# US 11,443,145 B2 · Data analyzing device and data analyzing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,145 B2 - Document ID: US11443145B2 - Status: Granted - Kind: B2 - Application number: 16/507,062 - Filed: 2019-07-10 - Published: 2020-02-13 - Granted: 2022-09-13 - Earliest claimed: 2018-08-07 - Assignees: Keyence Corporation - Applicants: Keyence Corporation - Inventors: Taiga Nomi; Yasunobu Umehara - Web page: https://patentgrep.com/patent/US11443145B2 ## CPC - G06F 18/2113: by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation - G06F 18/211: Selection of the most significant subset of features - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/2415: based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate - G06F 18/24323: {Tree-organised classifiers} - G06F 18/24765: {Rule-based classification} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract To enable effectively narrowing down features to be generated, thereby generating effective features at a high speed, in obtaining the features from a large volume of data. A fixed rule and an additional rule are stored in advance. The fixed rule specifies a rule of a calculation operation for generating a new feature. The additional rule specifies whether to perform a calculation operation for generating the new feature on a basis of meta-information, not depending on whether the fixed rule is applicable. An objective variable is predicted from plurality of features on the basis of the fixed rule and the additional rule. ## Claims ### Claim 1 A data analyzing device for analyzing analysis target data, comprising: a data input unit which receives an input of analysis target data including a plurality of features and an objective variable; a display unit which displays a list of the plurality of features input by the data input unit; a supplementary information adding unit which adds supplementary information to each of the plurality of features in the list displayed by the display unit based on an input by a user; a rule storage unit which stores a fixed rule and an additional rule, the fixed rule specifying a rule of a calculation operation for generating a new feature from the feature alone or a combination of the plurality of features, and the additional rule specifying whether to perform a calculation operation for generating the new feature on a basis of the supplementary information added by the supplementary information adding unit, not depending on whether the fixed rule is applicable; and a prediction model generating unit which generates a prediction model for predicting the objective variable from the plurality of features, on a basis of the fixed rule and the additional rule stored in the rule storage unit. ### Claim 2 (depends on 1) The data analyzing device according to claim 1, wherein the supplementary information includes a degree of importance. ### Claim 3 (depends on 2) The data analyzing device according to claim 2, wherein the additional rule includes a rule that prevents a calculation operation of a combination of the plurality of features in which the degrees of importance of the supplementary information are less than a first predetermined value. ### Claim 4 (depends on 2) The data analyzing device according to claim 2, wherein the additional rule includes a rule that allows a calculation operation of only a combination of the feature in which the degree of importance of the supplementary information is less than the first predetermined value and the feature in which the degree of importance of the supplementary information is equal to or greater than a second predetermined value, which is higher than the first predetermined value. ### Claim 5 (depends on 1) The data analyzing device according to claim 1, wherein the supplementary information includes a system of units. ### Claim 6 (depends on 5) The data analyzing device according to claim 5, wherein the additional rule includes a rule that allows no calculation operation except for subtraction, for a combination of the features in which the systems of units of the supplementary information are time. ### Claim 7 (depends on 1) The data analyzing device according to claim 1, wherein the supplementary information includes information relating to whether the feature is controllable by the user. ### Claim 8 (depends on 1) The data analyzing device according to claim 1, wherein the additional rule includes a blacklist rule that specifies a condition for preventing a calculation operation for generating a new feature. ### Claim 9 (depends on 1) The data analyzing device according to claim 1, wherein the additional rule includes a whitelist rule that specifies a condition for allowing a calculation operation for generating a new feature. ### Claim 10 (depends on 8) The data analyzing device according to claim 8, wherein the additional rule includes the whitelist rule that specifies a condition for allowing a calculation operation for generating a new feature, and the blacklist rule is applied before the whitelist rule is applied. ### Claim 11 (depends on 9) The data analyzing device according to claim 9, wherein the additional rule includes a blacklist rule that specifies a condition for preventing a calculation operation for generating a new feature, and the whitelist rule is applied before the blacklist rule is applied. ### Claim 12 (depends on 1) The data analyzing device according to claim 1, wherein the additional rule includes a selection forcing rule that specifies a condition for making the feature remain as a new feature at any time. ### Claim 13 (depends on 1) The data analyzing device according to claim 1, which is configured to allow a user to add a type of the supplementary information. ### Claim 14 A data analyzing method for analyzing analysis target data, comprising: receiving an input of analysis target data including a plurality of features and an objective variable; displaying a list of the plurality of features input; allowing a user to input and add supplementary information to each of the plurality of features in the displayed list; storing a fixed rule and an additional rule, the fixed rule specifying a rule of a calculation operation for generating a new feature from the feature alone or a combination of the plurality of features, and the additional rule specifying whether to perform a calculation operation for generating the new feature on a basis of the supplementary information capable of being added by the supplementary information adding unit, not depending on whether the fixed rule is applicable; and generating a prediction model for predicting the objective variable from the plurality of features, on a basis of the fixed rule and the additional rule that are stored.