Abstract: An illustrative method includes generating, based on log data associated with at least one user session in a network environment associated with a user, a logical graph, wherein the logical graph comprises: (1) a first node corresponding to the user, (2) a plurality of additional nodes, and (3) a set of edges connecting the first node to one or more of the additional nodes, wherein each edge in the set of edges represents a change in behavior of the user; using the logical graph to detect an anomaly, wherein detecting the anomaly includes determining that a change has been made to at least one edge included in the set of edges; and generating, in response to detecting the anomaly, an alert.

Abstract: A system and method for slot selection is provided. A customer order is received for an in-store pickup at a retail store and a set of inputs is received. The set of inputs includes slot-related information related to a first set of timeslots available at the retail store within a first time-period, inventory information, and order preparation constraints. Based on the set of inputs, a capacity constraint is determined. The capacity constraint sets a number of customer orders to be scheduled for the in-store pickup within each of the first set of timeslots. Thereafter, a first timeslot is determined from among the first set of timeslots. The first timeslot accommodates the customer order in accordance with the capacity constraint and a pickup wait time within the first timeslot is below a threshold. The first timeslot is displayed on a customer device.

Abstract: Methods and systems are described for providing hierarchical demand forecasting for state space reduction. Using a hierarchical architecture, a base model may be trained to capture a range of shared structure in a first data set that can be used to draw inferences on using smaller sets of data representative of the “whole picture.” For example, training data may be sampled and prepared and used to train a base model in a first stage. In a next stage, one or more downstream models may be trained on the structure and samples of uncensored demand generated by the base model to produce forecasts for items and locations, including items and locations for which there may be little or no historical data. The downstream models that would otherwise require a large amount of data for training can be generated on demand using less training data, training time, computing processing, and memory.

Abstract: Determining additional signals for determining cybersecurity risk is disclosed, including: obtaining signals associated with a cybersecurity risk, wherein the obtained signals include technographic signals and query derived signals obtained from queries; combining the technographic signals and the query derived signals into a Bayesian model indicating the cybersecurity risk; and determining additional technographic signals or additional query derived signals associated with the cybersecurity risk to obtain such that the additional technographic signals or the additional query derived signals are to be computed to impact the cybersecurity risk.

Abstract: A result ranking system can include a computing device that is configured to obtain a plurality of items based on a query and a value corresponding to each item of the plurality of items. The computing system can also be configured to retrieve a value distribution corresponding to the query and generated based on customer interaction data. The computing system can also, for each item of the plurality of items, determine a feature value based on the value distribution and the corresponding value of the item. The computing system can be further configured to transmit the plurality of items to a customer device for display in an arrangement based on the corresponding feature value.

Abstract: Devices, systems, and methods are provided for cloud-based job scheduling and management. A method may include receiving, by at least one serverless processor of a cloud-based network, data from a first interface. The method may include determining, based on the data, a first activity and a second activity, the first activity associated with a first service of the cloud-based network, and the second activity associated with a second service of the cloud-based network. The method may include determining, based on the data, a precondition associated with causing execution of the first activity and the second activity. The method may include determining that an event associated with the cloud-based network has occurred, and generating an instance associated with causing performance of the first activity and the second activity. The method may include discarding the instance after performance of the first activity and the second activity.

Abstract: Described are a system, method, and computer program product for applying deep learning analysis to predict and automatically respond to predicted changes in financial device primacy for a financial device holder. The method includes receiving transaction data representative of a plurality of transactions between the financial device holder and at least one merchant. The method also includes generating time series data based on the transaction data and generating a predictive model configured to: (i) receive an input of time-interval-based transaction data; and (ii) output a probability of primary financial device primacy change, the predictive model trained based on historic transaction data. The method further includes determining a probability of primary financial device primacy change for the financial device holder by applying the predictive model to the time series data. The method further includes, generating at least one communication to at least one issuer and/or the financial device holder.

