Digital Commons Network^™

Bgp-Mvpn Source Discovery For Multiple Rendezvous Points, Aswin Kuppusami, Vengada Prasad Govindan, Mani Panchanathan

Defensive Publications Series

In multi-site Border Gateway Protocol (BGP) Multicast Virtual Private Network (MVPN) deployments, it is common to have site local Rendezvous Points (RPs) behind each of the Provider Edge (PE) nodes that participate in MVPN communications. Multiple RPs are necessary for de-centralized management and are used to make receivers join the RP most suited to them in multicast. However, it has always been a problem in such topologies that have multiple RPs for receivers to find sources. Presented herein are techniques that provide a mechanism for MVPN source-discovery that can greatly improve the efficiency of source discovery. In addition, techniques herein …

Reducing Stress In 3d Objects Made Using Fused Filament Fabrication, Tim Kuipers, Johan Versteegh

Defensive Publications Series

We propose a new 3D printing method to lessen the effects of tension in FFF printed objects. By simply changing the toolpaths of the outer wall traces we can print materials that otherwise would need a heated chamber and strict temperature control to avoid deformations.

Multivariate Time Series Unsupervised Anomaly Detection And Diagnosis In 5g Networks, Sreyan Ghosh, Sakshi ., Vijay Kataria

Defensive Publications Series

For a variety of reasons (including, for example, increasing cyber security threats, increased network heterogeneity, the increased use of virtualization technologies, etc.) maintaining the fifth generation (5G) networks of tomorrow will be challenging. To address such challenges techniques are presented herein that support a multivariate time series unsupervised method for anomaly detection using Key Performance Indicators (KPIs) that are derived from various infrastructure level metrics collected from all kinds of networking nodes deployed in 5G networks. Multivariate time series unsupervised anomaly detection is the future of anomaly detection with systems generating real-time time series data but this is an area …

An Accelerated Peer-To-Peer (P2p) Communication Method Facilitated By Reusing Existing P2p Paths For Low-Power And Lossy Networks, Huimin She, Harbor Dong, Wenjia Wu, Nan Yi

Defensive Publications Series

The Wireless Smart Utility Networks (Wi-SUN) alliance promotes interoperable wireless standards-based solutions for Internet of Things (IoT) deployments, such as distributed automation (DA). For some applications, such as smart utility or smart city applications, it is desirable to provide optimized peer-to-peer (P2P) routing. However, for P2P traffic within a Destination Oriented Directed Acyclic Graph (DODAG), packets either have to be routed through a root in a non-storing mode or through a common ancestor in a storing mode. Techniques herein provide for locally reusing and distributing projected directed advertisement object (P-DAO) tracks. For example, when a node receives a P-DAO track …

Multivariate Time Series Unsupervised Anomaly Detection And Diagnosis In 5g Networks, Sreyan Ghosh, Vijay Kataria

Defensive Publications Series

For a variety of reasons (including, for example, increasing cyber security threats, increased network heterogeneity, the increased use of virtualization technologies, etc.) maintaining the fifth generation (5G) networks of tomorrow will be challenging. To address such challenges techniques are presented herein that support a multivariate time series unsupervised method for anomaly detection using Key Performance Indicators (KPIs) that are derived from various infrastructure level metrics collected from all kinds of networking nodes deployed in 5G networks. Multivariate time series unsupervised anomaly detection is the future of anomaly detection with systems generating real-time time series data but this is an area …

Federated Data Access, Hp Inc

Defensive Publications Series

Data has become critical to drive decisions, manage devices, support engineering teams, support service

support teams, and many other uses on data driven organizations.

Data is coming from multiple sources, collected and stored in multiple systems and not easy to share

avoiding duplications and inefficiencies; assuring data quality and consistency.

Current approaches are creating data layers which internally are managing copies of the data for

operational purposes.

Due to the amount of data systems available it is also difficult to be aware of the existence of this data or

difficulties to share it so usually it ends with teams creating …

Improving Query Suggestions Based On Search Box Edits, Cliff Chin Ngai Sze, Lingyi Zhang

Defensive Publications Series

Users often enter terms into a search box and then modify the query. Such modifications may be based on, e.g., the real-time query suggestions offered by the search engine, or the user thinking of a different phrasing for the query. Such changes to entered search terms prior to executing the search are not captured in the search history, and are not taken into account for tailoring post-search query suggestions or search results. This disclosure describes the use of a trained machine learning model to customize query suggestions and/or search results based on terms previously typed in the search box, obtained …

