Abstract: This application provides a keyword extraction method. The method includes: receiving an information entity including a title and a text; performing word segmentation on the text, to obtain a plurality of candidate words; and performing character segmentation on the title corresponding to semantics of the text, to obtain a plurality of characters; sequentially inputting the plurality of candidate words to a keyword extraction model, to obtain an attention weight of each candidate word relative to each character; selecting, from the plurality of candidate words, a candidate word that appears in the title; determining an extraction threshold according to an attention weight of the selected candidate word relative to each character; and determining a keyword of the text of the information entity from the candidate words according to the extraction threshold. This application further provide a method for training a keyword extraction model, a computer device, and a storage medium.

Abstract: The present invention belongs to the field of environment monitoring, particularly relates to a CO2 storage state networking monitoring device, system and method with multi-information fusion. The present invention comprises: obtaining orientation electrical signal data and real-time pressure signals, analyzing a fluid flowing state at a view of a pressure sensor through the real-time pressure signals, and obtaining a CO2 flowing state through the orientation electrical signal data; and obtaining a CO2 regional storage state by combining an orientation CO2 content, a CO2 flowing state and the fluid flowing condition at the view of the pressure sensor. By combining accurate short-range CO2 boundary monitoring of orientation electrodes with long-range monitoring of pressure sensors to achieve a wide range of CO2 flowing state monitoring, the present invention can observe more data with higher reliability and effectively aims at the problem of strong inter-well heterogeneity.

Abstract: This application discloses network congestion control methods and apparatuses. In an implementation, a method comprises: obtaining, by the an intelligent network interface card comprised in a network congestion control apparatus, at least two types of traffic. Identifying, by the intelligent network interface card, algorithm matching features of the at least two types of traffic, and in response to determining to perform congestion control on one type of traffic of the at least two types of traffic, determining, by the intelligent network interface card, a congestion control algorithm that matches an algorithm matching feature of the one type of traffic. Performing, by the intelligent network interface card, congestion control on the one type of traffic according to the congestion control algorithm that matches the algorithm matching feature of the one type of traffic.

Abstract: The present invention belongs to the field of geological exploration and specifically relates to the fault characterization method and system for precise navigation of deep oil and gas based on image fusion, aiming to solve the problem that faults in deep formations are difficult to characterize with conventional seismic interpretation methods. The present invention includes: obtaining amplitude gradient images by calculating amplitude gradient vectors; calculating dip attribute images based on the enhanced seismic data; fusing gradient amplitude attribute fault confidence region with dip angle attribute data volume that defines the fault position through a hierarchical wavelet transform method to obtain a superimposed fault attribute map; dividing bead-like structures based on superimposed fault attribute maps; calculating the score of branch fault data points based on the center point position of bead-like structures, and dividing and analyzing the dominant fault areas.

Abstract: The invention belongs to the field of environmental monitoring, and in particular relates to a method for optimally selecting a carbon storage site based on multi-frequency band seismic data.

Abstract: The present invention provides a processing method and device for data of a well site test based on a knowledge graph. The processing method for the data of the well site test based on the knowledge graph comprises: carrying out format identification on received historical data of the well site test to generate format identification results; establishing a mind map according to the format identification results; generating the knowledge graph of the data of the well site test according to the mind map; and processing the historical data of the well site test and new data of the well site test according to the knowledge graph.

Abstract: The present invention belongs to the field of treatment for data identification and recording carriers, and specifically relates to a method and system for analyzing filling for a karst reservoir based on spectrum decomposition and machine learning, which aims to solve the problems that by adopting the existing petroleum exploration technology, the reservoir with fast lateral change cannot be predicted, and the development characteristics of a carbonate cave type reservoir in a large-scale complex basin cannot be identified. The method comprises: acquiring data of standardized logging curves; obtaining a high-precision 3D seismic amplitude data body by mixed-phase wavelet estimation and maximum posteriori deconvolution and enhancing diffusion filtering. According to the method and the system, the effect of identifying the development characteristics of the carbonate karst cave type reservoir in the large-scale complex basin can be achieved, and the characterization precision is improved.

Abstract: The present disclosure belongs to the field of geological prospecting and particularly relates to an intelligent real-time updating method and system for a stratigraphic framework with geosteering-while-drilling, aiming to solve the problems of insufficient precision in position and dipping angle of a stratigraphic framework due to differences in parameters measured by different instruments for well logging and mud logging while drilling.

Abstract: The present disclosure belongs to the field of capture, utilization, and storage of carbon dioxide, particularly relates to a method and system for intelligently identifying a carbon storage box based on a GAN network, and aims at solving the problem that the analysis accuracy of a fault zone area in the prior art is insufficient. The method comprises the steps: delineating seismic waveform data of a stable sedimentary area through a GAN network, and removing seismic waveform data points in the fault zone area; obtaining a stable sedimentary background seismic waveform data invertomer; obtaining a three-dimensional wave impedance prediction data volume; making a difference to obtain an abnormal wave impedance data volume; retaining abnormal wave impedance data of fault-karst in the three-dimensional variance attribute volume to obtain a fault-karst wave impedance data volume; and then obtaining a carbon storage box interpretation model.

Abstract: A refinement option recommendation system provides suggestions for completed search queries and refinement options. Upon receiving, at a search engine for a site, a portion of a search query from a user, the refinement option recommendation system determines a completed search query based on the portion of the search query. For example, if the portion includes “bak” or “baking,” the completed search query suggestion may include “baking recipe books” or “baking ingredients.” The refinement option recommendation system also determines a refinement option associated with the completed search query based on historical queries. For example, the refinement option may include recipe books associated with a particular culture based on historical queries by the user or by other users. As such, a first suggestion for the completed search query and a second suggestion for the refinement option are both provided to the user.

