31results about How to "Dig" patented technology

The invention relates to a monitoring method based on image features and an LLTSA algorithm for a tool wear state. According to the method, an image texture feature extraction technology is introduced into the field of tool wear fault diagnosis, and monitoring for the tool wear state is realized in combination with three flows of ' signal denoising', 'feature extraction and optimization' and 'mode recognition'. The method comprises the steps of firstly, acquiring an acoustic emission signal in a tool cutting process through an acoustic emission sensor, and carrying out signal denoising processing through an EEMD diagnosis; secondly, carrying out time-frequency analysis on a denoising signal through S transformation, converting a time-frequency image to a contour gray-level map, extracting image texture features through a gray-level co-occurrence matrix diagnosis, and then further carrying out dimensionality reduction and optimization on an extracted feature vector through a scatter matrix and the LLTSA algorithm to obtain a fusion feature vector; and finally training a discrete hidden Markov model of the tool wear state through the fusion feature vector, and establishing a classifier, thereby realizing automatic monitoring and recognition for the tool wear state.

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 provides a relation predicating method, a device and electronic equipment. The relation predicating method comprises the steps of fusing a plurality of medicament single-attribute similarity networks, a plurality of target single-attribute similarity network and a plurality of disease single-attribute similarity networks, thereby obtaining a fused medicament similarity network, a fused target similarity network and a fused disease similarity network; constructing a three-element heterogeneous network according to the fused medicament similarity network, the fusedtarget similarity network and the fused disease similarity network; predicting the network node of the three-element heterogeneous network, and obtaining a first association relation which comprisesa first medicament-target association relation, a second medicament-disease association relation and a first target-disease association relation. Therefore medicament-target-disease three-element association relation information can be sufficiently mined. The similarity networks of multiple attributes of medicament, disease and target are fused. Accuracy reduction of the predication result causedby eccentricity caused by a single attribute is prevented.

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 invention discloses a device for measuring a seismic wave speed and electromagnetic attenuation of hydrate-containing sedimentary media. The device comprises a reaction vessel. The reaction vessel comprises a base. An outer cylinder and an inner cylinder are arranged on the base. A top cover is arranged above the outer cylinder and the inner cylinder. The reaction vessel is arranged in a constant temperature box. Magnets are arranged at the outer side of the top cover. The magnets are wound by coils. The reaction vessel is further connected with a gas bottle. A rubber film is arranged at the outer side of the outer cylinder. A confining pressure is set at the outer side of the rubber film. A sample is arranged between the outer cylinder and the inner cylinder. A data collection device is arranged on the sample. The invention further discloses a method for measuring the seismic wave speed and electromagnetic attenuation of hydrate-containing sedimentary media. The device and the method can be used to measuring dynamic properties of hydrate samples.

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 invention discloses a multi-keyword expansion retrieval method based on a ciphertext. The method comprises steps of extracting a keyword set from the data source; constructing an inverse documentvector set based on the keyword set and grouping the inverse document vector set; carrying out B + index tree construction on each vector set, carrying out encryption through a security KNN algorithm,then encrypting a data source through a symmetric encryption algorithm, uploading the encrypted index tree sets and the data source to a cloud server, carrying out fuzzy processing on retrieval keywords input by a user, and carrying out correction according to the situation of input errors of the user; And finally, carrying out semantic analysis operation on the fuzzy query keyword set, expandingthe query keyword set, generating a query vector according to the keyword set subjected to semantic analysis, carrying out grouping processing on the trap door by utilizing the trap door obtained after the processing of an encryption algorithm, and uploading the trap door to a cloud server. From the perspective of trap door expansion, fuzzy processing and semantic analysis are carried out on theretrieval keywords input by the user, and the use experience of the user is improved.

The present invention discloses an extraction method for metagenome, and a method of probe hybridization-bead capture is used to reduce the host DNA content in a host metagenomic DNA sample. According to the method, the Alu repeat sequence of the host DNA sequences and conserved sequence at both ends thereof are used as templates to design one-way or two-way probes, wherein the 5 'end of each probe is modified with biotin, streptavidin coated beads are used to capture host DNA hybridized with probes, in order to achieve aims of weakening host DNA background in a metagenome, and enhancing sequencing data efficiency.