Abstract: A system may transmit an MLM to one or more entities. The system may receive, from the one or more entities, data associated with a plurality of customers, the data generated by the MLM. The system may train a federated deep NN based on the data. The system may receive, from a user, a first request for a loan. The system may generate, using the federated deep NN, a risk score associated with the user, wherein the risk score comprises a likelihood the user will satisfy condition(s) of the loan. The system may transmit, to lender(s), the risk score and a second request for loan option(s) for backing the first request for the loan. The system may receive, from the first lender(s), the loan option(s) for backing the first request for the loan, and may transmit the loan option(s) to the user.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate fault localization and alert aggregation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a graph component that employs an algorithm to generate a directed graph of computing elements having performance alerts in one or more abstraction layers of a computing environment. The computer executable components can further comprise a fault localization component that employs a topological sort algorithm to identify one or more of the computing elements causing the performance alerts based on the directed graph.

Abstract: An information processing apparatus includes at least one processor. The processor performs a process of displaying biological information of a user in a first region of a display screen, displaying a text indicating a content of a conversation between the user and a chatbot in a second region of the display screen together with the biological information displayed in the first region, and displaying a result of a web search in a third region of the display screen together with the biological information displayed in the first region and the text displayed in the second region.

Abstract: A computer program stored in a computer-readable storage medium includes executing operations for providing a content processing method when executed on one or more processors in a computing device The operations can include an operation of displaying a first screen including a project-involved object for receiving a selection input for a project, and an operation of displaying a second screen for displaying a project execution step corresponding to the selected project. The second screen may include a navigation area including a step selection object for receiving a selection input for the project execution step and a project execution area for content processing corresponding to the project execution step.

Abstract: A user interface generation system and associated methods are disclosed for displaying nodes of a computer program or computation. The system may determine an ordering and position of elements for display. The ordering can include determining a first ancestor branch of a node associated with a stage with an earliest start time among the start times associated with the stages of a plurality of ancestor branches. This first ancestor branch may be designated as first in the ordering. A second ancestor branch may be determined from among the remaining ancestor branches having an stage with an earliest start time among the start times associated with the remaining stages. This second ancestor branch can be designated as second in the ordering.

Abstract: Generating a cybersecurity risk model using sparse data is disclosed, including: obtaining signals associated with a cybersecurity risk, wherein the obtained signals include technographic signals and query derived signals obtained from queries; generating pseudo signals based at least in part on a priori factors relating to the cybersecurity risk; and combining the pseudo signals and the obtained signals into a Bayesian model indicating the cybersecurity risk.

Abstract: Artificial Intelligence (AI)-based network control includes obtaining data from a network having a plurality of network elements; analyzing the data with one or more Machine Learning (ML) algorithms to determine one or more actions for network control; analyzing the determined one or more actions to determine any risks associated therewith; and one of allowing, modifying, and blocking the determined one or more actions based on the determined risks to safeguard the network. The risks can be based on one or more of (1) non-deterministic behavior AI inference which is statistical in nature, (2) unbounded uncertainty of the AI inference that can result in arbitrarily large inaccuracy on rare occasions, (3) unpredictable behavior of the AI inference in presence of input data that is different than data in training and testing datasets, and (4) malicious input data.

Abstract: A method for multi-policy conflict avoidance in an autonomous network comprising: collecting network state information; acquiring a set of multiple policies to be verified; constructing a policy ordering space tree containing all multi-policy execution sequences; performing a depth-first traversal on the policy ordering space tree, extracting a multi-policy execution sequence to be verified, then constructing an initial simulation data plane, injecting each policy in the multi-policy execution sequence into the simulation data plane one by one in sequence, and storing a simulation data plane after each policy is inserted; detecting whether there is a conflict in the simulation data plane generated after each policy is executed, inferring dependencies among multiple policies in the conflict policy sequence, pruning the policy ordering space tree, to efficiently select and update the multi-policy execution sequence avoiding conflicts.

Abstract: A method may be used to predict a business' category by analyzing the business' vendors. A neural network architecture may be trained via supervised learning to predict categories for businesses based on listed vendors. The neural network may be used to classify uncategorized businesses within an accounting software database. A list of factors associated with a business' success may be generated by analyzing, aggregating and ranking factors determined to be relevant to a business based on its categorization. The factors associated with the business' success may be related to the products and/or services offered by the business and the format of which those products and/or services are offered by the business. The factors may also be related to the products and/or services purchased by the business from a vendor and the format of which those products and/or services are purchased from the vendor.