Automatic Detection Of Gaps In Availability Of Authoritative Online Content, Abraham Ittycheriah, Alyssa Lingad, Anne Merritt, Cong Yu, Jan Machowski, Kinton Cheung, Maki Sugimoto, Renato Da Costa, Sarah Montgomery-Taylor, Shaan Varia, Shekhar Sharad, Srayan Datta, Tetiana Kedzierska, You Wu

Defensive Publications Series

This disclosure describes techniques to measure authority content gap (ACG), which represents the (lack of) authoritativeness in online content related to individual topics. The ACG metric is defined for various verticals, e.g., health, government services, legal, etc., and can be specific to region, country, language, or time period. The ACG is refreshed periodically, and it can be used in combination with other metrics relating to a content publisher. The ACG is a useful measure in various contexts, e.g., when an unpopular or obscure topic achieves sudden popularity, or when a new topic emerges. The ACG for a topic can indicate …

Automated Extraction Of Pivot Topics For Sideways Expansion Of Search Scope, Alankar Jain, William Mcmeans, William M Leszczuk, Sitaram Iyer, Seher Aylin Altiok, Mehrbod Sharifi, Jerome Miglino, James K. Barlow

Defensive Publications Series

Users benefit from mechanisms that can help them refine their queries to facilitate searching for information connected to their underlying intent. Apart from refinements to narrow the scope of a query, users can benefit from suggestions that can help them pivot their information seeking by expanding their search sideways to related topics. This disclosure describes computational techniques for automated determination of suitable topics and/or queries for helping users expand the scope of their information search by pivoting to topics related to their query. The techniques involve selecting a meta-query, performing query expansion, identifying, aggregating, and deduplicating related entities. The identified …

Metadata Service To Enable Display Of Rich Artifacts In Machine Learning Pipelines, Ajay Alfred, Pavel Dournov, Jingxiao Wu, Hongye Sun, Apoorv Verma (Ap), Ajay Gopinathan, Hui Miao, Neoklis Polyzotis

Defensive Publications Series

Cloud-based machine learning (ML) platforms enable ML practitioners to build, rebuild, and serve multiple machine learning models in production environments. Proper ML metadata tracking and management is important to enable large-scale experimentation and to provide traceability and verifiability for modern production ML. This disclosure describes a ML metadata service to manage the lifecycle of metadata consumed and produced by ML pipelines. The ML metadata service enables logging detailed metadata as artifacts, capturing metadata as typed artifacts, and capturing a ML pipeline in an intuitive workflow graph. The metadata service enables provision of a ML dashboard that displays visualizations of a …

Use Of Ad-Hoc Metrics To Identify Code Revision That Introduced Anomalies, Noah A. Brubaker

Defensive Publications Series

Large-scale software codebases are updated frequently by a large number of developers, leading to a large number of code revisions. It is difficult to identify the exact code revision at which an undesirable behavior (bug or culprit) was introduced, since there may be numerous subsequent changes to the codebase prior to detection of the undesirable behavior. This disclosure describes a general-purpose culprit finder that streamlines and automates the detection of a behavioral change to software code. In particular, the described techniques enable quick determination of the exact code revision that introduced a bug. An ad-hoc signal is defined that numerically …

Linearlegions: A Linear Size Cardinality Estimator, N/A

Defensive Publications Series

Counting the number of unique items in a data set is of interest in many applications. For example, the owner of a web property, e.g., a video sharing website, a social media website, a search engine, etc., benefits from knowing the number of unique visitors to their site, the number of unique people that a certain advertisement was shown to, etc. This disclosure describes a practical cardinality estimator that uses O(m + log log N) space and has a conjectured O(1/sqrt(m)) relative error, where m is an accuracy parameter and N is the maximum cardinality that …

Monitor Color Matching, Hp Inc

Defensive Publications Series

Color matching between two or more monitors is achieved without the use of a

host computer by a main monitor retrieving, at power-up, color information from daisychained

monitors, comparing the retrieved data to its own color data, determining needed

color adjustments, and commanding the main and/or daisy-chained monitors to perform

the applicable color adjustments.

Service Category System In Low-Power And Lossy Networks, Caijun Jiang, Xiao Xu, Xiaopu Zhang, Dapeng Zhu

Defensive Publications Series

Presented herein are novel techniques to resolve cache capacity issues in Low-Power and Lossy Networks (LLNs) by utilizing border router edge computing. Following deployment of a network, such as an information-centric networking (ICN) network, a border router will generate a bitmap for all support services through negotiations with a cloud service (CS) and low-power devices. The border router will then cache data that satisfies specific service criteria for low-power devices that have registered for such data. The border router will further publish the service bitmap to a sleep proxy. A given low-power device can periodically examine the service bitmap via …

