JP7725946B2 - Display control device, display control method, and program - Google Patents

Description

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

Patent Document 1 states that "Using a machine-learned prediction module, multiple combinations of raw material formulations are created as design variables so that the feature values will reach the target values, and a search is made for combinations of raw material formulations so that the feature values at that time will reach the target values."
[Prior art documents]
[Patent Documents]
[Patent Document 1] JP 2020-30683 A

A display control device according to one aspect of the present invention may include a first extraction unit that extracts products under manufacturing conditions in which the magnitude of a first characteristic falls within a first range and the magnitude of at least one other characteristic falls within a predetermined range, based on prediction results from a prediction device that performs machine learning using a combination of a product's manufacturing conditions and multiple product characteristics as training data and predicts products under manufacturing conditions that satisfy specified characteristics. The display control device may include a calculation unit that classifies the products under the manufacturing conditions extracted by the first extraction unit into unit ranges of the magnitude of the first characteristic and calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and classifies the products under the manufacturing conditions extracted by the first extraction unit into unit ranges of the magnitude of at least one other characteristic and calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic. The display control device may include a display control unit that causes a screen to be displayed on the display unit showing the number of products under each unit range of the magnitude of the first characteristic and the number of products under each unit range of the magnitude of the at least one other characteristic.

The display control device may include a designation unit that designates at least one first unit range among multiple unit ranges of the magnitude of the first characteristic. The display control device may include a second extraction unit that extracts products under manufacturing conditions in which the magnitude of the first characteristic falls within at least one first unit range and the magnitude of at least one other characteristic falls within a predetermined range. The calculation unit may classify products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of the first characteristic and calculate the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and may also classify products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of at least one other characteristic and calculate the number of products under the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic. In response to the designation of at least one first unit range by the designation unit, the display control unit may update the number of products displayed on the screen for each unit range of the magnitude of the first characteristic and the number of products under each unit range of the magnitude of the at least one other characteristic based on the calculation result by the calculation unit.

The designation unit may designate at least one first unit range by selecting at least one first unit range from multiple unit ranges of the magnitude of the first characteristic displayed on the screen.

The designation unit may further designate at least one second unit range among the multiple unit ranges of the magnitude of the at least one other characteristic. The second extraction unit may further extract products under manufacturing conditions in which the magnitude of the first characteristic falls within at least one first unit range and the magnitude of the at least one other characteristic falls within at least one second unit range. The calculation unit may classify the products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of the first characteristic and calculate the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and may further classify the products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of the at least one other characteristic and calculate the number of products under the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic. In response to the designation of at least one second unit range by the designation unit, the display control unit may further update the number of products displayed on the screen for each unit range of the magnitude of the first characteristic and the number of products for each unit range of the magnitude of the at least one other characteristic based on the calculation result by the calculation unit.

The display control unit may cause the display unit to display a screen that further shows a list of products that meet 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 for the manufacturing conditions extracted by the second extraction unit. The display control unit may cause the display unit to display a screen indicating the reliability of the product for the manufacturing conditions extracted by the second extraction unit.

The derivation unit may derive the reliability of the product under the manufacturing conditions extracted by the second extraction unit by comparing the manufacturing conditions of the product extracted by the second extraction unit with the manufacturing conditions of the product indicated in the training data.

The derivation unit may derive the reliability based on the similarity between the manufacturing conditions indicated in the training 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 product yield, which is one of the product characteristics predicted by the prediction device.

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

The first extraction unit may extract, from among the products under manufacturing conditions indicated in the training data, products under manufacturing conditions in which the magnitude of the first characteristic falls within a first range and the magnitude of at least one other characteristic falls within a predetermined range. If the first extraction unit cannot extract, from among the products under manufacturing conditions indicated in the training data, products under manufacturing conditions that satisfy at least one unit range of the first range of the first characteristic or at least one unit range of the predetermined range of the at least one other characteristic, the first extraction unit may extract, based on the prediction results, products under manufacturing conditions that satisfy at least one unit range of the first range of the first characteristic or at least one unit range of the predetermined range of the at least one other characteristic.