Abstract: Detecting anomalous behavior of a device, including: generating, using information describing historical activity associated with a user device, a trained model for detecting normal activity for the user device; gathering information describing current activity associated with the user device; and determining, by using the information describing current activity associated with the user device as input to the trained model, whether the user device has deviated from normal activity.

Abstract: A system and method for preparing structural analyses for solar installation projects, designing photovoltaic solar electrical systems and thermal solar systems processing solar installation plans, including the processing and interpretation of user input and jobsite information, supplementation of user input with data queried from relevant databases, processing and analyses of jobsite information according to requisite analyses, automated generation of forms and reports for review by a reviewing entity, delivery of signed and sealed documents for process by appropriate regulatory bodies, and addition of third-party verified eSignature and/or file encryption to sign and/or seal reports and plan documents.

Abstract: An information processing apparatus comprises: an obtaining unit configured to obtain an estimation result estimated using an estimation model; a determination unit configured to determine a conversion table configured to correct the estimation result using the estimation model based on an estimation accuracy in the estimation model; and a correction unit configured to correct the estimation result based on the conversion table.

Abstract: An embodiment of the invention may include a method, computer program product and system for deployment of microservices within a shared pool of configurable computing resources. An embodiment may include creating a dependency map for a plurality of microservices of an application deployed on the shared pool of configurable computing resources. An embodiment may include identifying attributes, with associated values, for each microservice of the plurality of microservices and identifying eligible deployment locations within the shared pool of configurable computing resources. An embodiment may include creating a bipartite graph based on the plurality of microservices and the identified eligible deployment locations. An embodiment may include applying bipartite matching to the shared pool of configurable computing resources based on the created bipartite graph.

Abstract: Techniques for identifying and validating online content items for presentation to users are disclosed. Disclosed systems and methods use a sentiment analyzer to determine a sentiment of a candidate content item and collateral content items identified using keywords associated with the candidate content item, determine a measure of agreement in sentiment using the sentiments determined for the candidate content item and collateral content items, and provide at least a portion of the candidate content item in a display at a client computing device, the display including a consensus belief indicator representing the measure of agreement in sentiment.

Abstract: A method for managing a data protection module includes: obtaining client metadata of a client environment data protection module (CEDPM); analyzing the client metadata to extract relevant data; inferring at least a period of time a first user of the CEDPM spent to initiate performing a task, a number of steps taken by the first user to initiate performing the task, and a number of attempts made by the first user to initiate performing the task; obtaining at least an ease of use score, an automation efficiency score, and a success score for a product feature; obtaining a maturity rating for the product feature based on the scores; determining that the maturity rating for the product feature is less than a predetermined maturity rating; and sending a recommendation to a second user of a vendor environment (VE) data protection module to manage the maturity rating for the product feature.

Abstract: Load Plan Generator (LPG) is a BIAPPS utility for generating ODI load plans based on desired subset of fact tables for loading BIAPPS Data Warehouse. The tool simplifies the configurations process by minimizing the manual steps and configurations and provides a guided list of configurations steps and checklists. The load plan components can include different sets of load plans that will be stitched together by the load plan generator to create one load plan for loading chosen fact groups in the warehouse sourcing from different transaction systems.

Abstract: Techniques and mechanisms for managing a set of data network nodes in a Network Management System (NMS). In some examples, a network orchestrator receives a first service request to trigger a first service transaction to re-configure the set of data nodes in the data network, and trigger, the first service transaction to re-configure the set of data nodes. In some examples, the network orchestrator receives a second service request to trigger a second service transaction to re-configure the set of data nodes. The orchestrator determines whether the second service transaction conflicts with the first service transaction that is currently running. If the second service transaction does not conflict with the first service, it triggers processing the second service. If the second service transaction does conflict with the first service transaction, it delays from processing the second service transaction.

Abstract: This application discloses a fault rectification operation recommendation method and apparatus, and a storage medium in the field of communication technologies. In some implementations, after fault information is obtained, a rectification contingency plan corresponding to the fault information may be searched for from a contingency plan library. When the rectification contingency plan corresponding to the fault information cannot be found in the contingency plan library, the fault information may be processed by using a recommendation model to obtain a recommended contingency plan. Further, one operation is selected from one or more candidate operations included in the recommended contingency plan as a fault rectification operation.

