Patent
Characteristic recommendation method and device
TLDR
In this paper, the authors proposed a method for automatic selection of the effective combined characteristics, which are time-saving and labor-saving, effectively solve the difficult problems of time waste and labor waste in the existing manual characteristic selecting process and can improve effectiveness of a recommendation system.Abstract:
The invention discloses a characteristic recommendation method and a characteristic recommendation device. The characteristic recommendation method comprises the following steps: according to an output textual characteristic estimation model, determining target values of textual characteristics in sample data, wherein the output textual characteristic estimation model is obtained according to the optimal combined characteristics selected from training data; according to the target values, sorting the textual characteristics in the sample data and according to a sequence of the target value from high to low, carrying out recommendation on the textual characteristics in the sample data. The characteristic recommendation method and the characteristic recommendation device can realize automatic selection of the effective combined characteristics, are time-saving and labor-saving, effectively solve the difficult problems of time waste and labor waste in the existing manual characteristic selecting process and can improve effectiveness of a recommendation system.read more
Citations
More filters
Patent
Method and device of pushing information and electronic equipment
TL;DR: In this article, a method of pushing the information can improve the quality of information pushing, and includes: utilizing factorization machine (FM) learning to obtain learning feature vectors in a plurality of preset time cycles, wherein each learning feature vector corresponds to a feature in the to-be-pushed information; acquiring browsing statistic vectors of the to be-pushing information in the plurality of time cycles.
Patent
Feature factor determination method and device
TL;DR: In this paper, a feature factor determination method and device is presented, which comprises the steps of obtaining a reference AUC value according to N candidate feature factors, wherein each candidate feature factor is used for describing one type of risk control feature, and the type of the risk control features comprises at least one of the following features of an insuring feature, an underwriting feature, or a claim settlement feature.
Patent
Seasonal characteristics and position characteristics-based rural tourism recommendation method and system
TL;DR: Wang et al. as discussed by the authors proposed a seasonal characteristics and position characteristics-based rural tourism recommendation method and system, which comprises the steps of extracting user evaluation time based on historical user evaluations of scenic spots, extracting seasonal characteristics; according to name and position information of the scenic spots; and by mapping the longitude and latitude information to corresponding tag blocks, constructing geographic space position characteristics ofthe scenic spots.
Patent
Model training method and device used in machine learning
TL;DR: In this paper, the authors proposed a model training method used in machine learning, which comprises the steps of extracting features from training samples; training a pre-established target model by means of the extracted features, wherein the non-linear part of the target model is expressed as the formula in the description; V belongs to R, lambda belongs to RC, D belongs to RL, V, lambda and D are the model parameters of the nonlinear part, and X belongs to RB and represents the feature matrix of the training samples, X=(x1, x2,...xi,...
References
More filters
Patent
Method and system for recommending information
TL;DR: In this article, a method and system for recommending information is presented. But the authors focus on recommending information based on the information similarity model, the statistic model of the behavior data and a user interest model, and the generated comprehensive recommending list is returned to the client as the recommending result.
Patent
Method and system for recommending order
Zheng Qiaoling,Wang Haohong +1 more
TL;DR: In this paper, the authors proposed a method and a system for recommending an order based on recommending correlation function, a recommending ranking function and a related mean accuracy remote memory access protocol (RMAP) function according to preset correlation factors.