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

The product may be a compound or a composition.

A manufacturing method according to one aspect of the present invention may include a first extraction step in which a prediction device performs machine learning using a combination of a product's manufacturing conditions and multiple product characteristics as training data to predict products under manufacturing conditions that satisfy specified characteristics, and extracts products under manufacturing conditions in which the magnitude of a first characteristic falls within a first range and the magnitude of at least one other characteristic falls within a predetermined range. The prediction device predicts products under manufacturing conditions that satisfy specified characteristics. The manufacturing method may also include a calculation step in which the products under the manufacturing conditions extracted in the first extraction step are classified into unit ranges of the magnitude of the first characteristic and the number of products under the classified manufacturing conditions is calculated for each unit range of the magnitude of the first characteristic, and the products under the manufacturing conditions extracted in the first extraction step are classified into unit ranges of the magnitude of at least one other characteristic and the number of products under the classified manufacturing conditions is calculated for each unit range of the magnitude of the at least one other characteristic. The manufacturing method may also include a display control step in which a screen indicating the number of products under each unit range of the magnitude of the first characteristic and the number of products under each unit range of the magnitude of the at least one other characteristic is displayed on a display unit.

A program according to one aspect of the present invention may cause a computer to execute a first extraction step of extracting products under manufacturing conditions in which the magnitude of a first characteristic falls within a first range and the magnitude of at least one other characteristic falls within a predetermined range, based on prediction results from a prediction device that performs machine learning using a combination of a product's manufacturing conditions and multiple product characteristics as training data to predict products under manufacturing conditions that satisfy specified characteristics. The program may also cause the computer to execute a calculation step of classifying the products under the manufacturing conditions extracted in the first extraction step into unit ranges of the magnitude of the first characteristic and calculating the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and classifying the products under the manufacturing conditions extracted in the first extraction step into unit ranges of the magnitude of at least one other characteristic and calculating the number of products under the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic. The program may also cause the computer to execute a display control step of displaying on a display unit a screen showing the number of products under each unit range of the magnitude of the first characteristic and the number of products under each unit range of the magnitude of the at least one other characteristic.

Note that the above summary of the invention does not list all of the features of the present invention. Subcombinations of these features may also constitute inventions.

FIG. 2 is a diagram illustrating an example of functional blocks of a product information providing system. FIG. 4 is a diagram illustrating an example of a screen displayed on a display unit. FIG. 10 is a diagram showing an example of a state in which at least one first unit range is selected from a plurality of unit ranges of the magnitude of a second characteristic as at least one other characteristic displayed on the screen. FIG. 10 is a diagram illustrating an example of a list of candidate products in which the reliability of each candidate product is indicated. 10 is a flowchart illustrating an example of a screen display procedure. FIG. 10 is a diagram illustrating an example of a screen showing the number of products for each unit range for each characteristic. FIG. 10 is a diagram illustrating an example of a screen showing the number of products for each unit range for each characteristic. FIG. 2 illustrates an example of a hardware configuration.

The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention as claimed. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

Traditionally, materials research has been conducted to find new or alternative materials. Materials research based on computer analysis, known as materials informatics, is also being conducted. Materials informatics is a method of applying information science and technology to the materials field to develop new materials or search for alternative materials.

Figure 1 shows an example of the functional blocks of a product information provision system 10 that utilizes materials informatics. The product information provision system 10 derives correlations between multiple pieces of input data using artificial intelligence such as machine learning, and provides information about products that meet desired functions, performance, or other characteristics.

When there are a large number of candidate products provided by the product information providing system 10, it may not be easy to select the desired product from among those candidate products. Furthermore, the processing burden on the product information providing system 10 may increase when narrowing down the desired product. Therefore, this embodiment makes it easier to narrow down the desired product to be selected from multiple products, thereby reducing the processing burden on the product information providing system 10.

The 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 with one or more computers. The product information providing system 10 provides an electronic catalog showing information about products whose manufacturing conditions meet the desired characteristic conditions.

