Data processing system and data processing method

Patent metadata

Field	Value
Publication number	US-10747768-B2
Application number	US-201615374191-A
Country	US
Kind code	B2
Filing date	Dec 9, 2016
Priority date	Jun 14, 2016
Publication date	Aug 18, 2020
Grant date	Aug 18, 2020

Abstract

There is provided a data processing system. A storing unit stores ontology data. A selection unit selects a data stream including key information corresponding to a query using the ontology data stored in the storing unit, among data streams including key information uniquely given to sensor data. A processing unit processes the selected data stream.

First claim

What is claimed is:

1. A data processing system comprising:
a storage device storing work procedure ontology data generated from a work procedure manual subjected to natural language processing, a series of assembly operation elements being connected in an order of the work procedure manual; and
a processor configured to:
partition first sensor data into data pieces;
associate each data piece of the partitioned first sensor data with each assembly operation element of the series of assembly operation elements;
determine a set of learning data by performing machine learning using the partitioned first sensor data as a teacher data set;
calculate a degree of similarity between the learning data and each assembly operation element of the series of assembly operation elements;
compare second sensor data sequentially obtained from a sensor installed in an assembly process with the learning data to extract an assembly operation element with a highest degree of similarity from the series of assembly operation elements;
reconfigure the extracted assembly operation element with the highest degree of similarity as first sequence information;
reconfigure the work procedure ontology data into second sequence information;
compare the first sequence information with the second sequence information; and
in response to the extracted assembly operation element reconfigured as the first sequence information being different from an assembly operation element in the second sequence information, output a result indicating a failure.

2. The data processing system according to claim 1 , wherein the processor is further configured to:
determine the assembly operation element of the series of assembly operation elements using the work procedure ontology data; and
extract second sensor data corresponding to the determined assembly operation element.

3. The data processing system according to claim 1 , wherein:
the storage device is configured to store a data processing routine template associated with the work procedure ontology data, and
the processor is configured to select a data stream and process the selected data stream abased on the data processing routine template.

4. The data processing system according to claim 1 , wherein:
time information is included in data obtained by cutting out the second sensor data into a time window having a predetermined time period, and
the processor is configured to use the first sequence information and the second sequence information to detect a failure of a product assembly time.

5. A data processing method comprising:
storing work procedure ontology data generated from a work procedure manual subjected to natural language processing, a series of assembly operation elements being connected in an order of the work procedure manual;
partitioning first sensor data into data pieces
associating each data piece of the partitioned first sensor data with each assembly operation element of the series of assembly operation elements;
determining a set of learning data by performing machine learning using the partitioned first sensor data as a teacher data set;
calculating a degree of similarity between the learning data and each assembly operation element of the series of assembly operation elements;
comparing second sensor data sequentially obtained from a sensor installed in an assembly process with the learning data to extract an assembly operation element with a highest degree of similarity from the series of assembly operation elements;
reconfiguring the extracted assembly operation element with the highest degree of similarity as first sequence information;
reconfiguring the work procedure ontology data into second sequence information;
comparing the first sequence information with the second sequence information; and
in response to the extracted assembly operation element reconfigured as the first sequence information being different from an assembly operation element in the second sequence information, outputting a result indicating a failure.

Assignees

• Fuji Xerox Co Ltd

Inventors

• Watanabe Masao

Classifications

• G06F16/24568 Primary

  Data stream processing; Continuous queries · CPC title

• G06F16/217

  Database tuning (G06F16/2282 takes precedence; database performance monitoring G06F11/3409) · CPC title

• G06F16/24575

  using context · CPC title

• G06F16/24573

  using data annotations, e.g. user-defined metadata · CPC title

• G06F16/258 Primary

  Data format conversion from or to a database · CPC title