps, and stages in the devices, systems, programs, and methods shown in the claims, the specification, and the drawings is particularly "before", "before etc., and it should be noted that they can be implemented in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flow in the claims, the specification, and the drawings, even if the description is made using "first," "next," etc. for the sake of convenience, it means that it is essential to carry out in this order. not a thing

10 Product information providing system 100 Prediction device 102 Data collection unit 104 Model generation unit 106 Prediction unit 110 Storage unit 200 Display control device 202 First extraction unit 204 Calculation unit 206 Second extraction unit 210 Designation unit 212 Derivation unit 214 Display control unit 250 Display unit 1200 Computer 1210 Host controller 1212 CPU
1214 RAM
1220 input/output controller 1222 communication interface 1230 ROM

Claims (15)

Machine learning using combinations of product manufacturing conditions and product characteristics as training data, and based on the prediction results of a prediction device that predicts products with manufacturing conditions that satisfy the specified characteristics, the size of the first characteristic a first extraction unit for extracting products under manufacturing conditions in which the magnitude of at least one other characteristic is within a first range and the magnitude of at least one other characteristic is within a predetermined range;
The products under the manufacturing conditions extracted by the first extraction unit are classified for each unit range of the magnitude of the first characteristic, and the number of the classified products under the manufacturing conditions is counted according to the magnitude of the first characteristic. The products under the manufacturing conditions calculated for each unit range and extracted by the first extraction unit are classified by the unit range of the size of the at least one other characteristic, and the classified products under the manufacturing conditions are obtained. a calculation unit that calculates the number of for each unit range of the magnitude of the at least one other characteristic;
a display control unit that causes a display unit to display a screen showing the number of products per unit range of magnitude of the first characteristic and the number of products per unit range of magnitude of the at least one other characteristic. Display controller. a designation unit that designates at least one first unit range among a plurality of unit ranges of magnitude of the first characteristic;
A second extraction unit for extracting products under manufacturing conditions in which the magnitude of the first characteristic is within the at least one first unit range and the magnitude of the at least one other characteristic is within the predetermined range. and
The calculation unit classifies the products under the manufacturing conditions extracted by the second extraction unit for each unit range of magnitude of the first characteristic, and calculates the number of classified products under the manufacturing conditions by the first characteristic. The products under the manufacturing conditions calculated for each unit range of characteristic magnitudes and extracted by the second extraction unit are classified by each unit range of at least one other characteristic magnitude. calculating the number of products under the same manufacturing conditions for each unit range of magnitude of the at least one other characteristic;
The display control unit controls the size of the first characteristic displayed on the screen based on the calculation result of the calculation unit in response to the designation of the at least one first unit range by the designation unit. 2. The display control device of claim 1, updating the number of products per unit area of and the number of products per unit area of magnitude of said at least one other characteristic. The specifying unit specifies the at least one first unit range by selecting the at least one first unit range from a plurality of unit ranges of the magnitude of the first characteristic displayed on the screen. The display control device according to claim 2. The designating unit further designates at least one second unit range among a plurality of unit ranges of the magnitude of the at least one other characteristic,
The second extracting part is a production condition in which the magnitude of the first characteristic is in the at least one first unit range and the magnitude of the at least one other characteristic is in the at least one second unit range further extract the products of
The calculation unit classifies the products under the manufacturing conditions extracted by the second extraction unit for each unit range of magnitude of the first characteristic, and calculates the number of classified products under the manufacturing conditions by the first characteristic. The products under the manufacturing conditions calculated for each unit range of characteristic magnitudes and extracted by the second extraction unit are classified by each unit range of at least one other characteristic magnitude. further calculating the number of products under the manufacturing conditions for each unit range of magnitude of said at least one other property;
The display control unit controls the size of the first characteristic displayed on the screen based on the calculation result of the calculation unit in response to the designation of the at least one second unit range by the designation unit. 4. The display control device according to claim 2 or 3, further updating the number of products per unit area of and the number of products per unit area of magnitude of said at least one other characteristic. 5. The display control according to any one of claims 2 to 4, wherein the display control unit causes the display unit to display the screen further showing a list of products under the manufacturing conditions extracted by the second extraction unit. Device. further comprising a derivation unit for deriving the reliability of the product under the manufacturing conditions extracted by the second extraction unit;