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

The data collection unit 102 collects combinations of product manufacturing conditions and multiple product characteristics as training data and stores them in the memory unit 110. Product manufacturing conditions may include at least one of the raw materials that make up the product, the blending ratio of the raw materials that make up the product, and the product manufacturing method. The blending ratio may be a composition ratio or a mass percentage. The manufacturing method includes all conditions related to experiments and manufacturing, such as reaction rate, reaction time, reaction pressure, and stirring conditions. The product may be a chemical product, pharmaceutical, machine part, or food. The product may be a compound or composition. The concept of a product includes not only real products that can be actually manufactured, but also virtual products that have not yet been manufactured, and test products (sample products) that have not yet reached the stage of becoming a real product.

Product characteristics may include appearance (surface gloss), flame retardancy, oil resistance, hardness, cold temperature resistance, heat temperature resistance, oxygen index, tensile strength, elongation, yield, etc. Product characteristics may be any 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's manufacturing conditions as explanatory variables and the product's characteristics as objective variables, to generate a trained model that predicts products under manufacturing conditions that satisfy desired characteristics, and stores the trained model in the memory unit 110. The trained model indicates the relationship between the product's manufacturing conditions and multiple product characteristics. The algorithm may be any type of algorithm, such as a neural network, support vector machine, multiple regression analysis, or decision tree. The prediction unit 106 uses the trained model to predict products under manufacturing conditions in which multiple characteristics each fall within a desired range.

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

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

Based on the prediction results from the prediction device 100, the first extraction unit 202 extracts products with manufacturing conditions in which the magnitude of the first characteristic falls within a first range and the magnitude of at least one other characteristic, a second characteristic (hereinafter also referred to as the "second characteristic"), falls within a predetermined range (hereinafter also referred to as the "second range"). The first and second ranges may be specified in advance by the user. The first and second ranges may be defined as ranges from the minimum to maximum allowable values of the product's first and second characteristics. An example will be described in which the first extraction unit 202 extracts products that satisfy the ranges of two characteristics, but the number of characteristics is not limited to two. The first extraction unit 202 may extract products that satisfy all of the respective ranges of multiple characteristics.

Products with manufacturing conditions extracted by the first extraction unit 202 may include products with manufacturing conditions indicated in the training data. In other words, products with manufacturing conditions extracted by the first extraction unit 202 may include, in addition to products predicted by the prediction device 100, already existing products indicated as training data, i.e., products that have already been proven to be manufacturable.

The first extraction unit 202 may first extract, from the training data, i.e., from existing products, products with manufacturing conditions in which the magnitude of the first characteristic falls within a first range and the magnitude of the second characteristic falls within a second range. In this case, the first extraction unit 202 determines whether any of the extracted existing products satisfies at least one unit range in the first range of the first characteristic or at least one unit range in the second range of the second characteristic. In other words, the first extraction unit 202 determines whether any training data exists that satisfies the conditions for a portion of the first range or the second range. Then, if no existing products are extracted that satisfy at least one unit range in the first range of the first characteristic or at least one unit range in the second range of the second characteristic, the prediction unit 106 predicts products with manufacturing conditions that satisfy at least one unit range in the first range of the first characteristic or at least one unit range in the second range of the second characteristic. Based on the prediction result of the prediction unit 106, the first extraction unit 202 extracts products with manufacturing conditions that satisfy at least one unit range in the first range of the first characteristic or at least one unit range in the second range of the second characteristic.

In other words, if the first extraction unit 202 is unable to extract from existing products products with manufacturing conditions that satisfy the conditions for a partial range of desired characteristics, it may extract products with manufacturing conditions based on the prediction results, only from among products with manufacturing conditions that satisfy the conditions for that partial range of characteristics.

