Abstract: A server computing device, including memory storing a knowledge graph including a plurality of ontology entities connected by a plurality of edges. The server computing device may further include a processor configured to generate a glossary file based on the knowledge graph. The glossary file may include a plurality of ontology entities included in the knowledge graph. The processor may receive a plurality of utterance templates. Each utterance template may include an utterance and a predefined intention. For each utterance template, the processor may generate one or more utterance template copies in which one or more ontology entities included in the utterance are replaced with one or more utterance template fields. The processor may generate a plurality of training utterances at least in part by filling the one or more utterance template fields of the one or more utterance template copies with respective ontology entities included in the glossary file.

Abstract: A server computing device, including memory storing a knowledge graph including a plurality of ontology entities. The server computing device may further include a processor configured to receive a tokenized utterance including a plurality of words and one or more metadata tokens. The processor may extract a respective word embedding vector from each word included in the tokenized utterance. Based on a glossary file, the processor may determine a respective ontology entity type of each word included in the tokenized utterance. The processor may extract a character embedding vector from each character included in the tokenized utterance. Based on the plurality of word embedding vectors, the plurality of respective ontology entity types of the words, and the plurality of character embedding vectors, the processor may determine a predefined intention of the tokenized utterance using at least one recurrent neural network. The predefined intention may indicate a target ontology entity type.

Abstract: A computer-implemented method is disclosed that operates in conjunction with machine learning binary classification of an event. The method generates a rule relating to whether or not the event will occur. In one embodiment, the method includes obtaining foreground sequences corresponding to the event happening and background sequences corresponding to the event not happening. For each foreground sequence of a number of foreground sequences, the computer computes a plurality of difference values. The rule may be determined based on a largest difference value for one of the plurality of foreground sequences. A corresponding system is also disclosed.

Abstract: Methods, computing systems, and computer-readable media for predicting pore pressure. As an example, the method includes receiving data representing a subterranean domain, modeling the domain based on the data, ranking the data, testing and validating the model, calibrating the model, and predicting a pore pressure in the domain.

Abstract: A server computing device, including memory storing a knowledge graph including a plurality of ontology entities connected by a plurality of edges. The server computing device may further include a processor configured to generate a glossary file based on the knowledge graph. The glossary file may include a plurality of ontology entities included in the knowledge graph. The processor may receive a plurality of utterance templates. Each utterance template may include an utterance and a predefined intention. For each utterance template, the processor may generate one or more utterance template copies in which one or more ontology entities included in the utterance are replaced with one or more utterance template fields. The processor may generate a plurality of training utterances at least in part by filling the one or more utterance template fields of the one or more utterance template copies with respective ontology entities included in the glossary file.

Abstract: A server computing device, including memory storing a knowledge graph including a plurality of ontology entities. The server computing device may further include a processor configured to receive a tokenized utterance including a plurality of words and one or more metadata tokens. The processor may extract a respective word embedding vector from each word included in the tokenized utterance. Based on a glossary file, the processor may determine a respective ontology entity type of each word included in the tokenized utterance. The processor may extract a character embedding vector from each character included in the tokenized utterance. Based on the plurality of word embedding vectors, the plurality of respective ontology entity types of the words, and the plurality of character embedding vectors, the processor may determine a predefined intention of the tokenized utterance using at least one recurrent neural network. The predefined intention may indicate a target ontology entity type.

Abstract: A server computing device, including memory storing a knowledge graph. The server computing device may further include a processor configured to receive a natural language input and generate a tokenized utterance based on the natural language input. Based on the tokenized utterance, the processor may select a predefined intention indicating a target ontology entity type of the natural language input. The processor may identify at least one input ontology entity token included in the tokenized utterance and may identify at least one relation between the predefined intention and the input ontology entity token. Based on the predefined intention, the at least one input ontology entity token, and the relation, the processor may generate a structured query. Based on the structured query and the knowledge graph, the processor may output an output ontology entity token having the target ontology entity type.

Abstract: A method for planning and drilling a well includes receiving geomechanical and geological data for a subterranean domain, and receiving an initial well trajectory including a well path and survey points. The method includes conducting a wellbore stability analysis along the well trajectory based in part on the geomechanical and geological data. Conducting the wellbore stability analysis includes identifying a subset of the well path intervals along the well trajectory as having a risk for instability. The method includes calculating a geomechanics nudge for one or more survey points along the well trajectory. The geomechanics nudge is calculated as a derivative of the wellbore stability at the one or more survey points. The method includes modifying the one or more survey points and the one or more well path intervals connected thereto based in part on the geomechanics nudge to generate a modified well trajectory.

Abstract: The present disclosure provides a method for processing data on Internet of Vehicles, a server, and a terminal. In a technical solution of the present disclosure, the server first acquires the historical travel data, and then performs training on the historical travel data to obtain the program script used to analyze the driving behavior of the user, and finally sends the program script to the terminal. The driving behavior of the user is dynamically analyzed according to the program script and the travel data, which resolves a problem that algorithm accuracy decreases because an algorithm is not updated in time, ensures accuracy of analyzing the driving behavior of the user, and further decreases additional costs brought by updating terminal firmware.

