52 results about "Causal inference" patented technology

Method and system for analyzing relationship between molecular structure and biological activity in one or more molecules by transforming molecular structure data into a hierarchical representation of chemical concepts and descriptors and detecting common tree-like patterns in the data.

The invention is a soft measuring method for mineral grinding system flooding particle index, which is made up of hardware platform and measuring software, the method includes the selection of assistant variables, case representation, acquisition of initial case in case bank, case reasoning, case storing and maintaining steps. The method uses normal computer control system and normal detector to provide online process data, through a little artificial sampling, creates the soft measuring model of mineral grinding flooding particle based on case reasoning. Compared with normal particle meter, the method reduces the cost.

The invention provides a micro-service fault root cause positioning method and device based on causal inference, and solves the problems that a current micro-service fault root cause positioning method cannot give consideration to positioning accuracy and positioning efficiency, and the network operation cost is large. The method comprises three stages of fault network element positioning, causal inference model construction and fault root cause positioning, and can strictly distinguish the causal relationship between component nodes, thereby being capable of eliminating redundant nodes, overcoming the defect that traditional manual or simple machine operation and maintenance are time-consuming and labor-consuming, and meanwhile, the fault root cause can be quickly and accurately positioned through the causal traceability characteristic, and the method has certain research value and significance for development of intelligent operation and maintenance.

The invention discloses a mechanism data dual-drive combined performance degradation positioning method. The problem of root cause positioning of communication drive test performance degradation in different scenes is solved. The method comprises two modules, the causal relationship learning module designs a causal relationship learning model, considers the isomerism of node relationships, and clarifies the equation representation of the node relationships in a causal relationship graph; the causal inference module carries out causal inference based on the intervention index and the distribution index, and carries out inference of a final fault root cause based on the intervention deviation and the distribution abnormity condition. According to the method, an efficient algorithm with interpretability is adopted, the root cause positioning accuracy of a traditional method is greatly improved under a current network test environment data set test, meanwhile, the recall rate is high, and generalizability is achieved. In addition, practical application of enterprise maintenance engineers is facilitated, scheme analysis and conclusions can be issued to an operation and maintenance base layer, the operation and maintenance efficiency is improved, and the operation and maintenance cost is reduced.

A system and method for predicting driving actions based on intent-aware driving models that include receiving at least one image of a driving scene of an ego vehicle. The system and method also include analyzing the at least one image to detect and track dynamic objects located within the driving scene and to detect and identify driving scene characteristics associated with the driving scene and processing an ego-thing graph associated with the dynamic objects and an ego-stuff graph associated with the driving scene characteristics. The system and method further include predicting a driver stimulus action based on a fusion of representations of the ego-thing graph and the ego-stuff graph and a driver intention action based on an intention representation associated with driving intentions of a driver of the ego vehicle.

The invention belongs to the technical field of data mining, in particular to a recursive causal inference method based on causal segmentation. The method of the invention adopts the divide-and-conquer strategy, recursively utilizes the low-order conditional independence test to divide the data set into layers of causality, then reconstructs the causality of each sub-data set, and finally merges to obtain the whole causality information of the data set. This method can be used in high-dimensional data set for causal inference and causal relationship mining. Under the background of big data era, causality inference algorithm has been widely used in the fields of economics, Internet social network, medical big data and so on, but high-dimensional data problem is a common problem in the industry information intelligence, so it is urgent to solve the related problems in this field. The present invention is helpful to solve the problem of how to deal with the ever-increasing mass data causal information mining, and plays an important role in extracting the precious causal information in the mass data.

The invention discloses a feature evaluation method and device influencing user retention. The method comprises the steps: collecting a corresponding specified feature value of each account in a current platform according to a plurality of specified feature variables; acquiring retention information of each account, wherein the retention information is used for reflecting whether the current account is a retention account or not; determining an intervention variable according to the acquired specified characteristic value; and determining a causal effect of the intervention variable on user retention by combining the retention information and adopting a causal inference algorithm. According to the embodiment of the invention, the influence of each characteristic variable on user retention is judged through a causal inference method, so that key factors influencing the user retention can be quickly analyzed, and after the key factors are obtained, a platform party can perform targeted improvement on the factors through some customized strategies, so that the retention rate of the user is improved.

Computer implemented methods, systems, and computer readable medium are provided for performing causal inference analyses to determine the more effective treatment among alternative treatments in the healthcare setting using real world observational data. Both binary treatment and adaptive treatment strategies are considered in the analysis. The methods comprise generating a Bayesian marginal structural model and performing a single step of Bayesian regression that incorporates matching, weighting, and estimation processes and in which the matching process is performed using a Guassian process (“GP”) prior covariance function.

The invention discloses a multi-modal data-oriented vehicle insurance fraud behavior prediction system, method and device, and the method comprises the steps: extracting risk factors from picture data, combining the risk factors with corresponding structured data fields, constructing a vehicle insurance fraud risk prediction model based on the algorithms of feature engineering, machine learning, deep learning and the like, and predicting the fraud behavior of the vehicle insurance. And carrying out early warning on a risk behavior. After prediction, risk assessment and importance ranking are carried out on the picture factors, and visual expression is carried out on the factors with high risks and high weights. According to the method, manual risk assessment can be effectively assisted, and visual causal relationship expression of the model and the prediction result is realized by using data of different types of pictures. According to the method, a computer vision algorithm is utilized to perform factor extraction on some picture data difficult to use, and a prediction model and a result are visually displayed by means of factors analysis, causal inference and other algorithms.