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

The display control unit 214 may cause the display unit 250 to display a screen showing the number of products for each unit range of the magnitude of the first characteristic and the number of products for each unit range of the magnitude of the second characteristic. The display control unit 214 may cause the display unit 250 to display a screen showing the number of products for each unit range of the magnitude of the first characteristic and the number of products for each unit range of the magnitude of the second characteristic in a predetermined format such as a bar graph (histogram), pie chart, or line graph. The display control unit 214 may cause the display unit 250 to display a screen showing an N-dimensional scatter plot in which each of the multiple characteristics is associated with each dimension. The display control unit 214 may cause the display unit 250 to display a screen showing a two-dimensional scatter plot showing the number of products for each unit range of the magnitude of the first characteristic and the number of products for each unit range of the magnitude of the second characteristic. The display control unit 214 may cause the display unit 250 to display a screen showing a map showing manufacturing locations and product characteristics for each manufacturing location. The display control unit 214 may cause the display unit 250 to display, as product characteristics, a screen showing an image of an electron microscope image obtained by capturing an image of the product with an electron microscope. For each characteristic, the number of products per unit range is shown, so that, for example, the quantity of candidate products that exhibit desired characteristics can be immediately ascertained.

The designation unit 210 designates at least one first unit range from among the multiple unit ranges of the magnitude of the first characteristic. The designation unit 210 may designate at least one first unit range by selecting at least one first unit range from the multiple 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 falls within at least one first unit range and the magnitude of the second characteristic falls within a second range. The calculation unit 204 classifies the products under the manufacturing conditions extracted by the second extraction unit 206 into each unit range of the magnitude of the first characteristic and calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic. Furthermore, the calculation unit 204 classifies the products under the manufacturing conditions extracted by the second extraction unit 206 into each unit range of the magnitude of the second characteristic and calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the second characteristic.

In this embodiment, an example will be described in which the first extraction unit 202 extracts products under manufacturing conditions in which the magnitude of the first characteristic falls within a first range and the magnitude of the second characteristic falls within a second range based on the prediction results from the prediction device 100. However, the first extraction unit 202 may extract products under manufacturing conditions in which the magnitudes of three or more characteristics fall within predetermined ranges based on the prediction results from the prediction device 100. The first extraction unit 202 may extract products under manufacturing conditions in which the magnitude of the first characteristic falls within a first range and the magnitude of at least one other characteristic falls within a predetermined range based on the prediction results from the prediction device 100. The second characteristic is an example of at least one other characteristic. The second range is also an example of a predetermined range. The first extraction unit 202 may extract products under manufacturing conditions in which the magnitudes of the first through Nth characteristics (N is a positive integer) fall within predetermined ranges. When the first extraction unit 202 extracts 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 result by the prediction device 100, the second extraction unit 206 may extract 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. When the first extraction unit 202 extracts products under manufacturing conditions in which the magnitudes of the first characteristic to the Nth characteristic (N is a positive integer) each fall within a predetermined range, the second extraction unit 206 may extract products under manufacturing conditions in which the magnitude of the first characteristic is within at least one first unit range and the specific magnitudes of the second characteristic to the Nth characteristic each fall within a predetermined range.

In response to at least one first unit range being specified by the specification unit 210, the display control unit 214 updates the number of products per unit range of the size of the first characteristic and the number of products per unit range of the size of the second characteristic displayed on the screen based on the calculation results by the calculation unit 204.

The designation unit 210 may further designate at least one second unit range from among the multiple unit ranges of the magnitude of the second characteristic. The second extraction unit 206 may further extract products under manufacturing conditions in which the magnitude of the first characteristic falls within at least one first unit range and the magnitude of the second characteristic falls within at least one second unit range. The calculation unit 204 may classify the products under the manufacturing conditions extracted by the second extraction unit 206 into unit ranges of the magnitude of the first characteristic and calculate the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic. Furthermore, the calculation unit 204 may classify the products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of the second characteristic and further calculate the number of products under the classified manufacturing conditions for each unit range of the magnitude of the second characteristic. In response to at least one second unit range being specified by the specification unit 210, the display control unit 214 may further update the number of products per unit range of the size of the first characteristic and the number of products per unit range of the size of the second characteristic displayed on the screen based on the calculation results by the calculation unit 204.