The display control according to any one of claims 2 to 5, wherein the display control unit causes the display unit to display the screen indicating the reliability of the product under the manufacturing conditions extracted by the second extraction unit. Device. The deriving unit compares the manufacturing conditions of the product extracted by the second extracting unit with the manufacturing conditions of the product indicated in the teaching data, thereby determining the manufacturing conditions extracted by the second extracting unit. 7. The display control device according to claim 6, wherein said reliability of a product is derived. The display control according to claim 7, wherein the derivation unit derives the reliability based on a degree of similarity between the manufacturing conditions indicated in the teaching data and the manufacturing conditions extracted by the second extraction unit. Device. 9. The display according to any one of claims 1 to 8, wherein the display control unit causes the display unit to display the screen showing the product yield, which is one of the product characteristics predicted by the prediction device. Control device. 10. The display control device according to any one of claims 1 to 9, wherein the products under manufacturing conditions extracted by said first extraction unit include products under manufacturing conditions indicated in said teacher data. The first extracting unit selects products whose magnitude of the first characteristic is within a first range and whose magnitude of the at least one other characteristic is predetermined from among the products under the manufacturing conditions indicated in the teaching data. Extract products with manufacturing conditions in the range, and select at least one unit range of the first range of the first characteristic or the at least one other characteristic in advance from among the products with the manufacturing conditions indicated in the training data If a product with manufacturing conditions that satisfy at least one unit range of the defined range cannot be extracted, based on the prediction result, the at least one unit range of the first range of the first characteristic or the at least one other 11. The display control device according to claim 10, wherein products with manufacturing conditions satisfying said at least one unit range of a predetermined range of characteristics are extracted. 12. The display control device according to any one of claims 1 to 11, wherein the manufacturing conditions include at least one of raw materials constituting the product, a mixing ratio of the raw materials, and a manufacturing method of the product. 13. The display control device of claim 12, wherein the product is a compound or composition. Machine learning using combinations of product manufacturing conditions and product characteristics as training data, and based on the prediction results of a prediction device that predicts products with manufacturing conditions that satisfy the specified characteristics, the size of the first characteristic a first extraction step of extracting a product under manufacturing conditions in which the magnitude of at least one other characteristic is within a first range and the magnitude of at least one other characteristic is within a predetermined range;
The products under the manufacturing conditions extracted in the first extraction step are classified by unit range of the magnitude of the first characteristic, and the number of classified products under the manufacturing conditions is counted according to the magnitude of the first characteristic. The products under the manufacturing conditions calculated for each unit range and extracted in the first extraction step are classified by the unit range of the size of the at least one other characteristic to produce the classified products under the manufacturing conditions. a calculating step of calculating the number of for each unit range of magnitude of the at least one other characteristic;
and a display control step of causing a display unit to display a screen showing the number of products per unit range of magnitude of the first characteristic and the number of products per unit range of magnitude of the at least one other characteristic. Display control method. Machine learning using combinations of product manufacturing conditions and product characteristics as training data, and based on the prediction results of a prediction device that predicts products with manufacturing conditions that satisfy the specified characteristics, the size of the first characteristic a first extraction step of extracting a product under manufacturing conditions in which the magnitude of at least one other characteristic is within a first range and the magnitude of at least one other characteristic is within a predetermined range;
The products under the manufacturing conditions extracted in the first extraction step are classified by unit range of the magnitude of the first characteristic, and the number of classified products under the manufacturing conditions is counted according to the magnitude of the first characteristic. The products under the manufacturing conditions calculated for each unit range and extracted in the first extraction step are classified by the unit range of the size of the at least one other characteristic to produce the classified products under the manufacturing conditions. a calculating step of calculating the number of for each unit range of magnitude of the at least one other characteristic;
and a display control step for displaying on a display unit a screen showing the number of products per unit range of magnitude of the first characteristic and the number of products per unit range of magnitude of the at least one other characteristic. program to run.

Images