The invention provides a high-generalization face replacement method and device based on causal inference and electronic equipment. The method comprises the following steps: determining a source face image and a target face image; inputting the source face image and the target face image into a face replacement model to obtain a face replacement image output by the face replacement model, wherein the face replacement model determines identity information representation of the source face image based on a causal effect of an expression attitude parameter of the target face image on the identity information, and performs face replacement based on the identity information representation and the perception information representation of the target face image; the face replacement model is obtained by training based on a sample source face image and a sample target face image. According to the method, the device, the electronic equipment and a storage medium provided by the invention, a high-quality and vivid face replacement image is obtained, so that the stability and generalization ability of a face replacement technology in different target scenes are improved.

The invention discloses an agent behavior interpretation method based on causal relationship inference, and belongs to the technical field of auxiliary decision making and causal inference. The method comprises the following steps of: performing training data acquisition on an intelligent agent trained by adopting reinforcement learning, wherein the data comprises an environment state, an adopted action and reward information in an intelligent agent training process; performing offline training on the data through causal relationship discovery and data regression fitting methods, and outputting a reasonable behavior causal relationship model; and performing online interpretation on the behaviors of the intelligent agent by using the behavior causal relationship model. According to the method, a good behavior interpretation effect can be achieved.

The invention discloses a wooden dwelling customization method based on case inference. The method includes the following steps of (1) carrying out collection, sorting, classification, statistics andanalysis on data information of wooden dwellings, and constructing a case library of the wooden dwellings, wherein the case library comprises a dwelling house-type library, a functional structure library, a culture resource library and a data resource library; (2) on the basis of an original dwelling case library, mapping the morphoses of the wooden dwellings according to rules into diversified structure trees of the wooden dwellings, wherein each tree-shaped node represents different structural elements of the wooden dwellings according to different hierarchies and forms a product allocationdesign representation model of the structure trees; (3) executing the allocation design flow of the wooden dwellings. The wooden dwelling customization method based on the case inference has the advantages that not only can the digitalized representation of user demands be achieved, but also the extraction result is accurate. By adopting the wooden dwelling customization method, not only can personalized customization design of traditional wooden dwellings be achieved, but also digitalized protection and inheritance of traditional intangible cultural heritages are achieved.

According to the social noise text entity relationship extraction optimization method and system, problems that in the social text field, the data labeling cost is high, the data updating speed is high, a data set has deviation, and an original model may fall into false correlation can be solved. According to the method, causal inference is introduced into the process of generating word vectors through natural language processing, advantages of intervention and anti-facts in causal inference are applied, data enhancement is achieved, and deviation caused by a data set is weakened. According to the method, the input cost of manual data labeling can be reduced, non-normalization and innovativeness of the text in an actual scene can be effectively simulated, and robustness of the model for social noise text entity relation extraction is improved; due to the fact that the method processes the word vectors, the method has good adaptability and application possibility for various existing models.

The invention discloses a tool variable generation and counter-fact reasoning method and device based on a neural network. Aiming at the problem that a previous tool variable-based counter factual reasoning (such as handwritten numeric recognition) method needs to define and acquire tool variables in advance, the tool variables are directly learned and decoupled from observable variables, so that the causal inference efficiency is greatly improved, and the time and the cost are saved. According to the method, the tool variables are automatically extracted from the observable variables for the first time, and the method has originality and uniqueness in algorithm and application. The method is applied to an existing tool variable-based counter-fact prediction method, and compared with a method using a real tool variable, the performance causal inference is obviously improved. The method focuses on decoupling the representation of the tool variables from the observable variables, solves the problem that the tool variable-based counter-fact prediction technology needs to use prior knowledge and high cost to obtain tool variable data in advance, and improves the precision in the fields of handwritten numeral recognition and the like.

The invention relates to a non-cooperative topology inference method based on unknown node positions. The non-cooperative topology inference method comprises the following steps: monitoring the power of a non-cooperative network in a given area L by using sensor nodes randomly distributed in the given area L; dividing the given area L into equal grids, and obtaining the power of each grid according to the power detected by the sensor nodes; inputting the power of each grid into a neural network to obtain a coordinate position of a non-cooperative node; monitoring a time sequence of the non-cooperative nodes by using a sensor network; constructing an autoregression model of the non-cooperative nodes and formed node pairs according to the time sequence of the non-cooperative nodes; using the residual sum of squares of the autoregression model to construct statistics; and obtaining the causal relationship of the non-cooperative node sum. According to the non-cooperative topology inference method based on the unknown node position, node positioning and causal inference are combined into one system to realize topology inference when the node position is unknown.

The invention discloses a causal inference method and system for cascaded medical observation data, and the method comprises the steps: building an improved cascaded nonlinear additive noise model with reasons in a causal relationship, an intermediate variable corresponding to each depth in a cascaded structure, and a result in the causal relationship as parameters, medical observation data with a cascade structure can be better matched, the accuracy of identifying the causal direction of the cascade medical data is improved, meanwhile, a variational lower bound corresponding to a maximized edge log-likelihood function is solved through a preset adversarial training model, KL divergence is bypassed by utilizing an adversarial strategy instead of an approximation formula, additive noise can be allowed to have wider distribution, so that the inference capability of the model is improved, and compared with the prior art, the causal direction of the medical observation data with the cascade structure can be well identified, and the causal direction identification accuracy is remarkably improved.