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

The derivation unit 212 derives the reliability of the product for the manufacturing conditions extracted by the second extraction unit 206. The reliability indicates the probability that the product can actually be manufactured. Methods for deriving reliability include a first method in which the reliability is determined based on the relationship between the output result and the training data, and a second method in which the reliability is determined based on the behavior exhibited within the artificial intelligence at the time of output from the prediction device 100. In the first method, the reliability is determined to be higher the more similar the output result (prediction result) of the prediction device 100 is to the training data. There are various criteria for similarity, and for example, the distance between the output result and the most similar training data may be used. In the second method, reliability is determined based on how much internal information of the artificial intelligence has been used, whether small fluctuations will cause large fluctuations in the results, etc. For example, the percentage of neurons used in the neural network may be used as reliability.

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

The derivation unit 212 may derive the reliability of the product for the manufacturing conditions extracted by the second extraction unit 206 by comparing the manufacturing conditions of the product extracted by the second extraction unit 206 with the manufacturing conditions of the product indicated in the training data. The derivation unit 212 may derive the reliability based on the 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 indicating the reliability of the product for 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 indicating a list of products including the reliability of the products extracted by the second extraction unit 206.

The derivation unit 212 may derive the reliability by deriving distances such as Euclidean distance and Manhattan distance between variables (characteristic values) indicated in the manufacturing conditions indicated in the training data and variables (characteristic values) indicated in the manufacturing conditions extracted by the second extraction unit 206. The derivation unit 212 may derive the highest reliability of the products under the manufacturing conditions predicted by the prediction device 100 and the products under the manufacturing conditions indicated in each of the multiple training data as the reliability of the products under the manufacturing conditions predicted by the prediction device 100. Variables indicated in the manufacturing conditions may be values such as the raw material composition ratio, temperature, and time in the manufacturing method. Products under the manufacturing conditions indicated in the training data are actually existing products. If the products under the manufacturing conditions predicted by the prediction device 100 are similar to the products under the manufacturing conditions indicated in the training data, there is a high possibility that the products under the manufacturing conditions predicted by the prediction device 100 can actually be manufactured. In other words, if a product with manufacturing conditions predicted by the prediction device 100 is similar to a product with manufacturing conditions indicated in the training data, the reliability of that product is high. Displaying the reliability of the product provides the user with additional criteria, making it easier for them to select the desired product from among multiple candidate products. This also reduces the processing load on the product information provision system 10.

When selecting a desired product from among candidate products, cost is one of the criteria. Yield is also one of the criteria for determining cost. The prediction device 100 uses the trained model to predict yield as a characteristic of a product under manufacturing conditions. Therefore, the display control unit 214 may cause the display unit 250 to display a screen showing the yield of the product 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 yield of the product extracted by the second extraction unit 206.

Figure 2 is an example of a screen 500 displayed on the display unit 250. Screen 500 includes a bar graph 502 showing the number of products for each unit range of the first characteristic, and a bar graph 504 showing the number of products for each unit range of the second characteristic. Screen 500 also includes list information 506 of candidate products showing the range of the first characteristic shown by bar graph 502 and the range of the second characteristic shown by bar graph 504, and a total number 508 of candidate products included in list information 506. Note that if it is not possible to display all products on one screen in list information 506, the display control unit 214 may use a scroll bar 512 to scroll to display all products.

Figure 3 shows an example of selecting at least one unit range 510 from multiple unit ranges of the magnitude of the second characteristic displayed on the screen 500. The user may select at least one unit range 510 on the screen 500 by dragging the range of the desired characteristic. In response to at least one unit range 510 being specified by the specification unit 210, the display control unit 214 may update the bar graph 502 showing the number of products for each unit range of the magnitude of the first characteristic shown on the screen 500, the bar graph 506 showing the number of products for each unit range of the magnitude of the second characteristic, the list information 506, and the total number 508 based on the calculation results by the calculation unit 204.

Figure 4 shows an example of a list of candidate products, with the reliability of each candidate product displayed. By displaying the reliability of each candidate product, it becomes easier to visually grasp the possibility of actually manufacturing the candidate products.

Figure 5 is a flowchart 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 results from the prediction device 100 (S102). The calculation unit 204 calculates the number of products per unit range for each characteristic for 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 per unit range for each characteristic (S106). The products displayed on the screen include products predicted by the prediction device 100 and products provided as training data. The display control unit 214 may also cause the display unit 250 to display an image showing 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 in a manner that allows the unit range corresponding to the product provided as training data to be distinguished. The display control unit 214 may cause the display unit 250 to display 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 shown in different colors or with lines of different thicknesses.