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 provides a low-voltage power distribution network operation state evaluation method based on data mining. The method comprises the following steps: S1, establishing a low-voltage power distribution network loop impedance model according to collected and processed low-voltage power distribution network data; S2, evaluating and analyzing the short-term operation state of the low-voltage power distribution network according to the loop impedance model; s3, evaluating and analyzing medium and long-term operation states of the low-voltage power distribution network according to the loop impedance model; and S4, performing multi-index evaluation based on the improved radar map. According to the method, the operation state of the low-voltage power distribution network side is evaluated, the big data technology is applied to the power distribution network data, useful values can be efficiently and deeply excavated, and power grid personnel are assisted to make operation decisions; the operation effect of the power distribution network is comprehensively evaluated, the implicit rule among the related data of the power distribution network is mined, and visual display is realized.

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 discloses an image hash code training model algorithm and a classification learning method based on binary weights. The model algorithm steps include: selecting a loss function, determining an objective equation, and performing binary encoding on classifiers and training image features; Code for unified learning, update binary code, optimize loss function; derive hash code training model. Also disclosed is a classification learning method using a hash code image training model based on binary weights. The steps include: the image to be searched is obtained through the hash code training model based on binary weights to obtain the hash code, and the hash code and the hash code are obtained. The Hamming distance between the binary codes of the classifiers; find the minimum Hamming distance in the Hamming distance, and obtain the corresponding classifier, which is the category of the image to be searched. The invention can classify images in multiple image categories and high-latitude scenes, improve the performance of algorithms on large-scale data sets, and is accurate, efficient, fast and low in memory consumption.

The present invention relates to a human body posture estimation method based on joint relationship, comprising the following steps: S1: building a joint relationship module, including two sub-modules, a channel-based feature relationship module and an adjacent joint space relationship module; S2: building a human body based on joint relationship Pose estimation model; S3: use the labeled human pose data to train the human pose estimation model based on the joint relationship; S4: use the trained human pose estimation model with the joint relationship module to perform the human pose estimation task based on a single image, and obtain the prediction human body posture. Compared with the prior art, the present invention effectively overcomes the problem that it is difficult to detect the position of limb joints with high degrees of freedom such as wrist joints, ankle joints and hidden invisible joints in the image, and the accuracy of human body posture estimation is high.

An embodiment of the invention provides a relation predicating method, a device and electronic equipment. The relation predicating method comprises the steps of fusing a plurality of medicament single-attribute similarity networks, a plurality of target single-attribute similarity network and a plurality of disease single-attribute similarity networks, thereby obtaining a fused medicament similarity network, a fused target similarity network and a fused disease similarity network; constructing a three-element heterogeneous network according to the fused medicament similarity network, the fusedtarget similarity network and the fused disease similarity network; predicting the network node of the three-element heterogeneous network, and obtaining a first association relation which comprisesa first medicament-target association relation, a second medicament-disease association relation and a first target-disease association relation. Therefore medicament-target-disease three-element association relation information can be sufficiently mined. The similarity networks of multiple attributes of medicament, disease and target are fused. Accuracy reduction of the predication result causedby eccentricity caused by a single attribute is prevented.

The invention discloses a method for evaluating an extreme coherent gust amplitude of wind direction change, and a wind direction change value. The problems of unit life shortening and tower collapse accidents due to inaccurate evaluation of fan load in the prior art are solved, and the method comprises the following steps of acquiring a long-term wind measurement data sample of a site, identifying wind speed and wind direction data by using a GAI judgment function; determining a gust event meeting requirements in the site sample data, and fitting a calculation relation between a probability function and a theoretical probability through a sample gust amplitude actually measured; obtaining an extreme coherent gust amplitude of site direction change, and conducting Dir function fitting on an average wind speed value and a direction change value of the site gust event; and determining the extreme coherent gust direction change value of the site wind direction change. The method is high in practicability and relatively easy to operate, deeper mining on wind resource evaluation data is performed, and the method is an optimal method which accords with the actual situation of extreme coherent gust of which the direction changes once a site encounters within fifty years.

