Abstract: Systems and methods for determining neural network brittleness are disclosed. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a modeling request comprising a preliminary model and a dataset. The operations may include determining a preliminary brittleness score of the preliminary model. The operations may include identifying a reference model and determining a reference brittleness score of the reference model. The operations may include comparing the preliminary brittleness score to the reference brittleness score and generating a preferred model based on the comparison. The operations may include providing the preferred model.

Abstract: Traditional systems and methods have implemented hand-crafted feature extraction from varying length time series that results in complexity and requires domain knowledge. Building classification models requires large labeled data and is computationally expensive. Embodiments of the present disclosure implement learning models for classification tasks in multi-dimensional time series by performing feature extraction from entity's parameters via unsupervised encoder and build a non-temporal linear classifier model. A fixed-dimensional feature vector is outputted using a pre-trained unsupervised encoder, which acts as off-the shelf feature extractor. Extracted features are concatenated to learn a non-temporal linear classification model and weight is assigned to each extracted feature during learning which helps to determine relevant parameters for each class. Mapping from parameters to target class is considered while constraining the linear model to use only subset of large number of features.

Abstract: A neural network may be trained on a training corpus that comprises a large number of dataset-visualization pairs. Each pair in the training corpus may consist of a dataset and a visualization of the dataset. The visualization may be a chart, plot or diagram. In each dataset-visualization pair in the training corpus, the visualization may be created by a human making design choices. The neural network may be trained to predict, for a given dataset, a visualization that a human would create to represent the given dataset. During training, features and design choices may be extracted from the dataset and visualization, respectively, in each dataset-visualization pair in the training corpus. After the neural network is trained, features may be extracted from a new dataset, and the trained neural network may predict design choices that a human would make to create a visualization that represents the new dataset.

Abstract: Systems, methods, and computer-readable media for context-aware synthesis for video frame interpolation are provided. A convolutional neural network (ConvNet) may, given two input video or image frames, interpolate a frame temporarily in the middle of the two input frames by combining motion estimation and pixel synthesis into a single step and formulating pixel interpolation as a local convolution over patches in the input images. The ConvNet may estimate a convolution kernel based on a first receptive field patch of a first input image frame and a second receptive field patch of a second input image frame. The ConvNet may then convolve the convolutional kernel over a first pixel patch of the first input image frame and a second pixel patch of the second input image frame to obtain color data of an output pixel of the interpolation frame. Other embodiments may be described and/or claimed.

Abstract: The disclosure herein describes a method and a system for generating hybrid learning techniques. The hybrid learning technique refers to learning techniques that are a combination a plurality of techniques that include of deep learning, machine learning and signal processing to enable a rich feature space representation and classifier construction. The generation of the hybrid learning techniques also considers influence/impact of domain constraints that include business requirements and computational constraints, while generating hybrid learning techniques. Further from the plurality hybrid learning techniques a single hybrid learning technique is chosen based on performance matrix based on optimization techniques.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.

Abstract: Today, artificial neural networks are trained on large sets of manually tagged images. Generally, for better training, the training data should be as large as possible. Unfortunately, manually tagging images is time consuming and susceptible to error, making it difficult to produce the large sets of tagged data used to train artificial neural networks. To address this problem, the inventors have developed a smart tagging utility that uses a feature extraction unit and a fast-learning classifier to learn tags and tag images automatically, reducing the time to tag large sets of data. The feature extraction unit and fast-learning classifiers can be implemented as artificial neural networks that associate a label with features extracted from an image and tag similar features from the image or other images with the same label. Moreover, the smart tagging system can learn from user adjustment to its proposed tagging. This reduces tagging time and errors.

Abstract: Method for detecting switch degradation and failures having steps of collecting and labelling, into predefined categories, switch machine data relative to a predetermined controlled switch placed in supervised environment and conditions; storing the labeled data of each movement switch in a database and pre-processing the labelled data. A learning LSTM weights and cell parameters by performing a training phase on a LSTM network using the pre-processed data, thus obtaining a final LSTM model inclusive of architecture and parameters of the LSTM network suitable for analyzing switch data relative to movements of switches actually located on a railway track; collecting data relative to the movements of a switch located on a railway track; and classifying the switch movements into said categories by applying the collected data to the final LSTM, thus detecting switch degradations and failures.