The designation unit 210 then determines whether a specification of a unit range for the characteristic has been accepted on the screen (S108). The designation unit 210 may accept a specification of a unit range for each of multiple characteristics. In other words, when narrowing down candidate products, the designation unit 210 may accept a specification to narrow down the range for each of multiple characteristics.

When the specification of the unit range of the characteristic is accepted, the second extraction unit 206 limits the range of the characteristic to the specified unit range and extracts products whose manufacturing conditions satisfy the specified range of the characteristic (S110). The calculation unit 204 calculates the number of products per unit range for each characteristic for the products extracted by the second extraction unit 206 (S112). The display control unit 214 updates the screen showing the number of products per unit range for each characteristic and displays it on the display unit 250 (S114).

As described above, according to this embodiment, the range of characteristics of multiple candidate products predicted by the prediction device 100 can be narrowed down on the screen at any time, making it easy to narrow down the candidate products and reducing the processing burden on the product information provision system 10.

Figures 6 and 7 show an example of a screen 600 that shows the number of products per unit range for each characteristic. Screen 600 shows the number of products per classification of the target product's use. Screen 600 shows the number of products per unit range for each of the target product's characteristics: appearance (surface gloss), flame retardancy, oil resistance, hardness, cold temperature resistance, heat temperature resistance, oxygen index, tensile strength, and elongation.

The screen 600 shown in Figure 7 shows an updated version of the screen 600 shown in Figure 6 after narrowing the range of the hardness property to a specified range 602, the range of the oxygen index property to a specified range 604, and the range of the elongation property to a specified range 606.

Figure 8 shows an example of a computer 1200 in which aspects of the present invention may be embodied, in whole or in part. A program installed on the computer 1200 may cause the computer 1200 to perform operations associated with an apparatus according to an embodiment of the present invention or to function as one or more "parts" of the apparatus. Alternatively, the program may cause the computer 1200 to perform the operations or one or more "parts." The program may cause the computer 1200 to perform a process or steps of a process according to an embodiment of the present invention. Such a program may be executed by the CPU 1212 to cause the computer 1200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

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

The communications interface 1222 communicates with other electronic devices via a network. A hard disk drive may store programs and data used by the CPU 1212 in the computer 1200. The ROM 1230 stores boot programs and other programs executed by the computer 1200 upon activation, and/or programs dependent on the computer's hardware. The programs are provided via a computer-readable recording medium such as a CD-ROM, USB memory, or IC card, or via a network. The programs are installed in the RAM 1214 or ROM 1230, which are also examples of computer-readable recording media, and executed by the CPU 1212. The information processing described in these programs is read by the computer 1200, resulting in cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing the operation or processing of information in accordance with the use of the computer 1200.

For example, when communication is performed between computer 1200 and an external device, CPU 1212 may execute a communication program loaded into RAM 1214 and instruct communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of CPU 1212, communication interface 1222 reads transmission data stored in a transmission buffer area provided in RAM 1214 or a recording medium such as a USB memory, and transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

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

Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. CPU 1212 may perform various types of processing on data read from RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search/replacement, etc., as described throughout this disclosure and specified by the program's instruction sequence, and write the results back to RAM 1214. CPU 1212 may also search for information in files, databases, etc. on the recording medium. For example, if multiple entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored on the recording medium, CPU 1212 may search for an entry that matches a condition specified by the attribute value of the first attribute from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

The programs or software modules described above may be stored on computer-readable storage media on or near computer 1200. Recording media such as a hard disk or RAM provided within a server system connected to a dedicated communications network or the Internet can also be used as computer-readable storage media, thereby providing the programs to computer 1200 via the network.

A computer-readable medium may include any tangible device capable of storing instructions that are executed by a suitable device. Consequently, the computer-readable medium having instructions stored thereon comprises an article of manufacture, including 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, etc. More specific examples of computer-readable media may 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, integrated circuit card, etc.

