31results about How to "Dig" patented technology

Embodiments of the present specification disclose a data processing method, apparatus and device for insurance fraud identification, and a server. The method may comprise: acquiring relationship association data of a target population, wherein the target population comprises a set of selected applied claimants and insurants; constructing multi-degree relationship network map data for the target population based on the relationship association data; clustering the multi-degree relationship network map data by using an unsupervised learning algorithm to determine a classified communities of thetarget population and corresponding community information; and calculating community characteristics of the classified communities based on the community information, and marking the classified community that meets the insurance fraud decision-making condition as a fraud group. According to the embodiments of the present specification, a group of fraudsters can be effectively and efficiently identified from a multi-degree relationship.

The weather data and traffic intersection passing data are firstly analyzed and preprocessed, and then input into a threshold cyclic neural network (GRU) to extract high-order features of the trafficflow, and the high-order features are input into a gradient lifting decision tree regression model (GBDT) for short-term traffic flow prediction. The method provided by the invention can carry out more in-depth mining analysis on the traffic flow data, and can effectively improve the accuracy of short-term traffic flow prediction after the output layer is changed to GBDT.

An embodiment of the invention discloses an insurance fraud identification data processing method, device, equipment and server. Multi-scale relationship network graph data of crowds are built based on multi-scale relationship association data of insurance applicants and the insured, a relationship network among people can be more deeply mined, identification efficiency is improved, and identification range is widened. Besides, a supervised learning model is jointly built according to characteristic data of insurance fraud people and used for learning relationship network characteristics and characteristics of the insurance fraud people. Ganged insurance fraud people have obvious multi-scale relationship characteristics on the relationship network, the characteristics of the insurance fraud people frequently show up similarity, so that the insurance fraud people can be more effectively and efficiently identified by the method, and identification processing efficiency is improved.

The embodiment of the invention provides a complex network construction method based on combination of mapping and density peak clustering. The method comprises the steps of preprocessing a time sequence through a preprocessing algorithm combining mapping and density peak clustering; Constructing complex networks. According to the method, a preprocessing algorithm combining mapping and density peak clustering is used for optimizing construction of a complex network, the fluctuation mode of a time sequence can be described more accurately, effective information in data can be mined more deeply,and higher robustness is achieved on noise.

The invention discloses an online car-hailing supply and demand prediction method of a neural network. The online car-hailing supply and demand prediction method includes the steps: collecting variousonline car-hailing travel data, utilizing the convolutional neural network to extract features and reduce dimensions, inputting the extracted feature map into the gated recurrent neural network to perform online car-hailing supply and demand prediction, adjusting the model in the training process, and finally, predicting the online car-hailing supply and demand difference through the adjusted model. According to the online car-hailing supply and demand prediction method, the online car-hailing supply and demand difference data can be deeply mined and analyzed, so that the online car-hailing supply and demand prediction is more accurate, and the performance is better.

The invention discloses a transformer substation clustering method considering both voltage sag monitoring information and associated factors thereof. The transformer substation clustering method comprises the steps of establishing a voltage sag event monitoring information index and an associated factor index thereof; inputting voltage sag characteristic index data of a regional power grid transformer substation to be analyzed and carrying out normalization processing on the data; adopting a fuzzy C-means clustering method, clustering the regional power grid transformer substation to be analyzed respectively according to three voltage sag characteristic indexes to obtain clustering results in three dimensions; selecting a key index, adopting the fuzzy C-means clustering method, and clustering the regional power grid transformer substation to be analyzed according to the key index to obtain a comprehensive clustering result; and analyzing voltage sag characteristics of transformer substations of various categories by taking the comprehensive clustering result of the transformer substation as principle and combining the clustering results in three dimensions, and giving a preliminary voltage sag governance suggestion. The transformer substation clustering method provided by the invention has the advantages of comprehensive index setting, good classification effect, rich extracted information and the like.