Abstract: According to an embodiment, a learning method of optimizing a neural network, includes updating and specifying. In the updating, each of a plurality of weight coefficients included in the neural network is updated so that an objective function obtained by adding a basic loss function and an L2 regularization term multiplied by a regularization strength is minimized. In the specifying, an inactive node and an inactive channel are specified among a plurality of nodes and a plurality of channels included in the neural network.

Abstract: A method for classifying a gesture made in proximity to a touch interface. A system receives data related to the position and/or movement of hand. The data is delimited by identifying a variable length window of touch frames. The variable length window of touch frames is selected to include touch frames indicative of feature data. The variable length window of touch frames is classified based upon classifications learned by the classifying module to identify gestures.

Abstract: Today, product developers with customized small batch production needs come across the problem of finding capable and flexible manufacturers, while manufacturers face underutilization due to inconsistent demand. In this disclosure, a digital manufacturing framework is presented to address the challenge of matching the underutilized manufacturers with the new product developers. This disclosure presents a Production as a Service (PaaS) framework to connect users (consumers or product developers) who have customized small batch manufacturing needs, with manufacturers that have existing underutilized resources. PaaS is a cloud-based, centralized framework based on a service oriented architecture (SOA) that abstracts the manufacturing steps of a product as individual (production) service requests. PaaS creates a market place for small-to-mid sized manufacturing industry by coordinating multiple manufacturers to provide the requested services.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a request for a predicted ensemble score in real-time. A subset of base model instances is formed by use of a preconfigured priority policy. A fitness score of the formed subset, quantifying the accuracy of the subset, is calculated as a sum of weights respective to the base model instances in the subset. A number of base models represented in the subset is less than or equal to a number of all based models.

Abstract: Methods, systems, and apparatus for providing an enhanced hotel guest experience. Disclosed methods include the actions of receiving data indicating the presence of a hotel guest from one or more sensors; generating a likelihood score that the hotel guest is going to their hotel room; determining that the generated likelihood score exceeds a likelihood threshold score; and based on determining that the generated likelihood score exceeds the likelihood threshold score, sending one or more instructions to one or more devices located within the hotel room.

Abstract: Systems and methods are provided for reducing failure rates of a manufactured products. Manufactured products may be clustered together according to similarities in their production data. Manufactured product clusters may be analyzed to determine mechanisms for failure rate reduction, including adjustments to test quality parameters, product formulas, and product processes. Recommended product adjustments may be provided.

Abstract: An answer to a question may selected from answers from a set of answering pipelines. Question answer data can be generated for a question, using a first answering pipeline. Another set of question answer data can be generated for the second question, using the second answering pipeline. The question answer data can include answers and confidence values for each answer. Using a weighting formula and a blending profile for the first answering pipeline, a vote weight can be determined for an answer with the highest confidence value. The same weighting formula and a second blending profile may be used to determine a vote weight for another answer with the highest confidence value. An answer to the question may be selected from the answers, based on the overall highest vote weight.

Abstract: In one or more embodiments of the present invention, a method modifies a graphical user interface (GUI) for an application to improve GUI usability. One or more processors identify a non-intuitive icon on a current graphical user interface (GUI) The processor(s) match the non-intuitive icon to a traditional icon that performs a same function as the non-intuitive icon when selected by a user. The processor(s) replace the non-intuitive icon with the traditional icon on the current GUI.

Abstract: A method and an apparatus for generating a model are provided. The method includes: acquiring a sample set including sample sentences and labeling knowledge corresponding thereto; and selecting a sample from the sample set, and performing following training steps: inputting a sample sentence into a first initial model to generate first prediction knowledge corresponding to the sample sentence; inputting the first prediction knowledge into a second initial model to generate a first prediction sentence corresponding to the first prediction knowledge; inputting labeling knowledge into the second initial model to generate a second prediction sentence corresponding to the labeling knowledge; inputting the second prediction sentence into the first initial model to generate a second prediction knowledge corresponding to the second prediction sentence; determining a first reward signal; and training, using a reinforcement learning method based on the first reward signal to obtain a first model.

