Care schedule and automated caregiver matching algorithm based on an integrated care database

Abstract

This recommendation engine shortens the time required from care plan creation to matching caregiver schedules, reduces workload through improved operational efficiency, and ultimately enables users to receive higher quality care services. [Solution] The recommendation engine comprises a data collection module, an analysis and learning engine, a recommendation module, and a service delivery interface. The data collection module collects user behavior data in real time. The analysis and learning engine individually analyzes the work history data of caregivers and organizes the availability conditions and probabilities of each caregiver using an AI algorithm. Based on the learned data, the recommendation module recommends the most suitable caregiver for the completed care plan. The service delivery interface learns and updates to improve caregiver satisfaction and recommendation accuracy, and automatically recommends schedules.

Description

Technical Field

[0006]

[0001] The present invention relates to a care schedule and a caregiver automatic matching algorithm based on an integrated care database.

Background Art

[0002] In South Korea and Japan, the aging population is rapidly increasing to the extent that they will enter a hyper-aged society in 2024. As a result, the population requiring care and nursing is also increasing rapidly. In such a situation, it is urgent to improve the work efficiency of the personnel engaged in caregiving services. In particular, it takes a huge amount of time to grasp the user's condition, create an appropriate care plan, and match a caregiver suitable for the plan. In the present invention, a recommendation engine using AI is proposed to shorten this time.

Summary of the Invention

Problems to be Solved by the Invention

[0003] The object of the present invention is as follows. 1. Construct a recommendation engine that efficiently collects and analyzes user data and provides personalized services. 2. Utilize artificial intelligence and machine learning algorithms to improve the recommendation accuracy. 3. Improve the speed of service provision and realize a SaaS-based platform that can be extended to multiple users.

Means for Solving the Problems

[0004] The present invention consists of the following components.

[0005] 1. Data collection module: Collect user behavior data in real time. Collect and utilize both structured data and unstructured data.

[0006] 2. Analysis and Learning Engine: The collected data includes individual analysis of caregiver work history data. The AI ​​algorithm organizes the work availability conditions and probabilities for each caregiver.

[0007] 3. Recommendation Module: Based on learned data, it recommends the most suitable caregiver for the completed care plan.

[0008] 4. Service Delivery Interface: Learns and updates in real time through user interaction, improving caregiver satisfaction and recommendation accuracy, and automatically recommending schedules. [Effects of the Invention]

[0009] This invention makes it possible to shorten the time required from the creation of a care plan to the matching of caregiver schedules. Furthermore, it reduces the workload through improved operational efficiency, ultimately enabling users to receive higher quality care services. [Brief explanation of the drawing]

[0010] [Figure 1] This is a system configuration diagram of the recommendation engine (language model and location / time model configuration diagram). [Figure 2] This is a system configuration diagram of the recommendation engine (learning system for the caregiver recommendation model). [Figure 3] This is an example of a user interface. [Modes for carrying out the invention]

[0011] 1. User behavior data collection - A specialized application for elderly care records caregivers' work history, the condition of clients, family satisfaction, workplace, travel distance, working hours, and more in real time. - Integrate additional data using external APIs. 2. Recommendation Algorithms - User-specific behavioral data is vectorized and input into a machine learning model. - Uses a location- and time-based prediction model. - Continuous learning will be conducted, taking into account the user's condition and satisfaction level. 3. Providing personalized results - We recommend the most suitable caregiver, taking into consideration the contents of the care plan (schedule, time, location, and duties). - We improve satisfaction and continuously enhance recommendation accuracy based on user information updated in real time.

Claims

1. A recommendation engine that collects and analyzes user data to provide recommended caregiver schedules.

2. A recommendation algorithm that uses filtering based on location and time prediction methods combined with user ratings.

Images