Abstract: Methods and systems are provided to efficiently update account profiles based on a predicted likelihood of use, including by ranking the account profiles according to the likelihood of use. The disclosed system can considerably improve the processing time to update account profiles with the most recent information available, including new access requests. An authentication platform receives a plurality of new access requests, including request data and account identifiers associated with account profiles. The request data is transmitted to a prediction engine that determines a ranking of the account identifiers based on a predicted likelihood of use during a next time interval. A profile batch scheduler retrieves a first set of access requests based on the ranking. The system updates a first set of account profiles based on the ranking, and stores the updated account profiles for use by the authentication platform.

Abstract: Methods and system for recommending components to a user. Implementations are directed to receiving, from a user, a user query for a design recommendation, the user query comprising a plurality of terms; determining, from the plurality of terms, a user intent including at least one query-derived design function and not including a named component for the design recommendation; receiving additional contextual information for the design recommendation, wherein the additional contextual information comprises a plurality of action attributes for the at least one query-derived design function; determining, from a database, a plurality of design recommendations, wherein each design recommendation comprises a respective recommended component and a plurality of recommended component actions; selecting, from the plurality of design recommendations, a subset of design recommendations; and providing, to the user, the subset of design recommendations.

Abstract: A user interface generation system and associated methods are disclosed for displaying nodes of a computer program or computation. The system may determine an ordering and position of elements for display. The ordering can include determining a first ancestor branch of a node associated with a stage with an earliest start time among the start times associated with the stages of a plurality of ancestor branches. This first ancestor branch may be designated as first in the ordering. A second ancestor branch may be determined from among the remaining ancestor branches having an stage with an earliest start time among the start times associated with the remaining stages. This second ancestor branch can be designated as second in the ordering.

Abstract: Log data associated with at least one user session in a network environment associated with an original user is received. A logical graph is generated using at least a portion of the received log data. One example of such a logical graph is a privilege change graph that models privilege changes between processes. Another example of such a logical graph is a user login graph that models machines with which the original user interacts. Another example of such a logical graph is a machine-server graph that clusters machines into nodes based on resources executing on the machine. The generated logical graph is used to detect an anomaly.

Abstract: The subject disclosure relates to techniques for real-time lane validation. A process of the disclosed technologies can include steps for receiving a route from a remote computing system, the route indicating lanes on the route that an autonomous vehicle must traverse, traversing at least one lane of the lanes on the route, and sending sensor data to the remote computing system after traversing the at least one lane, the sensor data indicating whether the at least one lane is in accordance with a virtual lane of a virtual map, the virtual lane corresponding to the at least one lane.

Abstract: An information processing method which is performed by an information processing apparatus for forecasting demand for a service provided by a mobile vehicle, comprises a classification step of classifying a plurality of unit regions included in a first area into a plurality of categories, respectively, by using a first classification model; a first building step of building a first demand forecasting model by determining a first set of parameters to be applied to each of the plurality of categories based on the classified categories and track record data in the first area; a second building step of building a second classification model by using classification criteria possessed by the first classification model, and building a second demand forecasting model by using the first set of parameters; and a forecasting step of performing demand forecasting in a second area by using the second classification model and the second demand forecasting model.

Abstract: An apparatus comprises a processing device configured to receive, from a given host device in a given data center that utilizes a given piece of software, first configuration information associated with the given host device. The processing device is also configured to identify available software upgrades for the given piece of software and to select issue indicators associated with installation of the available software upgrades on other host devices. The processing device is further configured to provide, to the given host device, a recommendation to install the available software upgrades for the given piece of software on the given host device responsive to determining that (i) the first configuration information associated with the given host device has at least a threshold level of similarity to the second configuration information of the other host devices and (ii) the issue indicators have at least a threshold issue criticality level.

Abstract: Systems and methods for automatic error rejection are provided. Systems and methods described herein bypass the creation of a staging table at the outset and, instead, attempt a direct merge from a source data location to a target data location. In the event that the merge fails, then a temporary/staging table can be loaded where errors can be logged, validations can be performed, and erroneous data can be corrected.

Abstract: Apparatuses and methods are provided to generate customizable databases and/or analyze performance. In an example embodiment, a method of generating customizable databases is provided. The method includes receiving a calculation expression relating to one or more defined characteristics. The calculation expression may be defined by a user. The method also includes loading data into a data warehouse. The data includes at least one of the one or more defined characteristics. The method further includes generating a data cube based on the received calculation expression and the data loaded into the data warehouse. The data cube includes an accessible table. A corresponding apparatus is provided. Additional method and apparatus to analyze performance are also provided.