The computer-readable instructions may include either source code or object code written in any combination of one or more programming languages. The source code or object code may include conventional procedural programming languages. The conventional procedural programming languages may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or object-oriented programming languages such as Smalltalk®, JAVA®, C++, etc., and the "C" programming language or similar programming languages. The computer-readable instructions may be provided to a processor or programmable circuitry of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus locally or via a wide-area network (WAN) such as a local area network (LAN), the Internet, etc. The processor or programmable circuitry may execute the computer-readable instructions to create 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, etc.

The present invention has been described above using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be clear to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

The order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," or the like, and it should be noted that processes can be performed in any order, unless the output of a previous process is used in a subsequent process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that it is necessary to perform the processes in that order.

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 (11)

a first extraction unit that performs machine learning using training data on a combination of a product's manufacturing conditions and a plurality of product characteristics, and extracts products under manufacturing conditions in which the magnitude of a first characteristic falls within a first range and the magnitude of at least one other characteristic falls within a predetermined range, based on a prediction result by a prediction device that predicts products under manufacturing conditions that satisfy specified characteristics;
a calculation unit that classifies the products under the manufacturing conditions extracted by the first extraction unit into unit ranges of the magnitude of the first characteristic, calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and classifies the products under the manufacturing conditions extracted by the first extraction unit into unit ranges of the magnitude of the at least one other characteristic, and calculates the number of products under the classified manufacturing conditions 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 including a first area that indicates the number of products for each unit range of the magnitude of the first characteristic in a predetermined format , and a second area that indicates the number of products for each unit range of the magnitude of the at least one other characteristic in a predetermined format ;
a designation unit that designates at least one first unit range among a plurality of unit ranges of the magnitude of the first characteristic included in the first region;
a second extraction unit that extracts products having 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
Equipped with
the calculation unit classifies the products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of the first characteristic, and calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and classifies the products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of the at least one other characteristic, and calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic;
The display control device, in response to the at least one first unit range being specified by the specification unit, updates the number of products per unit range of the size of the first characteristic shown in the first area of the screen and the number of products per unit range of the size of the at least one other characteristic shown in the second area of the screen based on the calculation result by the calculation unit . 2. The display control device according to claim 1 , wherein the designation unit designates the at least one first unit range by selecting the at least one first unit range from a plurality of unit ranges of the size of the first characteristic displayed on the first area of the screen. the designation 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 included in the second region ;
the second extraction unit further extracts products having 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 at least one second unit range;
the calculation unit classifies the products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of the first characteristic, and calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and classifies the products under the manufacturing conditions extracted by the second extraction unit into unit ranges of the magnitude of the at least one other characteristic, and further calculates the number of products under the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic;
3. A display control device as described in claim 1 or 2, wherein the display control unit, in response to the at least one second unit range being specified by the specification unit, further updates the number of products per unit range of the magnitude of the first characteristic shown in the first area of the screen and the number of products per unit range of the magnitude of the at least one other characteristic shown in the second area of the screen based on the calculation result by the calculation unit . 4. The display control device according to claim 1 , wherein the display control unit causes the display unit to display the screen further including a third area that further shows a list of products having the manufacturing conditions extracted by the second extraction unit. a derivation unit that derives reliability of the product under the manufacturing conditions extracted by the second extraction unit according to a predetermined algorithm from a similarity between the product under the manufacturing conditions extracted by the second extraction unit and the teacher data or a usage rate of information inside the artificial intelligence of the prediction device , wherein the reliability is higher as the similarity or the usage rate is higher;
