Technological tasks
The Tech-tasks module is tasks related to the development, implementation and improvement of new technologies, products and processes. If you have development, implementation and other needs you can post information below.
Development of the embedding-service and its integration into kb-retriever
To develop a centralized micro-embedding service for converting text into vector representations (embeddings) and integrate it into kb-retriever
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Neurotechnology and artificial IntelligenceNumber of applications
1
Integration and optimization of the 2GIS cartographic service into the mobile application at React Native / Expo
To develop a sustainable and productive solution for integrating 2GIS maps into the React Native/Expo mobile app to enhance navigation and user experience.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Other technological solutionsNumber of applications
1
Forecasting demand and operational load in the delivery service
Create a technological solution for predicting the volume of orders and the load on the delivery system, allowing you to plan resources in advance and improve the quality of service.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Technologies in transport and logisticsNumber of applications
0
Intelligent optimization of delivery routes, taking into account business constraints
To develop an intelligent technological solution for automatic optimization of delivery routes, aimed at reducing delivery time, reducing operating costs and increasing the efficiency of courier resources.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Technologies in transport and logisticsNumber of applications
2
Integration of EDI with eGov Mobile for signing documents by individual entrepreneur drivers
Goal: To create a reliable and scalable mechanism for automatically signing documents (acts of completed works, invoices) Sole proprietors are taxi drivers through the eGov Mobile mobile app. The task arose during the implementation of a document management automation project for Yandex partners.Taxi. The existing aggregator APIs do not allow sending notifications about documents to be signed directly to the EDI system. We need to develop a solution that ensures: - Automatic loading of documents from the aggregator system. - Guaranteed delivery of notifications to the driver. - Signing documents via eGov Mobile using CEP. - Registration of the signing status in the corporate system.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
New production technologiesNumber of applications
2
TECHNOLOGICAL SPECIFICATION: SUPERIMPOSING A DIGITAL AVATAR ON VIDEO RECORDINGS OF BASKETBALL MATCHES
The goal of the project is to implement in a mobile sports application the function of automatic analysis of exercise technique based on user–uploaded videos based on free computer vision models (pose estimation). At the first stage, two basic exercises are considered: • pull-ups on a horizontal bar; • push-ups from the floor. The system must: • accept video from the user (portrait/landscape orientation, side view); • automatically find a person and his supporting projectile (horizontal bar, floor) on the video; • extract the skeletal model (coordinates of joints by frames); • calculate key biomechanical parameters of the equipment; • identify typical errors and the quality level of execution; • give the user a short rating (score) and 2-4 personalized recommendations. Available free pose assessment solutions are used for implementation.: • MediaPipe Pose / BlazePose (Google, free model for 33 skeleton key points); • OpenCV for working with video and basic preprocessing; • Python/Node.js for backend processing; • If necessary, ONNX Runtime / TensorFlow Lite for optimization.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Technologies in transport and logisticsNumber of applications
2
Computer Vision Management Platform: Data Markup, Training and Model Management (CV MLOps)
To develop a single platform for a full cycle of work with computer vision: image/video uploading and storage, data markup, quality control, model training, versioning, deployment and monitoring of the quality of models in operation.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Neurotechnology and artificial IntelligenceNumber of applications
2
Fatigue monitoring system for truck drivers
To develop an intelligent system for monitoring the condition of truck drivers in real time in order to detect signs of fatigue, drowsiness and loss of concentration, as well as to prevent traffic accidents.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Industrial SafetyNumber of applications
6
Video analytics system for smart helmets with video cameras
To develop a video analytics system that receives a video stream from employees' smart helmet cameras and identifies risk situations, security violations and incidents in real time, sending notifications to the dispatcher/shift supervisor and recording events in a log.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Neurotechnology and artificial IntelligenceNumber of applications
3
Development of predictive analytics system for industrial plants based on AI
To create a predictive analytics system for monitoring industrial equipment and technological processes in order to predict failures, optimize maintenance and increase production efficiency.
Decision acceptance deadline
22.01.26 (inclusive)
Preferred systems
Smart Field Information SystemsNumber of applications
4
