Abstract: Provided is a report writing support system including: a document model determination unit that determines a document model storing a template of a draft to be presented to a user, on the basis of an answer to a selective question and a question determination model that determines a further question to the answer; a template application unit that asks a descriptive question for asking a question about a content lacking in the template of the draft stored in the document model on the basis of the determined document model and the answer or a further answer, and applies an answer to the descriptive question to the template of the draft; and a presentation processing unit that presents the template of the draft, to which the answer to the descriptive question is applied, as a draft to be presented to the user.

Abstract: A method for reinforcement learning (RL) of continuous actions. The method may include receiving a state as input to at least one actor network to predict candidate actions based on the state, wherein the state is a current observation; outputting the candidate actions from the at least one actor network; receiving the state and the candidate actions as inputs to a plurality of distributional critic networks, wherein the plurality of distributional critic networks calculates quantiles of a return distribution associated with the candidate actions in relation to the state; outputting the quantiles from the plurality of distributional critic networks; and selecting an output action based on the candidate actions and the quantiles.

Abstract: The draft document generating method repeats question processing for component elements selected from the case database to the user. The question processing presents, by an output device, one or more of the component elements selected from the case database to the user, presents a question as to whether the component elements are applicable to contents of a draft document to the user, acquires, via an input device, an answer of the user to the question; and adds the answer in an answer history. The selecting of the one or more component elements for which the question processing is to be executed next from unprocessed component elements in the plurality of cases is based on statistics of part of the component elements in the plurality of cases. The draft document is generated based on a component element indicating that the answer history is applicable to contents of the draft document.

Abstract: The measurement guide device is able to easily select the next measurement target on the basis of previously obtained measurement results. The measurement guide device includes a database, a similarity search section, and a next-point proposal section. The database stores a virtual measured signal and a measurement procedure that are obtained by simulation. The similarity search section extracts, from the database, virtual measured signals similar to measurement results obtained by a measurement device, and measurement procedures regarding the virtual measured signals. The next-point proposal section selects at least one measurement procedure from the measurement procedures obtained by the similarity search section, and determines the next measurement point.

Abstract: A simulation estimation model estimates a feature value of a simulation result of a material from a descriptor of the material. A material feature value estimation model estimates a feature value of the material from the estimation result of the simulation estimation model and the descriptor of the material. One or more processors input a descriptor of a first material into the simulation estimation model to acquire a first simulation estimation result of the feature value of the first material. The one or more processors input the first simulation estimation result and the descriptor of the first material into the material feature value estimation model to acquire the feature estimation value of the first material.

Abstract: A system for determining a material to propose to a user is disclosed. The system calculates an availability evaluation value indicating availability for a user of each of materials based on a chemical formula of each of the materials. The system estimates a physical property value of each of the materials based on a chemical formula of each of the materials. The system calculates a physical property evaluation value of each of the materials based on an estimation result of the physical property value of each of the materials. The system calculates an overlooking risk evaluation value indicating priority of presenting each of the materials to the user based on the availability evaluation value and the physical property evaluation value of each of the materials. The system selects a material to present as a candidate material from the materials according to the overlooking risk evaluation value.

Abstract: One or more storage devices store a first machine learning model and a second machine learning model. The one or more processors generate each low-dimensional descriptor including the predetermined number of elements for multiple materials, and predict each characteristic value of the multiple materials from the low-dimensional descriptor. One or more processors select a part of materials from multiple materials based on the characteristic value, and generate a high-dimensional descriptor having the number of elements larger than the predetermined number. One or more processors predict each characteristic value of the part of the materials from the high-dimensional descriptor using the second machine learning model.

Abstract: Provided is a report writing support system including: a document model determination unit that determines a document model storing a template of a draft to be presented to a user, on the basis of an answer to a selective question and a question determination model that determines a further question to the answer; a template application unit that asks a descriptive question for asking a question about a content lacking in the template of the draft stored in the document model on the basis of the determined document model and the answer or a further answer, and applies an answer to the descriptive question to the template of the draft; and a presentation processing unit that presents the template of the draft, to which the answer to the descriptive question is applied, as a draft to be presented to the user.

Abstract: The system includes a material property prediction presenting unit, a cross-task compatible feature value generating unit, and a material property predicting unit. The material property prediction presenting unit accepts a specification of first task data that includes a record in which a material property is unknown and is to be a target of material property prediction through a first predictive model. The cross-task compatible feature value generating unit predicts feature values from material compositions in the first task data by using a second predictive model. The material property predicting unit generates the first predictive model by using the material compositions, experimental condition, feature values, and the known material property in the first task data. Also, the material property predicting unit inputs the material composition, experimental condition, and feature value in a record in which the material property is unknown in the first task data and predicts the unknown material property.