Abstract: Various embodiments are provided for integrating multiple domain learning and personalization in a dialog system for a user in a computing environment by a processor. One or more problem instances may be defined for multiple domains according to a problem instance template, identified user intent, links to one or more problem solvers associated with the multiple domains, or a combination thereof. A dialog plan may be determined to further define the one or more problem instances in response to user input. A solution may be provided to the user for the one or more problem instances.

Abstract: A factor estimation device is configured to receive information pertaining to objects, to extract state information from the information received, to identify a predetermined state pertaining to a first object from among the objects, to receive state information extracted that corresponds to the predetermined state and classify the predetermined state, to extract condition information from the information received, to identify the condition up until the predetermined state, and to receive condition information that is output by the condition-information extraction unit and corresponds to the condition identified and classify the condition identified. Subsequently, the factor estimation device is configured to estimate the condition that may result in the predetermined state on the basis of the result of classifying the predetermined state and the result of classifying the identified condition.

Abstract: An action selection learning device includes a memory; and a processor coupled to the memory and configured to generate a reference model that is a set of model parameter vectors that indicate an influence level of each factor that influences selection of an action alternative, calculate a selection probability for each action alternative, for each of the model parameter vectors, calculate a model parameter vector for each user using a subset of model parameter vectors extracted from the reference model, based on the selection probability for each action alternative and a selection history of the action alternative by each user, generate the action alternatives based on the model parameter vector for each user, and transmit the generated action alternatives to a terminal device.

Abstract: Provided are a method and apparatus for determining driver's drowsiness. The method for determining driver's drowsiness includes: mapping the biometric data to a drowsiness determination model generated in advance; determining drowsiness of the driver based on a distribution of the biometric data in the drowsiness determination model; detecting first biometric data of the driver at a predetermined first time interval; correcting the biometric data of the driver detected during a time after the first time interval based on a center of distribution of the first biometric data; and determining whether or not the driver drowses based on the corrected biometric data, thereby optimizing the drowsiness determination model for each person/situation using driver data measured on a vehicle.

Abstract: A method for performing at least one action on a user's computing-device, according to at least one user-moment, in-cluding: collecting data comprising at least one signal from the computing-device; analyzing the collected data in real time, to determine occurrence of at least one user-moment; analyzing by the processor a plurality of user-moments, to predict at least one future user-moment, related to what a user is expected to do, need or want; receiving a list comprising at least one action that may be applied on the user's computing-device; receiving at least one rule, associating the at least one action with the at least one predicted user-moment; receiving at least one rule-condition, associated with the rule and the at least one predicted user-moment; and performing at least one applied-action on the user's computing-device, according to the applied-rule, if the at least one rule-condition is met.

Abstract: A system for inducing a physical state in a user. The system includes a sensor associated with the user, an audio output device, and a computer. The computer obtains, from a database, an identification of a type of music associated with a first phase of sleep, and determines, based on data from the sensor, that a user is in a second phase of sleep. Music of the type associated with the first phase of sleep is selected, and the selected music is output to the user through the audio output device.

Abstract: The present invention relates to a method and server for providing a probability of encountering other people and, more specifically, to a technique for calculating a probability of an encounter between a user and any other user by analyzing information provided by the users. The server for providing a probability of encountering other people according to the present invention comprises: a user information database unit for storing event information provided by two or more users; a schedule analysis unit for analyzing event information and extracting time information and space information of each of the users according to an information extracting algorithm so as to generate probability factor information; and a probability calculation unit for determining the degree of overlapping between the user probability factor information of each two users so as to calculate the probability that the two users encounter each other.

Abstract: A stacked quantum computing device including a first chip that includes a first dielectric substrate and a superconducting qubit on the first dielectric substrate, and a second chip that is bonded to the first chip and includes a second dielectric substrate, a qubit readout element on the second dielectric substrate, a control wire on the second dielectric substrate, a dielectric layer covering the control wire, and a shielding layer covering the dielectric layer.