Abstract: In one embodiment, a device obtains a predictive model that predicts a behavior of a path in a network. The device computes, based in part on the predictive model, a route in the network that includes the path, in accordance with a routing policy that instructs the device to use the predictive model as an attribute of the path during computation of the route. The device validates that the path exhibited the behavior predicted by the predictive model. The device initiates retraining of the predictive model, when the behavior predicted by the predictive model does not match the behavior of the path.

Abstract: A system for performing document extraction is configured to: (a) receive a first document; (b) extract the first document into document elements, the document elements including pages, lines, paragraphs, or any combination thereof; (c) determine a first set of fields of interest for the first document, wherein the first set of fields of interest are determined via a type of the first document or via a first set of queries for probing the first document; (d) determine, from a plurality of closed domain question answering (CDQA) models, a first set of CDQA models that provides answers to each field of interest included in the first set of fields of interest; and (e) provide answers to the first set of fields of interest to the client device.

Abstract: Features are disclosed for dynamically provisioning an application stack using a set of infrastructure resources. A computing device can receive an infrastructure template from an administrative device. Based on the infrastructure template, the computing device can determine a schema and an infrastructure as code. Using the schema, the computing device can receive a specification file from a developer device or an administrative device. The specification file can be a service specification file or an environment specification file. The computing device can inject the values of the specification file into the infrastructure as code. The computing device can use the injected infrastructure as code to generate and deploy the application stack to the developer device.

Abstract: A method for manufacturing and executing single-use systems. Invention provides provably secure system design, instantiated in heterogeneous hardware that exists solely for the lifetime of a mission. More specifically, the present invention provides a functional mission analysis, formal specification and mathematically rigorous machine-checkable representation of a hardware mission instantiation to significantly reduce the vulnerabilities of a mission.

Abstract: An illustrative geologic modeling method may comprise: obtaining a geologic model representing a subsurface region in physical space, the subsurface region being divided into multiple zones; sequentially generating a physical space simulation mesh for each of said multiple zones by: (a) mapping a current zone of the physical space geologic model to a current zone of a design space model representing a current zone of an unfaulted subsurface region; (b) gridding the design space model to obtain a design space mesh; (c) partitioning cells in the current zone of the design space mesh with faults mapped from the current zone of the physical space geologic model, thereby obtaining a partitioned design space mesh for the current zone; and (d) reverse mapping the partitioned design space mesh for the current zone to the physical space for the current zone.

Abstract: Methods, computer readable media, devices, and systems provide for distributed machine learning. In one aspect, a method of training a model is disclosed. The method includes receiving, by a client device, from one or more servers, an intermediate model, training, by the client device, the intermediate model based on private data, and transmitting, by the client device, to the one or more servers, the trained intermediate model.

Abstract: A system and method are disclosed for analyzing the maturity of one or more supply chain entities according to competencies of an omni-channel retailer. The one or more supply chain entities including a retail manager that assesses the one or more supply chain entities according to one or more competencies and determines one or more maturity gaps associated with the one or more competencies. The retail manger further identifies one or more transition projects that fill the one or more maturity gaps and roadmaps one or more transition activities that generate the one or more identified transition projects. The one or more supply chain entities further adjusts an inventory of one or more products at least partially based on the one or more roadmapped transition activities.

Abstract: An example embodiment may involve a software application executable on a computing device of a computational instance of a remote network management platform associated with a managed network. The computational instance may contain a database from which information associated with the managed network can be delivered to the client device. The software application may receive, from a client device of the managed network, a natural language query, parse the query using context-free grammar rules in Backus-Naur form (BNF), generate a search sentence based on the parsed query, search the database using the search sentence as a search query, and transmit, to the client device, a result of the search query. The context-free grammar rules may include an extended context-free grammar rule that defines a non-terminal symbol and comprises a Boolean NOT operator that eliminates one or more potential definitions of the non-terminal symbol from consideration when parsing the query.

