31 results about "Outcome variable" patented technology

Systems and methods are disclosed for routing callers to agents in a contact center, along with an intelligent routing system. An exemplary interface for use with a contact center includes a graphical user element for adjusting a time limit for a caller to be held before routed to an agent according to a pattern matching algorithm where the caller is compared to a set of agents via the pattern matching algorithm and routed to the best matching agent of the set of agents if available prior to the time limit and routed to the best matching agent of available agents if the time limit is exceeded. The interface may further display an estimated effect of the time limit on at least one outcome variable, which may include revenue generation, cost, customer satisfaction, first call resolution, cancellation, or other variable outputs from the pattern matching algorithm(s) of the system.

A method and system for making financial or medical decisions. The method comprises training sets of models using classification training with sets of data derived from segregated data sources. Overall weighting of each model within the sets of models are determined for each of the sub-datasets. The sets of models, the overall weighting of each model and a number of examples provided from the data for each of the datasets are transmitted to a central server over a communication network, wherein the central server is configured to determine the relative weights of each of the sets of models in the overall ensemble model based on the number of examples, combine the sets of models, receive new application data, and predict at least one of outcome variables, an uncertainty factor for the variables, and drivers of the outcome variables based on the new application data.

The invention discloses a resource description framework querying method and system based on a relational database, wherein the method includes the following steps: establishing a result variable table according to the SPARQL query statement input by a user, separating the SPARQL query statement to obtain each basic graphic pattern, and establishing the constant table, the variable table and the blank note table corresponding to the basic graphic patterns and a pattern string identifying the logical relation between the basic graphic patterns; generating a pattern tree based on the pattern string; generating the SQL subquery fragment for each basic graphic pattern according to the corresponding element structural table of each basic graphic pattern, and representing the relationship between the basic graphic patterns based on the pattern tree to connect the SQL subquery fragments into a whole SQL query statement section; utilizing the SQL query statement section obtained through conversion to query the RDF data in the relational database; and semantics wrapping the query result according to the limitation of the SPARQL result set and the user setting and returning the query result to the user.

Systems methods and recordable media for predicting multi-variable outcomes based on multi-variable inputs. Additionally, the models described can be used to predict the multi-variable inputs themselves, based on the multi-variable inputs, providing a smoothing function, acting as a noise filter. Both multi-variable inputs and multi-variable outputs may be simultaneously predicted, based upon the multi-variable inputs. The models find a critical subset of data points, or “tent poles” to optimally model all outcome variables simultaneously to leverage communalities among outcomes.

The invention discloses a volume radio direction finde (RDF) data distribution type query processing method based on a Hadoop platform and belongs to the field of the computers. The method mainly comprises the following steps. Step a, RDF data can be uploaded to a hadoop distributed file system (HDFS), data can be read by a MapReduce frame of the Hadoop platform and stored in a distributed database HBase. Step b, a simple protocol and RDF query language (SPARQL) inquiry statement section which is provided by a user can be preprocessed. Statements can be analyzed and extracted a prefix statement, an outcome variable and a picture-model sub sentence. Step c, prefix characters of the picture-model sub sentence can be restored, and the restored picture-model sub sentence can be converted into a tree model. Step d, the tree model can be resolved. Tree joints can be traversed in a bottom-up method and a left-to-right method and inquiry plans can be generated, wherein the inquiry plans are matched with each joints. The final inquiry plans can be sent to the Hadoop platform. Step e, data can be read form the HBase through the MapReduce frame. Distributed query can be implemented according to the inquiry plans. Eventually, the outcome variable can be returned to an inquiry result.

The described embodiments include a processor that executes a vector instruction. The processor starts by receiving a vector instruction that uses a first input vector, a second input vector, and a control vector, and optionally a predicate vector as inputs, wherein each of the vectors includes N elements. The processor then executes the vector instruction. In the described embodiments, when executing the vector instruction, the processor determines a key element position. If the predicate vector is received, the key element position is a predetermined active element position in the predicate vector, otherwise, the key element position is in a predetermined element position. The processor then uses the key element position to copy a result value into a result variable. When copying the result value into the result variable, if an element in the key element position of the control vector contains a predetermined value, the processor copies a value from the key element position in the second input vector into the result variable. Otherwise, the processor copies a value from the key element position in the first input vector into the result variable.

A process for determining responders in clinical testing environments that involves, inter alia, detecting treatment response through the use of small numbers of measurements of randomly varying outcome variables in individual clinical trial subjects, and by analyzing the measurements in such a way as to eliminate troublesome variables, such as a spontaneous population variability.

