[ad_1]
The food service industry faces severe labor, quality control and sustainability challenges exacerbated by the pandemic. According to NSF International, a product testing and certification organization, more than half of quick service restaurant (QSR) managers find employee turnover an issue for their business, with 20% saying it has had the biggest negative impact on operations. The past several months. One in 10 managers and employees admitted to NSF in a February survey that, when faced with high volumes, they have recently skipped automatic cleaning cycles or ignored error messages on devices.
Ingo Stork-Wersberg says his company PreciTaste has a solution – the key ingredient is AI. PreciTaste sells a service that monitors food quality in quick-service kitchens, predicts demand and supply, and provides preparation recommendations to staff.
PreciTaste has been bootstrapped as of today, marking the close of the startup’s $24 million Series A round. Melitas Ventures and Cleveland Avenue LLC co-led the fund, which was founded by Shake Shack CEO Danny Meyer, with investors including the CEOs of Burger King and McDonald’s and Enlightened Hospitality Investments.
“The pandemic has increased the need for digital optimization in the QSR space. While other industries are experiencing a slowdown, foodservice operators continue to focus on digital solutions to create kitchen efficiencies, which is a key reason for our … funding,” Stork-Wersberg told TechCrunch. “For the QSR operator, PreciTaste is a platform for authentic, on-demand cooking. Increase efficiency, improve quality and reduce food waste with our proprietary ‘always on’ kitchen management system. The technology has been proven to reduce take-out costs and food waste by instructing workers to cook only as much as they want.
Image Credits: Exactly
Storck-Würsberg originally developed technology at the Technical University of Munich and co-founded PreciTaste with his wife Laura ten years ago. The company began as PreciBake, focusing on automating baking processes in commercial ovens.
PreciTaste’s current flagship is designed to handle a wide range of tasks, like how many burgers to prepare before the lunch rush. First, the system predicts demand by monitoring store traffic (via cameras), sales systems and available items. Then it uses additional cameras in the kitchen to check the supply and determine the amount of food to cook.
Suggestions (eg, “Grill two burger patties,” “Bake bun for 40 minutes at 375 degrees”) are relayed to staff via touch screen. Depending on whether the QSR operator decides to enable the feature, you’ll see alerts if orders are incorrect. Managers can track jobs on the back end in one or more restaurants.
Stork-Würsberg claims that PreciTaste can eliminate a significant amount – 85% – of food waste at the point of sale, a claim that could discourage restaurant customers. Fast-service food prices rose 7.3 percent in May due to inflation, prompting diners to cut back on spending. A recent study found that 54% of consumers in the US are dining out more often, and 33% are choosing to “shop around” in their restaurant choices.
Image Credits: Exactly
But AI systems are only as accurate as the data used to train them. Unfortunately, Stork-Worsberg declined to say what samples were used to train PreciTaste’s algorithms, or whether the system works similarly on different types of food and kitchen layouts.
“PreciTaste uses proprietary data augmentation [machine] Based on a vast and rapidly growing library of food service data that includes image data from the 19,000 meals we currently track every five minutes, learning methods provide our customers with scalable and multi-region computer vision. he said. “To enable computer vision to work in any kitchen, including unfamiliar environments or conditions, PreciTaste uses growing recipe simulation data in its machine learning pipeline to add robustness to different grease levels, ratios, kitchen equipment (including gloves), closures and and others.
When asked about another hot-button topic – privacy – Stork-Wersberg said camera data is “mostly” deleted immediately. PreciTaste’s competitor, Uncle AI, has been described unflatteringly by some publications as a “surveillance” outfit.
“PreciTaste offers an offline-first edge AI solution. As such, we have complete control over what happens to our customers’ data and can accommodate their data protection needs and data retention policies, says Stork-Wersberg. “Because our model training and optimization requires computational resources that are not available at the edge, some data is uploaded anonymously to our servers. Most data is analyzed at the edge and in most cases is deleted immediately.”
Stork-Worsberg said PreciTaste’s prep tracking system is now installed at more than 1,500 locations, including a “growing list” of fast-casual restaurants based in the United States. (He won’t name brands.) But the company may face a tough road ahead with competition from the likes of Dragontail Systems, Leanpath, Winnow, Miso Robotics and the aforementioned Uncle.
Stork-Worsberg argues that technological superiority is PreciTaste’s differentiator.
Image Credits: Exactly
The system not only helps restaurants run more smoothly, but also collects data to ensure management is following best practices even when there is no management in place. Thus, it removes a blind spot and gives senior management previously unavailable numbers to base their decisions on. “PreciTaste combines advanced computer vision and deep learning to deliver an AI kitchen management solution.”
PreciTaste employs 98 people in Germany, India and the US and plans to hire 25 more by the end of the year.
[ad_2]
Source link