Abstract: Examples can include a system for generating a spool sheet. A user can select multiple components on a graphical user interface (“GUI”). Then they can select an option to create a spool sheet. The system can determine a list of components in the selection for use in a bill of materials. This can be included in a spool page that includes a printable spool sheet region. Within the spool sheet region, the GUI can display a view of the selected components at a location indicated by an anchor node of the template.

Abstract: A system for building, training and productionizing machine learning models is disclosed. A model training specification is received, and a plurality of sets of hyper-parameters is obtained. Sets of training data and hyper parameter sets are distributed to distributed training systems. Models are trained in parallel using different sets of training data. Models are trained using multiple sets of hyper parameters. A candidate hyper-parameter set is selected, based on a measure of estimated effectiveness of the trained predictive models, and a production predictive model is generated by training a predictive model using the selected candidate hyper-parameter set and the complete set of training data.

Abstract: The present invention relates generally to a process for determining optimized communication rate plans for one or more communications devices across one or more communications networks. The present invention provides for determining an intelligent rate plan for a user having one or more devices operative on a communications network with one or more rate plans. The present invention, in one or more embodiments provides a user of communication devices with a cost-effective rate plan solution in relation to the user's use of their devices and available cost-savings programs available to the user.

Abstract: A capacity expansion method includes obtaining a measured workload of a service of an application, obtaining an application model of the application, and obtaining a measured workload of each upper-level service of the service; determining a predicted workload of the service based on the measured workload of the service, determining the measured workload of each upper-level service of the first service, and determining a first workload ratio corresponding to a first calling relationship; and determining a predicted workload of each lower-level service based on the predicted workload of the service and determining a second workload ratio corresponding to a second calling relationship.

Abstract: Methods and systems assist data center customer to plan virtual data center (“VDC”) configurations, create purchase recommendations to achieve either an expansion or contraction of a VDC, and optimize the data center cost. Methods generate recommendations on lower cost combinations of virtual machine (“VM”) guest OS licenses, server computer hardware and VM software to optimize the costs are generated, generate data center customer plans for additional VMs with Quest OS for a projected period of time, provide recommendations on lower cost combination of guest OS licenses, server hardware, and VM software to optimize the cost. Methods also report any underutilized licensed servers and provide recommendations for cost savings when volume licenses can be replaced by instance based software licenses. Methods may generate VM placement recommendations to data center customers while the customers attempt to manually migrate VMs to different server computers.

Abstract: In an example, each of a plurality of members of social networking service is mapped to a weighted skill vector, each weighted skill vector including a list of skills for the member with an associated weight indicating strength of the skill. Members of the social networking service that belong to an industry are aggregated to obtain a weighted matrix of members and skills along with compensation vectors indicating compensation for each of the members in the matrix. The weighted matrix of users and skills and corresponding compensation vectors is used to train a machine learning skill monetary value prediction model to output a predicted monetary value for one or more skills contained in a candidate vector fed to the machine learning skill monetary value prediction model.

Abstract: Methods and systems assist data center customer to plan virtual data center (“VDC”) configurations, create purchase recommendations to achieve either an expansion or contraction of a VDC, and optimize the data center cost. Methods generate recommendations on lower cost combinations of virtual machine (“VM”) guest OS licenses, server computer hardware and VM software to optimize the costs are generated, generate data center customer plans for additional VMs with guest OS for a projected period of time, provide recommendations on lower cost combination of guest OS licenses, server hardware, and VM software to optimize the cost. Methods also report any underutilized licensed servers and provide recommendations for cost savings when volume licenses can be replaced by instance based software licenses. Methods may generate VM placement recommendations to data center customers while the customers attempt to manually migrate VMs to different server computers.

Abstract: Methods and systems assist data center customer to plan virtual data center (“VDC”) configurations, create purchase recommendations to achieve either an expansion or contraction of a VDC, and optimize the data center cost. Methods generate recommendations on lower cost combinations of virtual machine (“VM”) guest OS licenses, server computer hardware and VM software to optimize the costs are generated, generate data center customer plans for additional VMs with guest OS for a projected period of time, provide recommendations on lower cost combination of guest OS licenses, server hardware, and VM software to optimize the cost. Methods also report any underutilized licensed servers and provide recommendations for cost savings when volume licenses can be replaced by instance based software licenses. Methods may generate VM placement recommendations to data center customers while the customers attempt to manually migrate VMs to different server computers.