A method for predicting a patient's outcome variable, such as a probability of mortality / recovery, includes accessing at least one of a plurality past patients' data fields including physiological and / or laboratory data, and a time of stay indicating how long each patient had been under care at the time. An outcome variable estimation algorithm is generated by data mining from a plurality of past patients' physiological and / or laboratory data, corresponding time of stay, and associated outcome variables. A current patient's outcome variable is determined from the current patient's physiological and / or laboratory data, the current time of stay, and the outcome variable estimation algorithm.

Systems methods and recordable media for predicting multi-variable outcomes based on multi-variable inputs. Additionally, the models described can be used to predict the multi-variable inputs themselves, based on the multi-variable inputs, providing a smoothing function, acting as a noise filter. Both multi-variable inputs and multi-variable outputs may be simultaneously predicted, based upon the multi-variable inputs. The models find a critical subset of data points, or “tent poles” to optimally model all outcome variables simultaneously to leverage communalities among outcomes.

To achieve high-speed and efficient parameter calculation processing of a logistic regression model. A logistic regression parameter is calculated, the logistic regression parameter being a parameter of the logistic regression model indicating the relationship between an explanatory variable and an outcome variable being secure data corresponding to each sample. A data processing unit calculates the inner product (t_s) of the explanatory variable and the outcome variable with application of secure computation being computation processing applied with converted data of each of the variables, and performs computation processing excluding the calculation processing of the inner product, as computation processing without the converted data, to calculate the logistic regression parameter in accordance with the maximum likelihood method with the Newton-Raphson method (iterative convergence method).

The invention provides a system for automatically marking a source code. The system comprises a code reading unit for reading the source code of any source file into a character string variable and decomposing the character string variable into a string array, a level determining unit for prereading retraction format characters of multiple rows of statements and determining statement levels, a type judging unit for determining whether each statement is a branch / loop statement or not according to an initial keyword, a statement processing unit for adding a unique identification and a comment statement in each branch of a statement body part of each branch / loop statement, and a variable storing unit for storing outcome variables into the source file after all the statements in the string array are processed. The invention further provides a corresponding method for automatically marking the source code. By adopting the technical scheme, branch / loop statements in the source code can be automatically identified, and the unique identifications and rem statements are automatically added, so that manual intervention is reduced, and the processing complexity is lowered.

Different memory testing programs, systems, and methods for conducting memory tests, and for storing and displaying test data and trends residing on a client's machine are disclosed. The tests generally are based on generating a random sequence of signals, displaying the sequence to an examinee, the examinee memorizing the sequence, and inputting the sequence into the testing program. The signals could have visual, auditory, and / or positional components. The signals could also be alphanumeric strings.The testing program measures test outcome variables, computes a composite memory score based on the test outcome variables, records and displays the stored test data. The testing device may also include a communication interface for periodically transferring the stored test data to a database residing on a remote server displaying the test data of the examinee on a website through an internet connection.

The invention provides a policy evaluation method for a bus transit lane based on breakpoint regression, and belongs to the technical field of bus transit lane policy evaluation. The method comprisesthe steps: carrying out the breakpoint regression of the speeds of two types of motor vehicles through the actual measurement data, analyzing the abrupt changes of the outcome variables before and after the breakpoint through combining an image, quantitatively evaluating the impact on the speed of the buses and social vehicles from the bus transit lane, assisting an urban traffic administration department to formulate and optimize the bus transit lane policy. The method is low in cost, and the obtained conclusion is direct and effective. The method has a certain promotional value.

The invention discloses a hierarchical important feature selection method based on clinical high-dimensional breast cancer data. The feature selection method comprises steps of statistical feature selection and integrated feature selection. At the statistical feature selection step, a single factor analysis method is employed; and features having obvious impacts on outcome variables are selected preliminarily by different statistics and checking. At the integrated feature selection step, a gradient lifting tree is established; after model training, a feature importance score is obtained; witha designed and verified importance score threshold, selection of features having obvious impacts on outcome variables is realized. Therefore, problems of too high data feature dimension, excessive redundant features and data disorder during the clinical breast cancer prediction modeling process are solved effectively; the redundant or meaningless features in high-dimensional clinical breast cancerdata can be excluded; and thus a few of features having the important impact on the breast cancer modeling are selected and the high accuracy and practicability of the breast cancer model are ensured.