The invention discloses a chart granularity adjusting method and device, and belongs to the field of data mining. The chart granularity adjusting method includes the steps of obtaining a coordinate of a first point triggered by a user on a chart, obtaining the positions slide and operated by the user in real time, determining granularities corresponding to the positions, obtaining data corresponding to the granularities, keeping the coordinate of the first point in the granularity adjusting direction to be unchanged, and updating data on the chart in real time according to the granularities and the corresponding data. The chart granularity adjusting device comprises a first triggering module, a first obtaining module and a first adjusting module. By means of the chart granularity adjusting method and device, real-tine adjustment and accurate adjustment on the chart granularities are achieved, the granularity adjusting efficiency and the granularity adjusting accuracy are improved, and user operation is simplified.

The invention discloses a Hash code image training model based on binary weight, and a model algorithm comprises the steps: selecting a loss function, determining a target equation, and performing binary coding of a classifier and training image features; performing unified learning of a binary code, updating the binary code, and optimizing the loss function; and deducing the Hash code training model. The invention also discloses a classification learning method employing the Hash code image training model based on binary weight, and the method comprises the steps: obtaining a Hash code of a to-be-searched image through the Hash code training model based on binary weight, and solving Hamming distances between the Hash code and a classifier binary code; searching in the minimum Hamming distance from the Hamming distances, and obtaining the classifier corresponding to the minimum Hamming distance, wherein the classifier is the category to which the to-be-searched image belongs. The method can be used for the image classification for various types of images in high-latitude scenes, improves the performance of an algorithm in a large-scale data set, is precise, efficient and quick, andis small in consumption of the memory.

The embodiment of the invention provides a method for using a smart card service. The method is characterized by including the steps that a client terminal displays a service interface to a user and transmits a service request to a service server according to a user command; the service server feeds the execution result back to the client terminal and/or an intelligent card corresponding to the client terminal according to the service request.

The invention relates to a human body posture estimation method based on a joint relation, and the method comprises the following steps: S1, constructing a joint relation module which comprises two sub-modules: a channel-based feature relation module and an adjacent joint space relation module; s2, constructing a human body posture estimation model based on a joint relation; s3, training a human body posture estimation model based on a joint relation by utilizing the marked human body posture data; and S4, performing a human body posture estimation task based on a single image by using the trained human body posture estimation model added with the joint relation module to obtain a predicted human body posture. Compared with the prior art, the invention effectively overcomes the problem that the positions of four-limb joints with high degree of freedom, such as wrist joints, ankle joints and shielded invisible joints, are difficult to detect in the image, and is high in human body posture estimation accuracy.

The invention relates to the field of computer processing, in particular to a root cause positioning method, a root cause positioning device, a storage medium and electronic equipment. The root cause positioning method comprises the following steps: when service abnormality detection is performed based on calling index data of a called service device in a device calling pair to obtain a result of service abnormality, obtaining service abnormality detection information; performing dependency anomaly detection based on dependency index data of dependency equipment corresponding to the abnormal service equipment in the service anomaly detection information to obtain dependency anomaly detection information; constructing an exception attribute graph according to the service exception detection information and the dependency exception detection information; and when a plurality of abnormal service devices exist, calculating a root cause score of each abnormal service device by using the abnormal attribute graph, and sorting based on the root cause score of each abnormal service device to obtain a service device root cause sorting result. According to the root cause positioning method provided by the invention, fault root cause positioning of the equipment in the system can be accurately and quickly carried out.

The invention provides a multi-gene family identification and evolution analysis method. The method is an independent analysis technology or a joint analysis technology for target species and homologous species. The independent analysis method comprises the steps of protein gene family identification, protein gene family structure information analysis, family gene member chromosome distribution analysis, replication gene event prediction, Motif analysis and protein gene family evolutionary tree analysis. The joint analysis method comprises the following analysis processes: protein gene familyidentification, protein gene family evolutionary tree analysis, Ka/Ks analysis, gene selective evolution analysis and colinearity analysis. The method does not need design of primers, PCR amplification and construction of a genome library; the analysis process is mature, the period is short, the yield is high; analysis results are confirmed through two databases of Pfam and SMART, and the accuracyrate is high; and the method is suitable for DNA sequencing data or protein sequences.