# US 2020/0394256 A1 · Storage system and storage control method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0394256 A1 - Document ID: US20200394256A1 - Status: Published application - Kind: A1 - Application number: 16/822,982 - Filed: 2020-03-18 - Published: 2020-12-17 - Earliest claimed: 2019-06-12 - Assignees: Hitachi, Ltd. - Applicants: Hitachi, Ltd. - Inventors: Takahiro NARUKO; Hiroaki AKUTSU; Akifumi SUZUKI - Web page: https://patentgrep.com/patent/US20200394256A1 ## CPC - H03M 7/3079: {Context modeling} - G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/2193: {based on specific statistical tests} - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/0475: Generative networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - H03M 7/30: Compression (speech analysis-synthesis for redundancy reduction G10L19/00; for image communication H04N); Expansion; Suppression of unnecessary data, e.g. redundancy reduction - H03M 7/3059: {Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression} - H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A storage system that performs irreversible compression on time-series data using a compressor/decompressor based on machine learning calculates a statistical amount value of each of one or more kinds of statistical amounts based on one or more parameters in relation to original data (time-series data input to a compressor/decompressor) and calculates a statistical amount value of each of the one or more kinds of statistical amounts based on the one or more kinds of parameters in relation to decompressed data (time-series data output from the compressor/decompressor) corresponding to the original data. The machine learning of the compressor/decompressor is performed based on the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the original data and the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the decompressed data. ## Claims ### Claim 1 A storage system comprising: an interface device connected to a storage device; and a processor configured to perform irreversible compression on time-series data using a compressor/decompressor based on machine learning and store post-compression data which is time-series data subjected to the irreversible compression in the storage device, wherein an input to the compressor/decompressor is original data which is pre-compression time-series data, and an output of the time-series data from the compressor/decompressor is decompressed data which is data obtained by decompressing the post-compression data of the time-series data, wherein machine learning of the compressor/decompressor is performed on each of one or more kinds of statistical amounts based on one or more parameters, the time-series data is compressed using the compressor/decompressor after the machine learning, and the post-compression data of the time-series data is stored in the storage device, and wherein the processor calculates a statistical amount value of each of the one or more kinds of statistical amounts based on the one or more parameters in relation to the original data, and calculates a statistical amount value of each of the one or more kinds of statistical amounts based on the one or more parameters in relation to the decompressed data corresponding to the original data, and wherein the machine learning of the compressor/decompressor is performed based on the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the original data and the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the decompressed data. ### Claim 2 (depends on 1) The storage system according to claim 1, wherein the machine learning of the compressor/decompressor is performed based on an objective function set in the compressor/decomposer, and wherein, with regard to each of the one or more kinds of statistical amounts, the processor sets one or more kinds of values regarding a difference between the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the original data and the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the decompressed data in an objective function of the compressor/decompressor. ### Claim 3 (depends on 1) The storage system according to claim 1, wherein the one or more kinds of statistical amounts include at least one a mean and a dispersion, and wherein, with regard to at least one kind of statistical amount among the one or more kinds of statistical amounts, the one or more parameters include the number of samples and a calculation frequency. ### Claim 4 (depends on 1) The storage system according to claim 1, wherein the processor provides a first interface which is an interface receiving an input of one or more parameters necessary to calculate each statistical amount of the one or more kinds of statistical amounts. ### Claim 5 (depends on 4) The storage system according to claim 4, wherein the processor manages information including one or more parameters input via the first interface with regard to each of the one or more kinds of statistical amounts. ### Claim 6 (depends on 4) The storage system according to claim 4, wherein the processor calculates a statistical amount value of each of the one or more kinds of statistical amounts based on one or more parameters input via the first interface in relation to the original data, calculates a statistical amount value of each of the one or more kinds of statistical amounts based on the one or more parameters input via the first interface in relation to decompressed data corresponding to post-compression data of the compressor/decompressor after the machine learning, and provides a second interface which is an interface displaying statistical amount quality that conforms to a difference between a statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the original data and a statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the decompressed data. ### Claim 7 (depends on 6) The storage system according to claim 6, wherein the statistical amount quality is one or more kinds of values regarding the difference between the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the original data and a statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the decompressed data. ### Claim 8 (depends on 4) The storage system according to claim 4, wherein the kind of statistical amount is a kind of statistical amount designated via the first interface. ### Claim 9 A storage control method of a storage system that compresses data and stores the compressed data in a storage device, the method comprising: calculating a statistical amount value of each of one or more kinds of statistical amounts based on one or more parameters in relation to original data which is time-series data input to a compressor/decompressor which is used for irreversible compression and is based on machine learning; calculating a statistical amount value of each of the one or more kinds of statistical amounts based on the one or more kinds of parameters in relation to decompressed data which is output from the compressor/decompressor and corresponds to the original data; and performing the machine learning of the compressor/decompressor based on the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the original data and the statistical amount value calculated for each of the one or more kinds of statistical amounts in relation to the decompressed data.