Abstract: A method of consolidating a subterranean formation which comprises particles is provided. The method includes selecting a subterranean formation in need of consolidation, contacting the particles with a cationic polymer and then an anionic or non-ionic polymer, thereby agglomerating the particles and consolidating the formation, wherein the agglomeration increases the uniformity of the size of the particles. Methods of producing hydrocarbon wherein the formation is consolidated by the method herein described are also provided. Use of kits comprising cationic polymer and anionic polymer and/or non-ionic polymer to consolidate subterranean formations is further provided. Kits comprising the polymers used in the method are also provided.

Abstract: The present invention provides a facial recognition method, including: obtaining a target facial image; determining a covered region and a non-covered region of the target facial image; calculating the weight of the covered region, and calculating the weight of the non-covered region; extracting feature vectors of the covered region, and extracting feature vectors of the non-covered region; comparing the target facial image with each template facial image in a facial database according to the feature vectors of the covered region, the feature vectors of the non-covered region, the weight of the covered region, and the weight of the non-covered region, to calculate a facial similarity between each template facial image and the target facial image; and determining, when at least one of the facial similarities between the template facial images and the target facial image is greater than or equal to a similarity threshold, that facial recognition succeeds.

Abstract: The present invention provides a facial recognition method, including: obtaining a target facial image; determining a covered region and a non-covered region of the target facial image; calculating the weight of the covered region, and calculating the weight of the non-covered region; extracting feature vectors of the covered region, and extracting feature vectors of the non-covered region; comparing the target facial image with each template facial image in a facial database according to the feature vectors of the covered region, the feature vectors of the non-covered region, the weight of the covered region, and the weight of the non-covered region, to calculate a facial similarity between each template facial image and the target facial image; and determining, when at least one of the facial similarities between the template facial images and the target facial image is greater than or equal to a similarity threshold, that facial recognition succeeds.

Abstract: Disclosed is a railway hopper car comprising a car body (6), a top cover (1, 2), a bogie (24), a braking device (21), a coupler buffer device (22), and a bottom door (25, 28) and a bottom door opening and closing mechanism (23) mounted at a discharge port at the bottom of a chassis. The railway hopper car further comprises a longitudinal saddle (31) disposed in the center of the car body (6) in the length direction thereof and arranged along the longitudinal direction of the car body (6). By providing the longitudinal saddle (31), the sequential requirement to close the left bottom door (25) and the right bottom door (28) is eliminated, thereby simplifying the structure of the linkage bottom door opening and closing mechanism and reducing manufacture and maintenance costs thereof.

Abstract: The present disclosure provides a human-machine interactive method based on artificial intelligence and a human-machine interactive device based on artificial intelligence. The method includes: receiving a query from a user; processing the query based on a pre-generated model, and obtaining an answer with a human conversation style corresponding to the query, wherein the model is generated based on a human conversation corpus; and feeding back the answer to the user.

Abstract: A method for angle-domain common image gather (ADCIG) of a subsurface formation includes the step of converting seismic incident waves and seismic scattered waves at each of a number of image locations from time domain to frequency domain using Fourier transform. At each image location, the seismic waves in the frequency domain are decomposed into a number of local plane waves. Applying a cross-correlating imaging condition amongst the local plane waves to obtain a partial image at each image location. The plurality of partial images are then sorted into the angle domain.

Abstract: A method can include receiving data that characterizes anisotropy of a formation; receiving a model that models one or more planes of weakness in an anisotropic formation; and, based at least in part on the model and the data, outputting information germane to stability of a bore in an anisotropic formation.

Abstract: A computer-implemented method is disclosed that operates in conjunction with machine learning binary classification of an event. The method generates a rule relating to whether or not the event will occur. In one embodiment, the method includes obtaining foreground sequences corresponding to the event happening and background sequences corresponding to the event not happening. For each foreground sequence of a number of foreground sequences, the computer computes a plurality of difference values. The rule may be determined based on a largest difference value for one of the plurality of foreground sequences. A corresponding system is also disclosed.

Abstract: The present disclosure provides a method for processing data on Internet of Vehicles, a server, and a terminal. In a technical solution of the present disclosure, the server first acquires the historical travel data, and then performs training on the historical travel data to obtain the program script used to analyze the driving behavior of the user, and finally sends the program script to the terminal. The driving behavior of the user is dynamically analyzed according to the program script and the travel data, which resolves a problem that algorithm accuracy decreases because an algorithm is not updated in time, ensures accuracy of analyzing the driving behavior of the user, and further decreases additional costs brought by updating terminal firmware.

Abstract: A method can include receiving data that characterizes anisotropy of a formation; receiving a model that models one or more planes of weakness in an anisotropic formation; and, based at least in part on the model and the data, outputting information germane to stability of a bore in an anisotropic formation.

Abstract: Equalization techniques are provided for high-speed data communications and, more specifically, DFE (decision feedback equalizer) circuits and methods are provided which implement a high-order continuous time filter in a DFE feedback path to emulate structured elements of a channel response.