AWS Media and Entertainment Japan

Hokkaido Cultural Broadcasting

Document Processing

Established in 1972, Hokkaido Cultural Broadcasting serves its programs to the entire Hokkaido area as an affiliate of the Fuji Television Network .

"Amazon Bedrock helps us to automatically generate an article in about 2 minutes for only a few extra yen per article," says Sugimoto.
We can produce a short video for a single article in minutes, which is less than 20 percent of the old time of 30 minutes to an hour.

Reported impact

Business outcome

Using AWS to help create articles has had a large effect at Hokkaido Cultural Broadcasting. "Amazon Bedrock helps us to automatically generate an article in about 2 minutes for only a few extra yen per article," says Sugimoto.

  • Cost Reduction
  • Productivity Improvement
  • Speed to Market

Solution

Hokkaido Cultural Broadcasting airs a variety of news and shows that showcase the nature, food, and tourist attractions of Hokkaido, Japan. Expanding its online streaming services, the station used generative artificial intelligence (AI) and text-to-speech from Amazon Web Services (AWS) to streamline production of news scripts and videos, resulting in a low-cost solution to deliver more news. The broadcaster also made news sources easier to search using Amazon DynamoDB —a serverless, NoSQL database service. Sugimoto turned to AWS to streamline the production of news articles. Hokkaido Cultural Broadcasting had converted press releases to PDF format on a multifunction printer and emailed the PDF files to the news team.

Data flow

Sugimoto turned to AWS to streamline the production of news articles. Sugimoto built a solution to perform optical character recognition on these PDF files and store the text data on Amazon DynamoDB, letting the team view the releases in text on a management screen. Team members can use keywords to search text information stored on Amazon DynamoDB with less effort.

Solution architecture

5 components · 3 layers
  1. Compute
    • Amazon Bedrock Runs the foundation model layer for the document ingestion and extraction workflows.
    • Claude 2 Provides a large language model used by the document ingestion and extraction workflows.
  2. Storage
    • Amazon DynamoDB Stores high-scale application state and metadata for the document ingestion and extraction workflows.
  3. Serving
    • Amazon QuickSight Presents dashboards and analytics for the document ingestion and extraction workflows.
    • Amazon Polly Generates speech output used by the document ingestion and extraction workflows.

Architecture clues

  • The broadcaster also made news sources easier to search using Amazon DynamoDB —a serverless, NoSQL database service.
  • This mechanism is designed using an AWS serverless environment and has passed internal security regulations.

Evidence from the source

"We didn't know anything about AWS or the cloud to begin with," says Sugimoto.
"With support from AWS, we created a BI tool in just a couple of weeks.
As a solution, Sugimoto created a business intelligence (BI) tool using Amazon QuickSight —which powers data-driven organizations with unified BI at scale—to visualize, aggregate, and analyze the data at a low cost.
Expanding its online streaming services, the station used generative artificial intelligence (AI) and text-to-speech from Amazon Web Services (AWS) to streamline production of news scripts and videos, resulting in a low-cost solution to...
The broadcaster also made news sources easier to search using Amazon DynamoDB —a serverless, NoSQL database service.
The support and plentiful hands-on materials from AWS made it easier for the beginner to get started." Sugimoto's transformative digital data visualization tool was met with great acclaim and won the Japan Commercial Broadcasters...
Transparency Evidence & methodology 95/100 reference value · 90% confidence · 2 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value95/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence90%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability23/25
    11 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance8/10
    The publication date comes from publisher-controlled metadata.
  • Source transparency9/10
    2 source references document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. AWS

    Hokkaido Cultural Broadcasting customer story

    First-party
    https://aws.amazon.com/solutions/case-studies/uhb
    Source type
    Vendor-published customer story
    Published
    Jan 1, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date
  2. Hokkaido Cultural Broadcasting

    UHB 北海道文化放送

    First-party
    https://www.uhb.jp/company/company.html

    The company guide lists '従業員 153名(2026年4月現在)', i.e. 153 employees as of April 2026.

    Source type
    Official company website
    Supports
    • Company size

Date evidence

Not separately sourced Industry, Region. Treat these normalized attributes as lower-confidence until a dedicated source is added.