Described herein are techniques and mechanisms for medical practice data analytics. According to various embodiments, a system may include a clinic information database, a clinic data cluster engine, and a clinic data analytics engine. The clinic information database may store clinic data characterizing each of a plurality of medical practice clinics. The clinic data cluster engine may determine a respective plurality of clinic clusters based on the clinic information for each of a plurality of clustering mechanisms. The clinic data analytics engine may evaluate the performance of each of the plurality of clustering mechanisms to produce a respective performance evaluation by determining a respective predicted outcome variable for each of the respective clustering mechanisms and each of the respective clinic clusters and comparing each of the respective predicted outcome variable with a respective observed outcome variable.

The invention discloses a learning effect optimization method based on a user behavior causal relationship in MOOC log data. The method comprises the steps of based on log data of MOOC platform users,by means of user tendency calculation and matching, selecting and generating causal independent variables in a causal network according to a causal reasoning framework of a reverse fact, and obtaining the minimum data scale under different data scales according to the average Markov blanket length of the causal network when the length tends to be stable; obtaining a causal network group; screening edges among the network nodes by using an expert accuracy algorithm; grouping the screened network groups; comprehensively generating a final causal network by using a Bagging voting mechanism; obtaining the causal relationship between the user behavior and the learning effect; based on the causal relationship, reasonably planning the learning path of the user according to the reason variable node and the result variable node, the probability that whether the user completes the course is influenced by changing the operation behavior of the user or the learning time of the user, and the accuracy of relationship judgment between the variables is improved.

The invention discloses a knowledge tracking method, system and device based on causal reasoning and a storage medium, and the method comprises the steps: obtaining a random variable and a potential result, and determining a relational expression between the random variable and the potential result; obtaining observation variables, and dividing the observation variables into hybrid variables, adjustment variables and irrelevant variables; analyzing by adopting a causal reasoning method, and determining conversion output of the potential result according to a mixed variable, an adjustment variable and a relational expression between a random variable and the potential result; determining a first objective function according to the conversion output; obtaining a sample weight and determining a second objective function; based on the second objective function and the sample weights, determining a balance weight that can reduce covariance between the elements to assist in evaluating the causal relationship between the single variable and the resulting variable.

The invention discloses a patient hospitalization duration prediction method and device, electronic equipment and a storage medium. The method comprises the steps of constructing an ordered multi-classification prediction model by utilizing cascade connection of multiple binary base learners; training each base learner by using the training data set until each base learner meets the performance index requirement, and obtaining a trained prediction model; and selecting a to-be-predicted sample according to preset prediction features and inputting the to-be-predicted sample into the trained prediction model to obtain a prediction result. According to the method, a plurality of binary classification base learners are cascaded and connected in series to construct an ordered multi-classification prediction model, a sequence progressive relationship among classes in an ordered multi-classification outcome variable is reserved, the ordered classes are not assumed to be equal-ratio relationships, the method is more consistent with real data characteristics, and by splitting a data set layer by layer, two types of data in the data set used for training of each layer of base learners are relatively balanced, the problem of data imbalance among multiple types is effectively solved, and the accuracy of a prediction result is improved.

A method and device predict an outcome variable of an observed phenomenon based on values of a panel of three or more observed constituents and, to do so, employ a series of processes, implemented by a machine, for developing a K-component linear model wherein, among other things, the first component is by itself significantly predictive of the outcome variable, and a second component is correlated with the first component, and loadings for each constituent within any given one of the components subsequent to the first component are determined in a sequentially independent manner.

A system and method of simulating and optimizing industrial and other processes includes a computer that performs multivariate analysis of input variables and output variables to generate a data modelof the operation of the process. For industrial applications, the input variables include process variables and the output variables include result variables from the operation of the industrial process. The data model determines contributions to changes in the output or result variables by the respective input or process variables and is provided to a predictive algorithm to identify parameter values for input or process variables expected to have a most significant impact on the output or result variables during performance of the process. The outputs of the predictive algorithm are parameter values that are provided as input or process variables to the industrial process for simulation or performance optimization or product recommendations / optimizations.

A process for determining responders in clinical testing environments that involves, inter alia, detecting treatment response through the use of small numbers of measurements of randomly varying outcome variables in individual clinical trial subjects, and by analyzing the measurements in such a way as to eliminate troublesome variables, such as a spontaneous population variability.

The invention discloses a method, a device and a system for estimating the causal effect of a target variable on a result variable. According to the method disclosed by the invention, a related variable set of target variables is determined for a given target variable by utilizing observation data, and the related variable set comprises variables related to the target variable. However, a local causal network comprising the target variable and a variable associated with the target variable is learned with observational data relating to the target variable and the variable associated with the target variable, resulting in a learned local causal network of the target variable. Then, at least one of a direct causal effect and a total causal effect of the target variable to the result variableis determined according to a relationship between the target variable indicated in the learned local causal network of the target variable and the result variable. By utilizing the method and the device, the time required for evaluating the causal effect can be greatly shortened, the efficiency of evaluating the causal effect is remarkably improved, and quantitative evaluation is given for the causal effect.

