Method of recommending elderly care service

Abstract

The invention provides a method of recommending elderly care service. The method is characterized by including the following steps: (1) a service platform obtaining score information S of elderly careservice through an Internet webpage or a preset elderly care database, calculating the similarity degree sim' (u, v) between a user u to be recommended and a user v in the Internet webpage or the preset elderly care database; (2) establishing an evaluation time model, and calculating, by the service platform, a preference value Pu, i of the user u to be recommended and the user v in the Internetwebpage or the preset elderly care database; (3) predicting an elderly care service score S (u, i) required by the user to be recommended, and recommending, by the service platform, an elderly care service score S (u, i) to the user to be recommended in order from high to low. The beneficial effects of the method are that the recommended elderly care service fully takes into account the social circle, social characteristics and social trust of users and also takes into account changes in the interest of the users, so that recommended elderly care service institutions or the elderly care service are more user-friendly and rational.

Description

technical field [0001] The invention relates to the technical field of elderly care services, in particular to a method for recommending elderly care services. Background technique [0002] In China, the aging rate is accelerating and the negative population growth rate is increasing. It is predicted that in the next 20 years, the proportion of China's elderly population will double, and by 2050, the proportion of elderly people aged 60 and above will exceed 30%, and the society will enter a stage of deep aging. will become increasingly prominent. Because of such a growth situation, the pension issue has become a hot issue that everyone pays attention to. The increase in the number of elderly people has led to the rapid development of the elderly care service industry. More and more people pay attention to how to provide for the elderly. Nowadays, the issues related to the elderly care are also important to solve. [0003] With the rapid development of the Internet, there...

AI Technical Summary

Problems solved by technology

Some of the current recommendation algorithms for elderly care platforms only filter spam information, or recommend popular services, and recommend a certain service under a specific category. Such recommendation methods cannot meet the individual needs of customers and fail to meet user satisfaction. It also loses the original meaning of recommendation, and at the same time, it will lead to the loss of users, the unstable operation of the platform, and the loss of the platform

[0004] At present, the more common recommendation algorithm is the collaborative filtering algorithm, which determines that users with similar behavioral interests like the same product, but this cannot accurately perceive the user's real preferences, and there is no social and trust relationship between similar users, so it is recommended The results will be biased; the popular recommendation method is likely to cause the "Matthew effect". The service does not mean that the service is not good, but that users do not actively search, and the recommendation algorithm does not make recommendations, resulting in the failure to provide users with diverse services. Such a recommendation system loses its meaning; the user-based collaborative filtering algorithm is suitable for users Under few conditions, the new behavior of the user does not necessarily cause an immediate change in the recommendation result, and the real-time performance is poor, so the recommendation for the user is not accurate enough.

Images