Automatically Generating Variant Queries Of An Input Query Based On Input Mode, Matthew Sharifi, Victor Carbune

Defensive Publications Series

This disclosure describes techniques for translating an input query provided to a digital assistant to equivalent queries having a different input mode than the input query, such as typed or spoken input mode. A query provided by the user in one input mode is translated to variants for one or more other input modes based on grammars, user-permitted query logs, and/or machine learning models. Components of the digital assistant are updated with both the query and the equivalent query. The described techniques can be used to adapt digital assistant speech recognition and query response generation based on previous user queries, …

Adaptive Summarization Of Digital Assistant Responses To User Queries, Matthew Sharifi, Victor Carbune

Defensive Publications Series

This disclosure describes techniques for performing adaptive summarization of responses provided by a digital assistant to a user’s queries based on explicit and/or implicit feedback from the user that is indicative of their engagement with given responses. The feedback is determined based on user-permitted data from device sensors. If the user permits, past reactions of the user to output responses are used to train machine learning models or heuristics/rules that are used to determine the length of a query response appropriate for the user. Described features enable a digital assistant to automatically match the response length (duration) to the user’s …

Improving Malware Detection By Parsing Broken Code, Abhay Garg, Alexandre Ginet, Arijit De, Paneendra Ba, Yu Zhou

Defensive Publications Series

Spreadsheets, word processors, and other document editing applications enable users to write scripts or macros that automate a sequence of actions, e.g., keystrokes, mouse-clicks, etc. through code. Although macros can improve user efficiency by automating repetitive actions, executable code within a document can also potentially include malware. Macro-based malware is known to intentionally use broken syntax to bypass detection. This disclosure describes a parser that is resilient to syntax errors in code, and which can, by applying local corrections, continue to parse the rest of the code after encountering a parse error. Once corrected, the code can be subject to …

Edlab: A Benchmark Tool For Edge Deep Learning Accelerators, Hp Inc

Defensive Publications Series

Plenty of edge deep learning accelerators are proposed to speed up the inference of deep learning algorithms on edge devices. However, Various edge deep learning accelerators feature different characteristics in terms of power and performance, which makes it a very challenging task to compare different accelerators according to their specifications and in turn prohibits a new DL model from being effectively and efficiently deployed on a suitable edge device. We introduce EDLAB, an edge deep learning accelerator benchmark tool, to evaluate the overall performance of edge deep learning accelerators. EDLAB is an end-to-end benchmark tool that provides unified workloads, deployment …

Virtual Printing Expert Bot And Avatar System, Hp Inc

Defensive Publications Series

Digital printing presses are very sophisticated and consist of many features. As such, they are not easy to

operate. A virtual printing expert system was designed in order to assists the press operators personally,

and make their printing experience easy, smooth and fun, while ensuring high quality prints with high

utilization.

The system consists of a virtual figure, with: “eyes” (video camera), “voice” (speaker) “ears”

(microphone), “brain” (analytics engine, Deep Learning models, cloud and on-premise AI services) and

personality.

Like a human, the virtual expert can talk & listen, write & read, watch, recognize, ask & answer

questions, tip, direct …

Root Cause Identification, John Garrett, Fang Chen, Adrian Bjune

Defensive Publications Series

Presented herein is a novel machine learning approach that learns the failure patterns of a device and uses this information to drive automatic root case identification. Anomalous events can be associated with potential root causes in order to build intellectual capital for training future predictive automated remediation systems.

Sensemaking For Broad Topics Via Automated Extraction And Recursive Search, Alankar Jain, William M Leszczuk, Sitaram Iyer, Mehrbod Sharifi, Seher Aylin Altiok

Defensive Publications Series

The availability of vast amounts of diverse information related to a broad topic makes it difficult and time-consuming for users to find and digest the right information regarding various low-level topics within the broader space. Current approaches to addressing these challenges include providing curated topical pages, relevant query refinement suggestions, list of subtopics, etc. However, these approaches do not scale and offer inadequate support for sensemaking. This disclosure describes automated techniques that extract information from online information sources by using a query related to a high-level topic to recursively formulate additional queries for subtopics to construct a hierarchical set of …

Method To Secure Telemetry Logs In A Multi-Tenant Environment, Robert Barton, Vinay Saini, Cesar Obediente, Jerome Henry, Amit Singh

Defensive Publications Series

Modern service/hosting models utilize the concept of a multi-tenant infrastructure to share common network services while providing secure logical network segmentation between tenant customers. An on-going problem with network telemetry tools in multi-tenant and shared environments is that often they do not provide data confidentiality between tenants. Presented herein are techniques in which an access policy to telemetry logs can be generated in a multi-tenant environment through the use of role-based policy tokens that are attached to log entries as they are received at a collector.