The display control device according to claim 1 , wherein the display control unit causes the display unit to display the screen indicating the reliability of the product of the manufacturing condition extracted by the second extraction unit. The display control device according to claim 1 , wherein the display control unit causes the display unit to display the screen showing a product yield, which is one of the product characteristics predicted by the prediction device. 7. A display control device as described in any one of claims 1 to 6, wherein the first extraction unit extracts, from products under manufacturing conditions indicated in the training data stored in the memory unit of the prediction device , products under manufacturing conditions in which the magnitude of the first characteristic is within a first range and the magnitude of the at least one other characteristic is within a predetermined range, and if it is not possible to extract from products under manufacturing conditions indicated in the training data a product under manufacturing conditions that satisfy at least one unit range of the first range of the first characteristic or at least one unit range of the predetermined range of the at least one other characteristic, extracts, based on the prediction result, a product under manufacturing conditions that satisfy the at least one unit range of the first range of the first characteristic or the at least one unit range of the predetermined range of the at least one other characteristic. 8. The display control device according to claim 1 , wherein the manufacturing conditions include at least one of raw materials constituting the product, a blending ratio of the raw materials, and a manufacturing method for the product. The display control device according to claim 8 , wherein the product is a compound or a composition. a first extraction step of extracting products under manufacturing conditions in which the magnitude of a first characteristic falls within a first range and the magnitude of at least one other characteristic falls within a predetermined range, based on prediction results from a prediction device that performs machine learning using training data on combinations of manufacturing conditions and multiple characteristics of the product and predicts products under manufacturing conditions that satisfy specified characteristics;
a calculation step of classifying the products of the manufacturing conditions extracted in the first extraction step into units of a magnitude range of the first characteristic, calculating the number of products of the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and classifying the products of the manufacturing conditions extracted in the first extraction step into units of a magnitude range of the at least one other characteristic, and calculating the number of products of the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic;
a display control step of displaying on a display unit a screen including a first area showing the number of products per unit range of the magnitude of the first characteristic in a predetermined format for each unit range, and a second area showing the number of products per unit range of the magnitude of the at least one other characteristic in a predetermined format for each unit range ;
a designation step of designating at least one first unit range among a plurality of unit ranges of the magnitude of the first characteristic included in the first region;
a second extraction step of extracting products having 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;
Equipped with
the calculation step includes a step of classifying the products of the manufacturing conditions extracted in the second extraction step into units of a magnitude range of the first characteristic, and calculating the number of products of the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and a step of classifying the products of the manufacturing conditions extracted in the second extraction step into units of a magnitude range of the at least one other characteristic, and calculating the number of products of the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic,
The display control method includes a step of updating the number of products per unit range of the size of the first characteristic shown in the first area of the screen and the number of products per unit range of the size of the at least one other characteristic shown in the second area of the screen based on the calculation result in the calculation step, in response to the at least one first unit range being specified in the specification step . a first extraction step of extracting products under manufacturing conditions in which the magnitude of a first characteristic falls within a first range and the magnitude of at least one other characteristic falls within a predetermined range, based on prediction results from a prediction device that performs machine learning using training data on combinations of manufacturing conditions and multiple characteristics of the product and predicts products under manufacturing conditions that satisfy specified characteristics;
a calculation step of classifying the products of the manufacturing conditions extracted in the first extraction step into units of a magnitude range of the first characteristic, calculating the number of products of the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and classifying the products of the manufacturing conditions extracted in the first extraction step into units of a magnitude range of the at least one other characteristic, and calculating the number of products of the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic;
a display control step of displaying on a display unit a screen including a first area showing the number of products per unit range of the magnitude of the first characteristic in a predetermined format for each unit range, and a second area showing the number of products per unit range of the magnitude of the at least one other characteristic in a predetermined format for each unit range ;
a designation step of designating at least one first unit range among a plurality of unit ranges of the magnitude of the first characteristic included in the first region;
a second extraction step of extracting products having 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;
on the computer ,
the calculation step includes a step of classifying the products of the manufacturing conditions extracted in the second extraction step into units of a magnitude range of the first characteristic, and calculating the number of products of the classified manufacturing conditions for each unit range of the magnitude of the first characteristic, and a step of classifying the products of the manufacturing conditions extracted in the second extraction step into units of a magnitude range of the at least one other characteristic, and calculating the number of products of the classified manufacturing conditions for each unit range of the magnitude of the at least one other characteristic,
The display control step includes a step of updating the number of products per unit range of the size of the first characteristic shown in the first area of the screen and the number of products per unit range of the size of the at least one other characteristic shown in the second area of the screen based on the calculation result in the calculation step, in response to the at least one first unit range being specified in the specification step, a program .