Abstract: A technology is described for automating deployment of a machine learning model. An example method may include receiving, via a graphical user interface, credentials for connecting to a data store containing a plurality of datasets and connecting to the data store using the credentials. A selection of a target metric to predict using the machine learning model can be received, via the graphical user interface, and datasets included in the plurality of datasets that correlate to the target metric can be identified by analyzing the datasets to identify an association between the target metric and data contained within the datasets. The datasets can be input to the machine learning model to train the machine learning model to generate predictions of the target metric, and the machine learning model can be deployed to computing resources in a service provider environment to generate predictions associated with the target metric.

Abstract: In general, embodiments of the present invention provide systems, methods and computer readable media for curating a training data set to ensure that training data being updated continuously from a data reservoir of verified possible training examples remain an accurate, high-quality representation of the distribution of data that are being input to a predictive model for processing.

Abstract: A control data creation device is provided that has an acquisition part, a creation part and an evaluation part. The acquisition part acquires input information concerning traveling of a human-powered vehicle. The creation part creates by a learning algorithm a learning model that outputs output information concerning control of a component of the human-powered vehicle based on input information acquired by the acquisition part. The evaluation part evaluates output information output from the learning model. The creation part updates the learning model based on training data including an evaluation by the evaluation part, input information corresponding to an output of the output information and the output information.

Abstract: Disclosed herein are system, method, and computer program product embodiments for utilizing a feedback loop to continuously improve an artificial intelligence (AI) engine's determination of predictive features associated with a topic. An embodiment operates by training an AI engine for a topic using data from a data source, wherein the topic is associated with a geolocation. The embodiments first receives a set of predictive features for the topic from the trained AI engine. The embodiment transmits the set of predictive features for the topic to a set of electronic devices. The embodiment second receives a set of audiovisual content captured by the set of electronic devices. The set of electronic devices capture the set of audiovisual content based on the set of predictive features for the topic. The embodiment finally retrains the AI engine based on the first set of audiovisual content.

Abstract: Disclosed is a technique that can be performed by an electronic device. The electronic device can generate time-stamped events, extract training data from the time-stamped events, and sending the training data over a network to a remote computer. The electronic device can receive model data generated by the remote computer from the training data by use of a machine learning process, update a local model of the electronic device based on the received model data, and generate an output by processing locally sourced data of the electronic device with the updated local model.

Abstract: Systems for dynamically recognizing progress and generating recommendations are provided. In some examples, a system may image data from an augmented reality device. The image data may include video images, still images, images of machine-readable code, and the like. The received image data may be analyzed in real-time to identify an object within the data. In some examples, machine learning may be used to identify one or more characteristics of the object. The identified characteristics may be compared to one or more pre-defined goals or limits and a notification may be generated based on the comparison. The notification may be transmitted to the augmented reality device and displayed on the augmented reality device. In some examples, based on the comparison, machine learning may be used to generate one or more recommendations and a notification may be generated including the recommendations and may be transmitted to the augmented reality device for display.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying user behavior as anomalous. One of the methods includes obtaining user behavior data representing behavior of a user in a subject system. An initial model is generated from training data, the initial model having first characteristic features of the training data. A resampling model is generated from the training data and from multiple instances of the first representation for a test time period. A difference between the initial model and the resampling model is computed. The user behavior in the test time period is classified as anomalous based on the difference between the initial model and the resampling model.

Abstract: A model training method includes: acquiring a plurality of user data pairs, wherein data fields of two sets of user data in each user data pair have an identical part; acquiring a user similarity corresponding to each user data pair, wherein the user similarity is a similarity between users corresponding to the two sets of user data in each user data pair; determining, according to the user similarity corresponding to each user data pair and the plurality of user data pairs, sample data for training a preset classification model; and training the classification model based on the sample data to obtain a similarity classification model.

Abstract: An improved system and process for machine-learning upgrade analysis and training thereof is provided herein. A request to analyze the time to upgrade a current system to a target system may be received. A change list having one or more changes for the target system may be read. Custom code for the current system may be compared to the change list to identify recommended changes to the custom code to upgrade the custom code to be compatible with the target system. The recommended changes may be classified into one or categories respectively via a trained first machine-learning algorithm. Time to upgrade the custom code for the respective classified changes may be estimated via a trained second machine-learning algorithm. The recommended changes, the classifications of the recommended changes, and the time estimates of the recommended changes may be provided.