The invention provides a system for automatically marking a source code. The system comprises a code reading unit for reading the source code of any source file into a character string variable and decomposing the character string variable into a string array, a level determining unit for prereading retraction format characters of multiple rows of statements and determining statement levels, a type judging unit for determining whether each statement is a branch / loop statement or not according to an initial keyword, a statement processing unit for adding a unique identification and a comment statement in each branch of a statement body part of each branch / loop statement, and a variable storing unit for storing outcome variables into the source file after all the statements in the string array are processed. The invention further provides a corresponding method for automatically marking the source code. By adopting the technical scheme, branch / loop statements in the source code can be automatically identified, and the unique identifications and rem statements are automatically added, so that manual intervention is reduced, and the processing complexity is lowered.

A method for predicting an outcome variable of a patient, such as the probability of death / recovery, comprising accessing at least one of a plurality of past patient data fields, said data fields including physiological and / or laboratory data, and length of hospital stay, length of hospital stay Indicate how long each patient has been under surveillance at that time. An outcome variable estimation algorithm is generated by data mining based on a plurality of past patient physiological and / or laboratory data, corresponding hospital stays, and associated outcome variables. The outcome variable for the current patient is determined based on the current patient's physiological and / or laboratory data, the current length of hospital stay, and the outcome variable estimation algorithm.

The invention discloses a knowledge tracking method, system, equipment and storage medium based on causal reasoning, wherein the method includes: obtaining random variables and potential results, and determining the relationship between the random variables and potential results; Divided into confounding variables, adjustment variables and irrelevant variables; use the method of causal reasoning to analyze, and determine the conversion output of potential results according to the relationship between confounding variables, adjustment variables, random variables and potential results; according to the conversion output, determine the first target function; obtain the sample weight and determine the second objective function; determine the balance weight according to the second objective function and the sample weight, the balance weight can reduce the covariance between elements to help evaluate the causal relationship between a single variable and the outcome variable.

Performing parallel comparisons of variables to determine program code execution flow or to compare multiple variables is disclosed. Memory locations are packed with multiple sub-variables for comparison to sub-variables generated, for example, at runtime. Each binary sub-variable includes a “carryout” bit used to determine whether a comparison of one sub-variable with another sub-variable results in a “true” or a “false.” A modified version of twos complement arithmetic is performed on a set of sub-variables and may be completed at runtime or earlier. The modified version involves inverting each bit of the sub-variables, performing a masking operation to change the carryout bits to 0, adding a binary 1 to each sub-variable, and performing the masking operation a second time to change the carryout bits to 0. The result of this calculation may be stored in a separate memory location for future comparisons. At the time of comparing sub-variables, the result of the modified twos complement arithmetic is added to a variable, and the carryout bit of each sub-variable of the resulting variable is evaluated to determine results of the comparisons.

The invention discloses a reasoning rule configuration method, which includes the following steps: S1, determining the final reply target of the interaction scene, listing possible information of the final reply answer; S2, analyzing the variables that affect each possible information, listing the relevant information of the variables, Determine the relationship between variables; S3, according to the relevant information of variables obtained in S2 and the relationship between variables, judge whether to quote existing variables, if necessary, quote and enter S4; S4, according to the reply target, variable and the relationship between variables The relationship between defines the corresponding information variables; S5, judges whether the value of the result variable needs to be quoted in the final reply answer, if necessary, sets the result variable and then enters S6; S6, edits each answer of the interaction, and the final reply answer is composed of constants and reasoning Composition of operation results. The inference rule configuration method provides an inference rule configuration method that can improve the efficiency of configuring scenario inference rules and improve interactive experience.

The invention relates to a method for determining the electromagnetic compatibility (EMC) of a technical system. The method comprises specifying at least one influencing variable of the technical system, wherein the influencing variable has a potential influence on the EMC of the technical system; determining at least one EMC outcome variable of the technical system on the basis of a variation of the influencing variable. The invention further relates to an arrangement (200) for determining the electromagnetic compatibility (EMC) of the technical system, and the arrangement (200) comprises an input device (210) by means of which a user can specify at least one influencing variable of the technical system, wherein the influencing variable has a potential influence on the EMC of the technical system; a computing device (220) which is designed to determine at least one EMC outcome variable of the technical system on the basis of a variation of the influencing variable.