‘Catch Me Up’ Gen AI Tennis Summaries: Wimbledon and IBM new digital experience

Wimbledon and IBM launch new generative AI technology that will allow them to cover more stories and serve a wider audience. The 'Catch Me Up' is an IBM feature to enhance Wimbledon digital experience. The feature leverages the Generative AI ability of watsonx to provide personalised ‘catchup’ match summaries.

For two weeks every year in July, the All England Lawn Tennis Club (AELTC) organisation hosts Wimbledon, the most prestigious tournament in the sport. IBM has been partnering with the club for more than three decades, enhancing coverage of the championships and engaging fans with rich data-driven insights. This year, some of the most compelling stories of the championships, Wimbledon, will be told powered by IBM® watsonx™, the enterprise-ready generative AI platform, with its latest feature, 'Catch Me Up'.

AI is increasingly being implemented and changing the sports experiences and industry. Billions of people share their passions for sports and AI as something being integrated in our daily lives is becoming a powerful tool for sports organisations and sports personalities, sports organisations and federations and the sports practitioners and of course their fans.

Tennis is the 4th most famous sports modality in the world. Bearing that in mind is a big audience of 1.2 billion people and AI and related tech is increasingly being integrated in multiple dimensions of the sports.

IBM watsonx technology for sports: Generative AI use cases for enhanced customer engagement and experiences at Wimbledon

The All England Lawn Tennis Club (AELTC) and IBM are expanding their use of generative artificial intelligence (Gen AI) at this year’s Wimbledon, using the technology to create automated, personalised catchup summaries across the championships, Wimbledon’s digital channels.

‘Catch Me Up’ generates pre- and post-match player cards with AI-generated player stories containing key statistics and match highlights, as well as longer-form daily summaries of the day’s action.

Gen AI was first introduced at last year’s tournament when it was used to create automated spoken word commentary for its highlights, and the AELTC and IBM believe the technology can help them cover more matches and serve diverse audiences, complementing their existing coverage.

“So, this service is offering a very quick and easy way to come in and pick up on what those key storylines are that are relevant to you and to make sure that you’re aware of what’s going on. The top seed and the show courts, of course, get a lot of coverage. But there’s a lot of tennis going on across 18 courts over the two weeks, which means not all the stories get told,” added Kevin Farrar, head of sports partnerships at IBM and the company’s lead for the Wimbledon partnership.

‘Catch me up’ Wimbledon and IBM: Key Features

The ‘Catch Me Up’ feature at Wimbledon, designed in collaboration with IBM, uses advanced generative AI to provide timely player updates, highlight key storylines, and engage audiences. Powered by IBM's watsonx technology, the information is written in the tone of Wimbledon, maintaining authenticity and reliability from official data sources.

“There’s an awful lot happening during the Championships, especially early on in the championships, Wimbledon, and although we’d all love to spend all day, every day watching everything on three screens, that’s not possible for everyone”, Chris Clements, digital products lead at the AELTC, told about the project.

The feature is powered by IBM’s watsonx AI and data platform and the company’s Granite large language model (LLM), which has access to Wimbledon’s treasure trove of data and has been trained in the championships, Wimbledon’s editorial style. Watsonx integrates effortlessly with Wimbledon's operations, providing regulatory compliance and data integrity.

The AI model is trained solely on tennis data, taking into account aspects such as the possibility of winning based on substantial historical data. It combines structured data, such as match statistics, with unstructured data, like news and opinions, to create dynamic content and data visualisation tools. The result is interesting player narratives created in collaboration with AI and human expertise, which improves the overall Wimbledon experience.

“The top seed and the show courts, of course, get a lot of coverage. But there’s a lot of tennis going on across 18 courts over the two weeks, which means not all the stories get told,” said Kevin Farrar, head of sports partnerships at IBM and the company’s lead for the Wimbledon partnership.

The new feature displays pre-match analysis of recent performance and likelihood to win predictions, and post-match will include key statistics and highlights - available via wimbledon.com and the Wimbledon 2024 App. 

Gen AI has attracted the attention of plenty within the sports industry, but several implementations have been gimmicky, ineffective, or haven’t been Gen AI at all. Given both Wimbledon and IBM claim to only innovate if they can provide genuine value to fans, and not just for the sake of it, the rest of the industry should be paying attention to its latest application of the technology.

The championships, Wimbledon’s expanded use should also be interpreted as evidence of Gen AI’s maturity, with many properties now using it across their editorial, customer service, marketing, operational, and sporting activities.

The player cards will be based on individual user preferences, location, and other data related to their user profile, such as favourite players.

Wimbledon will also use Gen AI to provide greater coverage of more matches, including wheelchair events, with watsonx also being used to provide bullet point-based previews and post-match reviews for singles events on IBM Slamtracker.

The tennis Grand Slam has used AI across its digital operations for several years. Intelligent algorithms create data-driven metrics designed to engage fans across the championships, Wimbledon’s platforms, while video highlights are created using computer and audio recognition technology.
 

Gen AI ‘Catch Me Up’ behind-the-scenes benefits

The Catch Me Up feature saves the Wimbledon editorial team hours of time and frees them up to write more engaging stories and manage higher-value tasks. Behind the scenes, the process begins by collecting a huge volume of data from player rankings and momentum to games and sets played. This structured and unstructured data is managed by IBM® watsonx.data™, a data store built on an open lake house architecture that enables flexible, scalable access by applications across the Club’s hybrid cloud servers. Using a model trained and tuned in IBM® watsonx.ai™, the generative AI application extracts and summarises relevant data and generates stories in natural language, adapted to Wimbledon’s style and tone of voice. The entire workflow is managed and monitored using IBM® watsonx.governance™ to deliver reliable, integrated performance.

“We want to be able to bring that to life and Gen AI is helping us do that. It opens the door to create stories for the junior, senior, under-14 and the wheelchair tournaments. There might be great stories unfolding but the content team might not have capacity to cover them. This is about complementing the output of humans", says Kevin Farrar.

When asked by SportsPro how far away fans were from being able to demand personalised video highlights packages, IBM’s sports partnerships head, Kevin Farrar, said:

“I think it’s going to come, it’s technically possible but there is still a lot of ongoing work in that space. There’s some exciting possibilities and there is a push for more content that provides a more personalised experience.”

Long-standing tech partnerships in sports are increasingly leveraging advanced technologies to broaden their storytelling capabilities and reach a wider audience. Last year, Generative AI was deployed to create audio commentary. IBM is also renowned for its application in events like The Masters.