Abstract: The disclosed computer-implemented method may include matching transportation requests (e.g., made to a dynamic transportation matching system) to one or more transportation providers via transfer points. Matching one or more transportation requestors to a single transportation provider may lead to inefficiencies. By matching transportation requestors with one or more transportation providers via transfer points, a dynamic transportation matching system may increase the efficiency of trips for both transportation providers and transportation requestors. The method may also allocate transportation resources more efficiently across different regions, areas, and/or types of transit areas. In addition, the method may efficiently distribute transportation requestors across different transit options throughout a region to minimize congestion, to minimize over-usage of some constrained transit options, and/or to minimize travel time of transportation providers and/or transportation requestors throughout the region.

Abstract: Provided are a system and method for determining whether an apparent booking is a genuine or actual booking. Bookings occur in all sorts of industries, such as travel, medical, entertainment, weddings, catering, and the like. In one embodiment, the method includes determining whether an apparent booking identified from a website calendar, and associated with a merchant, is a genuine booking of the merchant or is an unavailability of the merchant not related to a booking. For example, the genuineness of the booking may be determined based on additional information associated with the merchant, a geographic location, other merchants, and the like.

Abstract: An information processing apparatus includes a processor which executes accepting purchase of a ticket for an event from a first ticket purchaser and, if the first ticket purchaser is to travel to a venue for the event by a vehicle, accepting registration of information on a ride-sharing usage pattern, selecting, as a ride-sharing candidate, a second ticket purchaser which conforms to the ride-sharing usage pattern for the first ticket purchaser from among ticket purchasers which have purchased tickets for the event or a similar event partially identical in venue and period to the event, and presenting the second ticket purchaser to the first ticket purchaser.

Abstract: The disclosed computer-implemented method may include (i) receiving a first transport request and a second transport request, (ii) evaluating a fitness of matching the first and second transport requests to be fulfilled by a transport provider, based at least partly on a transportation overlap between the first and second transport requests, (iii) generating a simulated future transport request, (iv) evaluating a fitness of matching the first transport request with the simulated future transport request, based at least in part on a transportation overlap between the first transport request and the simulated future transport request, and (v) matching the first and second transport requests based at least in part on the fitness of matching the first and second transport requests and based at least in part on the fitness of matching the first transport request with the simulated future transport request. Various other methods, systems, and computer-readable media are disclosed.

Abstract: A computer-implemented method of determining a route is provided. More specifically, provided is a method and apparatus for determining a route amongst obstacles and for recording the determined route. The methods and apparatus for determining a route may be uses for computerised navigation systems and autonomous vehicles.

Abstract: An apparatus and method for using a mobile computer device for graphically displaying and modifying information in a manner to enhance comprehension of the information and allowing for the mobile and decentralized management of information to be accomplished, wherein such information may be related to bed management and patient placement information and, furthermore, enabling the information of interest to be organized, sorted, and used in various useful and novel ways.

Abstract: Techniques are described for refining system-aided user determination in the current modeling context. At runtime, operations defined in a listing of workflow steps associated with a current workflow are executed. Each step is associated with a role that is associated with the execution of the step. To execute the operations, a workflow step from the listing of workflow steps is identified. Then whether the role associated with the workflow step is a reassigned role is determined based on a reassignment indicator that is persisted in a memory associated with the role. If the role is not associated with a reassignment indicator, the workflow step is executed using a first set of users associated with the role. Otherwise, the workflow step is executed using a second set of users identified as a reassigned set of users. At design time, at least one role is reassigned via a user interface.

Abstract: A Data Processing Risk Remediation System may be configured to: (1) access risk remediation data for an entity that identifies suitable action(s) to remediate a risk in response to identifying one or more data assets of the entity that may be affected by potential risk trigger(s); (2) receive an indication of an update to the one or more data assets; (3) identify one or more updated risk triggers for the entity; (4) analyze the one or more potential updated risk triggers to determine a relevance of a risk posed to the entity by the one or more updated risk triggers; (5) use one or more data modeling techniques to identify one or more data assets associated with the entity that may be affected by the risk; and (6) update the risk remediation data to include the one or more actions to remediate the risk.