Abstract: Effective compound feature quantities reflecting expert knowledge are efficiently generated to thereby accurately predict physical properties of an unknown compound with a device for predicting a material property using a case-by-case material database storing a plurality of case databases. The case databases include a plurality of records that record structural information about material structures in association with material properties about properties of materials. This device is includes a chemical space designation unit that receives a designation of at least one case database; an autoencoder learning unit that generates an autoencoder for converting structural information corresponding to the case database received by the chemical space designation unit to multi-variables; and a material property prediction unit that predicts material properties using the multi-variables converted by the autoencoder generated by the autoencoder learning unit.

Abstract: The present invention defines a spatial structure of a molecule without allowing freedom with respect to the selection of a coordinate system and predicts material properties based on a spatial structure of the molecule.

Abstract: Automated analysis of particle beam measurement results is facilitated by a device that calculates a spatial parameter distribution representing spatial structure of a sample based on a scattering pattern corresponding to projection of the spatial structure of the sample to wavenumber space, the projection being obtained by detecting scattering of a particle beam which enters the sample and intersects with the sample.

Abstract: The measurement guide device is able to easily select the next measurement target on the basis of previously obtained measurement results. The measurement guide device includes a database, a similarity search section, and a next-point proposal section. The database stores a virtual measured signal and a measurement procedure that are obtained by simulation. The similarity search section extracts, from the database, virtual measured signals similar to measurement results obtained by a measurement device, and measurement procedures regarding the virtual measured signals. The next-point proposal section selects at least one measurement procedure from the measurement procedures obtained by the similarity search section, and determines the next measurement point.

Abstract: A silicon-containing curing composition including a specific amount of a silicon-containing polymer having an Mw of 300 to 100,000 obtained by hydrolysis and condensation of an organosilane mixture containing specific amounts of organosiloxanes of formulae (1-1) through (1-5); a specific amount of a prepolymer containing at least two Si—H groups per molecule obtained by hydrosilylation between a cyclic siloxane compound of formula (2) and a compound of formula (3-1), (3-2), or (3-3); a specific amount of a linear siloxane compound containing more than one carbon-carbon double bond reactive with Si—H or Si—CH3 per molecule; specific amounts of an organic peroxide and a metal catalyst; and a specific amount of a filler. The details for the formulae (1-1) to (1-5), (2), (3-1) to (3-3) are as described in the specification.

Abstract: A silicon-containing curing composition including a specific amount of a silicon-containing polymer having an Mw of 300 to 100,000 obtained by hydrolysis and condensation of an organosilane mixture containing specific amounts of organosiloxanes of formulae (1-1) through (1-5); a specific amount of a prepolymer containing at least two Si—H groups per molecule obtained by hydrosilylation between a cyclic siloxane compound of formula (2) and a compound of formula (3-1), (3-2), or (3-3); a specific amount of a linear siloxane compound containing more than one carbon-carbon double bond reactive with Si—H or Si—CH3 per molecule; specific amounts of an organic peroxide and a metal catalyst; and a specific amount of a filler. The details for the formulae (1-1) to (1-5), (2), (3-1) to (3-3) are as described in the specification.

Abstract: A curable composition includes: 100 parts by mass of a silicon-containing polymer having a Mw of 3,000 to 100,000 obtainable by hydrolysis-condensation of an organosilane mixture including R1SiX3, R2SiX3, R3R4SiX2 and R5SiX3, the total of R2SiX3 and R3R4SiX2 being 5 to 60 mol %, optionally a prepolymer, optionally a cyclic siloxane compound, 0.0001 to 10 parts by mass of an organic peroxide and optionally a metal catalyst, and 10 to 1,500 parts by mass of a filler, wherein R1 is a C2-6 alkenyl group, R2 is a C1-6 alkyl group, R3 and R4 are each a C1-6 alkyl group, R5 is a phenyl group optionally substituted with a C1-6 alkyl group, and X is a C1-6 alkoxy group, one or more of R2 to R4 is a methyl group, f represents a number of 2 to 10, g represents a number of 0 to 8, and n represents 1 or 2.

Abstract: A curable composition includes: 100 parts by mass of a silicon-containing polymer having a Mw of 3,000 to 100,000 obtainable by hydrolysis-condensation of an organosilane mixture including R1SiX3, R2SiX3, R3R4SiX2 and R5SiX3, the total of R2SiX3 and R3R4SiX2 being 5 to 60 mol %, optionally a prepolymer, optionally a cyclic siloxane compound, 0.0001 to 10 parts by mass of an organic peroxide and optionally a metal catalyst, and 10 to 1,500 parts by mass of a filler, wherein R1 is a C2-6 alkenyl group, R2 is a C1-6 alkyl group, R3 and R4 are each a C1-6 alkyl group, R5 is a phenyl group optionally substituted with a C1-6 alkyl group, and X is a C1-6 alkoxy group, one or more of R2 to R4 is a methyl group, f represents a number of 2 to 10, g represents a number of 0 to 8, and n represents 1 or 2.