Abstract: The present invention belongs to the field of environment monitoring, particularly relates to a CO2 storage state networking monitoring device, system and method with multi-information fusion. The present invention comprises: obtaining orientation electrical signal data and real-time pressure signals, analyzing a fluid flowing state at a view of a pressure sensor through the real-time pressure signals, and obtaining a CO2 flowing state through the orientation electrical signal data; and obtaining a CO2 regional storage state by combining an orientation CO2 content, a CO2 flowing state and the fluid flowing condition at the view of the pressure sensor. By combining accurate short-range CO2 boundary monitoring of orientation electrodes with long-range monitoring of pressure senors to achieve a wide range of CO2 flowing state monitoring, the present invention can observe more data with higher reliability and effectively aims at the problem of strong inter-well heterogeneity.

Abstract: The present invention belongs to the field of treatment for data identification and recording carriers, and specifically relates to a method and system for analyzing filling for a karst reservoir based on spectrum decomposition and machine learning, which aims to solve the problems that by adopting the existing petroleum exploration technology, the reservoir with fast lateral change cannot be predicted, and the development characteristics of a carbonate cave type reservoir in a large-scale complex basin cannot be identified. The method comprises: acquiring data of standardized logging curves; obtaining a high-precision 3D seismic amplitude data body by mixed-phase wavelet estimation and maximum posteriori deconvolution and enhancing diffusion filtering. According to the method and the system, the effect of identifying the development characteristics of the carbonate karst cave type reservoir in the large-scale complex basin can be achieved, and the characterization precision is improved.

Abstract: This disclosure relates to a search result processing method and apparatus, and a storage medium. The method may include acquiring a search result according to a search keyword and obtaining an accurate matching score of the search result relative to the search keyword. The method may further include determining a semantic matching weight vector of the search result, a semantic representation vector of the search keyword, and a semantic representation vector of the search result. The method may further include obtaining a semantic matching score of the search result relative to the search keyword according to the semantic representation vectors and the semantic matching weight vector. The method may further include obtaining a similarity between the search result and the search keyword according to the accurate matching score and the semantic matching score.

Abstract: The present invention provides a processing method and device for data of a well site test based on a knowledge graph. The processing method for the data of the well site test based on the knowledge graph comprises: carrying out format identification on received historical data of the well site test to generate format identification results; establishing a mind map according to the format identification results; generating the knowledge graph of the data of the well site test according to the mind map; and processing the historical data of the well site test and new data of the well site test according to the knowledge graph.

Abstract: The present invention belongs to the field of treatment for data identification and recording carriers, and specifically relates to a method and system for evaluating the filling characteristics of a deep paleokarst reservoir through well-to-seismic integration, which aims to solve the problems that by adopting the existing petroleum exploration technology, the reservoir with fast lateral change cannot be predicted, and the development characteristics of a carbonate cave type reservoir in a large-scale complex basin cannot be identified. The method comprises: acquiring data of standardized logging curves; obtaining a high-precision 3D seismic amplitude data body by mixed-phase wavelet estimation and maximum posteriori deconvolution and enhancing diffusion filtering. According to the method and the system, the effect of identifying the development characteristics of the carbonate karst cave type reservoir in the large-scale complex basin can be achieved, and the characterization precision is improved.

Abstract: The present disclosure provides an earthquake evaluation method based on multi-type geophysical data.

Abstract: A feature extraction is performed on transaction data to obtain a user classification feature and a transaction classification feature. A first dimension feature is constructed based on the user classification feature and the transaction classification feature. A dimension reduction processing is performed on the first dimension feature to obtain a second dimension feature. A probability that the transaction data relates to a risky transaction is determined based on a decision classification of the second dimension feature, where the decision classification is based on a pre-trained deep forest network including a plurality of levels of decision tree forest sets.

Abstract: This disclosure relates to a search result processing method and apparatus, and a storage medium. The method may include acquiring a search result according to a search keyword and obtaining an accurate matching score of the search result relative to the search keyword. The method may further include determining a semantic matching weight vector of the search result, a semantic representation vector of the search keyword, and a semantic representation vector of the search result. The method may further include obtaining a semantic matching score of the search result relative to the search keyword according to the semantic representation vectors and the semantic matching weight vector. The method may further include obtaining a similarity between the search result and the search keyword according to the accurate matching score and the semantic matching score.

Abstract: This application provides a keyword extraction method. The method includes: receiving an information entity including a title and a text; performing word segmentation on the text, to obtain a plurality of candidate words; and performing character segmentation on the title corresponding to semantics of the text, to obtain a plurality of characters; sequentially inputting the plurality of candidate words to a keyword extraction model, to obtain an attention weight of each candidate word relative to each character; selecting, from the plurality of candidate words, a candidate word that appears in the title; determining an extraction threshold according to an attention weight of the selected candidate word relative to each character; and determining a keyword of the text of the information entity from the candidate words according to the extraction threshold. This application further provide a method for training a keyword extraction model, a computer device, and a storage medium.

Abstract: A feature extraction is performed on transaction data to obtain a user classification feature and a transaction classification feature. A first dimension feature is constructed based on the user classification feature and the transaction classification feature. A dimension reduction processing is performed on the first dimension feature to obtain a second dimension feature. A probability that the transaction data relates to a risky transaction is determined based on a decision classification of the second dimension feature, where the decision classification is based on a pre-trained deep forest network including a plurality of levels of decision tree forest sets.