Abstract: A system for providing a service to load and store an article of a passenger of an autonomous vehicle may include one or more processors that are configured to: based on Deep Neural Networks (DNN) training using various information, determine a risk of damage corresponding to storage positions in a storage space of the autonomous vehicle that accounts for movement of loads in the storage space during travelling along the travel route; classify the storage space into at least one of a safety zone, a normal zone, or a danger zone according to the determined risk; and determine positions of a plurality of loads to be loaded based on the determined risk of each load, a weight of each load, and a size of each load.

Abstract: Data from multiple sources may be gathered continuously to perform reconciliation operations. The data items in a first data set may be matched with those in the second data set using a data matching technique. Based on the matching, a confidence score indicative of an extent of match between the data items in the data sets may be generated. Based on the confidence score and predefined thresholds, it may be ascertained if the data items are reconciled. The non-reconciled items in at least one of the first data set and the second data set may be classified in a classification category, based on an artificial intelligence based technique, the classification category being indicative of an explanation of a non-reconciled data item being non-reconcilable. When the data item is not reconciled and classified, the data item is identified as an open item for further analysis.

Abstract: A method to associate a set of first entities to a set of second entities, e.g., computing jobs to processors, agent teams to workspace resources within a physical location, or the like. The NG is seeded using a force directed graph (FDG), whose “seed” particles represents the agents and their relative interconnectedness. The FDG is first brought into an equilibrium state to define a solution space. A relative coordinate system of the FDG solution space is then translated to a number of vertices represented in the NG, and then an initial seeding of the seed particles in the NG (based on their relative positions in the FDG solution space) is carried out. A search is then performed. During the search, each seed vertex releases its embedded agents to adjacent vertices to enable the agents to search for and achieve a required count.

Abstract: Systems and methods of the present disclosure facilitate managing a business. In some embodiments, the system includes a product data module and a plurality of business process modules executing on at least one processor of a server. The product data module may be configured to store at least one product description. Responsive to a first user, the system may associate a product class with a first description. Responsive to a second user, the system may associate a first product description with a first of the business process modules. The system may be configured to select a second business process module based on the product class and update the second business process module with the first product description.

Abstract: Methods and systems for managing supply chains are disclosed. Replenishment of items within retail stores and distribution centers is optimized to respond to real-time demands. One method includes receiving demand signals corresponding to a sold inventory items and evaluating those demand signals against real-time inventory positions and demand forecasts for that particular inventory item to determine whether to replenish the inventory item and how much inventory to replenish. A router service for assessment of such demand signals is also disclosed.

Abstract: A supply chain optimization method and system for at least one supply chain entity are provided. Input data related to a supply chain to be optimized is collected in real-time. A decision problem specific to and supply chain parameter(s) to be optimized for the at least one supply chain entity are inferred in real-time from the input data. A conversational user interface is used to query the user in real-time in order to gather additional supply parameter(s) to be optimized and a natural language input is received in real-time, via the conversational user interface, in response to the query. The natural language input is parsed in real-time to gather the additional supply chain parameter(s) and a solution to the decision problem is output based on the additional optimization parameter(s).

Abstract: A risk exposure model is developed for network or moveable assets not specific to a single, fixed address or location. An asset map using a plurality of geographic representation points is used to identify the physical locations of the asset portions (or possible physical locations in the case of a moveable asset). Baseline geographic, geologic, political, and demographic data is similarly represented using geographic representation points. Meta-data associated with each geographic representation point is used to identify details related to the asset or baseline feature at that geographic location. Risk exposure values are then calculated using the geographic representation points specific to the asset portions that are subject to risks associated with the location of the asset portion.

Abstract: A measure factory for generating analytic measures includes data sets representing business activities arranged as columnar arrays with each column being associated with a distinct source rule that applies to the column when it is used as a data source. The measure factory includes factory rules that govern which operations on available data sources may be executed under what conditions in the measure factory, such as by taking into account the source rules and other applicable factory rules. A factory rule execution hierarchy governs the execution of ready factory rules that lack dependency on other factory rules before executing ready factory rules that have dependency on other factory rules. A script generation facility generates a script to process the plurality of factory rules according to the factory rule execution hierarchy.