The invention discloses a device for measuring a seismic wave speed and electromagnetic attenuation of hydrate-containing sedimentary media. The device comprises a reaction vessel. The reaction vessel comprises a base. An outer cylinder and an inner cylinder are arranged on the base. A top cover is arranged above the outer cylinder and the inner cylinder. The reaction vessel is arranged in a constant temperature box. Magnets are arranged at the outer side of the top cover. The magnets are wound by coils. The reaction vessel is further connected with a gas bottle. A rubber film is arranged at the outer side of the outer cylinder. A confining pressure is set at the outer side of the rubber film. A sample is arranged between the outer cylinder and the inner cylinder. A data collection device is arranged on the sample. The invention further discloses a method for measuring the seismic wave speed and electromagnetic attenuation of hydrate-containing sedimentary media. The device and the method can be used to measuring dynamic properties of hydrate samples.

The present invention is applicable to the technical field of thermal power plants, and provides an online load prediction method of thermal power plants, comprising: obtaining historical thermal power plant load data and performing fractional accumulation generation transformation to obtain a fractional accumulation generation sequence of historical thermal power plant loads; The power plant load data forecasting model predicts the fractional order accumulation generation sequence of thermal power plant load; by performing fractional order accumulation on the predicted thermal power plant load fractional order accumulation generation sequence, the online prediction value of thermal power plant load is restored, and the present invention can overcome gray Problems that cannot be directly solved for load forecasting, such as the nonlinearity of correlation solution and related constraints, are suitable for forecasting problems with complex parameters and can be extended to multi-system output. It has the characteristics of clear physical meaning, small amount of calculation and high precision.

The invention discloses a substation clustering method that takes into account voltage sag monitoring information and associated factors, including establishing voltage sag event monitoring information indicators and associated factor indicators; inputting voltage sag characteristic index data of power grid substations in areas to be analyzed , and carry out normalization processing; using the fuzzy C-means clustering method, clustering the substations of the power grid in the area to be analyzed according to the three voltage sag characteristic indicators respectively, and obtaining the clustering results in three dimensions; selecting key indicators, using fuzzy The C-means clustering method, according to the key indicators, clusters the substations of the power grid in the area to be analyzed to obtain a comprehensive clustering result; mainly based on the comprehensive clustering results of the substations, combined with the clustering results of three dimensions, the voltage sag of each category of substations is analyzed characteristics, and give preliminary suggestions for voltage sag control. The clustering method of the invention has the advantages of comprehensive index setting, good classification effect, rich extracted information and the like.

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 discloses a method and a device for adjusting the granularity of a chart, belonging to the field of data mining. The method includes: acquiring the coordinates of the first point triggered by the user on the chart; acquiring the sliding position of the user operation in real time, and determining the granularity corresponding to each position; acquiring data corresponding to each granularity; keeping the first point at the granularity The coordinates in the adjustment direction remain unchanged, and the data on the chart are updated in real time according to the various granularities and corresponding data. The device includes: a first trigger module, a first acquisition module and a first adjustment module. The invention realizes the real-time adjustment and precise adjustment of the granularity of charts, improves the efficiency and accuracy of granularity adjustment, and simplifies user operations.

The invention discloses a neural network-based method for correcting rotation differences of multimodal remote sensing images. It includes the following steps: S1: Obtain a group of multimodal remote sensing image pairs with the same target scene, and perform image preprocessing; S2: For each preprocessed image, calculate phase consistency eigenvalues ​​and orientation angles, and according to the phase Consistency eigenvalues ​​and orientation angles to calculate the rotation feature vector of the image; S3: use the rotation feature vectors of the two images as the input of the neural network, and calculate and output the predicted difference angle of the two images; S4: Based on the predicted difference angle, complete multiple Modal remote sensing image rotation difference angle correction. The invention effectively solves the technical problem of quickly and accurately predicting the rotation difference angle between multimodal remote sensing images in the case of only simple image data information, and gets rid of the limitation of auxiliary geographic space information.

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.