# US 2023/0274465 A1 · Information compression system and information compression method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0274465 A1
- Document ID: US20230274465A1
- Status: Published application
- Kind: A1
- Application number: 18/103,038
- Filed: 2023-01-30
- Published: 2023-08-31
- Earliest claimed: 2022-02-25
- Assignees: Hitachi, Ltd.
- Applicants: Hitachi, Ltd.
- Inventors: Hiroaki AKUTSU; Katsuto SATO; Takahiro NARUKO
- Web page: https://patentgrep.com/patent/US20230274465A1

## CPC

- G06T 9/001: {Model-based coding, e.g. wire frame}
- G06T 9/002: {using neural networks}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The present disclosure provides an information compression system that is capable of achieving higher compression efficiency. A data acquisition section acquires data. A generation section (segmentation section and integration section) determines each object depicted by the data and a sense of each object, and according to results of the determination, generates compression target data by converting values of elements in the data to identification information indicating each object and the sense of each object. A data storage section generates compressed data by compressing the compression target data. This makes it possible to convert highly random element values to slightly random identification information and compress the resulting converted information while reducing the amount of information. Consequently, the compression ratio can be increased.

## Claims

### Claim 1

An information compression system that compresses data, the information compression system comprising:
an acquisition section that acquires the data;
a generation section that determines each object depicted by the data and a sense of each object, and generates compression target data according to results of the determination, the compression target data being obtained by converting values of individual elements in the data to identification information that indicates each object and the sense of each object; and
a compression section that generates compressed data by compressing the compression target data.

### Claim 2 (depends on 1)

The information compression system according to claim 1,
wherein the acquisition section further acquires point cloud data that includes a plurality of pieces of coordinate information indicating individual positions of a surface of the object, and
the generation section generates integrated data, as the compression target data, according to the point cloud data and the results of the determination, the integrated data including the coordinate information regarding each position of the surface of the object and the identification information identifying the object existing at the position indicated by the coordinate information.

### Claim 3 (depends on 2)

The information compression system according to claim 2, wherein the acquisition section acquires the point cloud data from the data.

### Claim 4 (depends on 2)

The information compression system according to claim 2, wherein the compression section converts the compression target data to data that is obtained by normalizing and quantizing the coordinate information included in the compression target data, and compresses the resulting converted data.

### Claim 5 (depends on 2)

The information compression system according to claim 2, wherein the compression section converts the compression target data to data that is obtained by replacing values representing individual pieces of identification information included in the compression target data according to the object and similarity of the sense, and compresses the resulting converted data.

### Claim 6 (depends on 2)

The information compression system according to claim 2, wherein the compression section converts the compression target data to list format data that is obtained by arranging values representing the coordinate information and color-indicating values generated from individual pieces of identification information included in the compression target data, and compresses the resulting converted data.

### Claim 7 (depends on 1)

The information compression system according to claim 1, wherein the compression section converts the compression target data to three-dimensionally arrayed data that has values of the identification information as values of individual elements, and compresses the resulting converted data.

### Claim 8 (depends on 1)

The information compression system according to claim 1, wherein the generation section and the compression section are integrally built by a learned model.

### Claim 9 (depends on 2)

The information compression system according to claim 2, wherein the compression section compresses coordinate information included in the compression target data on the basis of the individual pieces of identification information.

### Claim 10 (depends on 1)

The information compression system according to claim 1, further comprising:
a decompression section that generates decompressed data by decompressing the compressed data; and
a generation section that processes the decompressed data and outputs the resulting processed data.

### Claim 11 (depends on 10)

The information compression system according to claim 10, further comprising:
a data usage section that provides an interface for designating at least either a space where or a time when the data is acquired,
wherein the decompression section decompresses the compressed data according to the designation made by the interface.

### Claim 12

An information compression method that is used by an information compression system for compressing data, the information compression method comprising:
acquiring the data;
determining each object depicted by the data and a sense of each object, and generating compression target data according to results of the determination, the compression target data being obtained by converting values of individual elements in the data to identification information indicating each object and the sense of each object; and
generating compressed data by compressing the compression target data.