Small Form Factor Wide Field Of View Augmented Reality Head Mounted Display, Punarjeewa Abeysekera

Defensive Publications Series

In this disclosure, a method to create a wide field of view augmented reality head-mounted display which has a small form factor is disclosed. Two transparent video displays are used as a front-facing main display and two other transparent video displays are used from the left and right sides of the front-facing main display slightly tilted. A beam splitter is used to combine the real-world view and the computer-generated view. Two overhead displays are used with two convex lenses to project two images into the beam splitter. The result is a small form factor augmented reality head-mounted display with a …

Identity And Reputation Verification Via Social Vouching, N/A

Defensive Publications Series

Businesses, governments, and other entities verify the identity of customers in order to assess their trustworthiness and to avoid potential losses. Identity is often determined by confirming the ownership of an identifier, e.g., phone number. However, successfully determining an individual’s ownership of an identifier is insufficient to assess the reputation or trustworthiness of the individual. This disclosure describes the use of social graphs to robustly determine the identity and trustworthiness of an individual via their associations with other individuals or entities. Data from individuals associated with a potential customer are utilized, with permission from respective users, for the purpose of …

Edge Intelligence-Based Self-Healing Network For Large-Scale Low Power And Lossy Network Devices With Ioc, Lele Zhang, Li Zhao, Akram Sheriff, Chuanwei Li, Arvind Tiwari

Defensive Publications Series

Techniques are presented herein that support the derivation, leveraging machine learning (ML) algorithms, of a cross correlation index of Key Performance Indicators (KPIs) – specific to wireless technologies such as, for example, Internet Protocol version 6 (IPv6) over Networks of Resource-constrained Nodes (6Lo), Wi-Fi, and Institute of Electrical and Electronics Engineers (IEEE) technical standard 802.15.4 variants – across multiple tenants within a cloud native multi-tenanted environment to proactively optimize routing performance and identify performance optimizations so that the network may be automatically self-healed. Aspects of the presented techniques provide intelligent fault management capabilities for a customer (having, for example, outdoor …

Real-Time Updates For Earthquake Events Based On User Queries, Avi Rosenschein, Mor Schlesinger, Arbel Zinger, Dor Graidy, Itai Tzur

Defensive Publications Series

This disclosure describes techniques for generation of timely earthquake alerts based on crowdsourced user search queries that are posed in near real-time to an earthquake event. With user permission, user intent about a search query is determined based on search query keywords entered by a user. If it is determined that the user likely felt an earthquake, the user is served with a yes/no question asking whether they felt shaking. User responses from multiple users and/or other indicators such as analysis of device IMU data, social media posts, etc. are aggregated and analyzed to determine whether an earthquake event has …

Picking Best Suited Smart Device To Provide Response To A Query, Michael Schäer, Agoston Weisz, Vitaly Gatsko

Defensive Publications Series

Users can issue commands, e.g., spoken commands, to virtual assistants available on various smart devices that have different capabilities. Responses to different types of queries may be best served on specific device types. This disclosure describes techniques to provide responses to a user query, e.g., a spoken query to a virtual assistant, via an automatically selected device from available user devices. Such selection can be based on explicit user preferences or can be based on user-permitted data, as well as be based on the type of query. Implementation of the described techniques can provide an enhanced user experience of interaction …

Critical User Journey Test Coverage, Carlos Arguelles, Tylor Sampson, Joseph Kubik, Erez Bibi

Defensive Publications Series

In the space of software testing, making sure that all critical user scenarios or journeys (CUJs) in a product have been tested is important. A CUJ is essentially a series of steps in the product taken by users of the product to achieve a desired outcome. Ensuring CUJ coverage during testing is a difficult problem that often requires subject matter experts to identify critical scenarios and expensive manual efforts to track coverage. This disclosure describes automatic extraction of CUJs based on analysis of test logs and production logs, e.g., traffic logs at a website. Data mining techniques are applied to …

Techniques To Enable Time Of Day Loading In Pluggable Optics Based On Obtaining A 1pps Signal Utilizing A Repurposed Pin For An Optical Connector, Raghupathi S, Manoj Kumar, Prashant Anand

Defensive Publications Series

Obtaining a 1 Pulse Per Second (1PPS) signal is essential for delivering latency and jitter sensitive applications over a packet network through pluggable optics based on a disaggregated solution that may be applicable to service provider (SP) routing and/or server products for various applications. Techniques are presented herein that enable a 1PPS signal to be provided from a network router to an enhanced Small Form Factor Pluggable (SFP+) device by re-purposing an existing pin of an SFP+ connector for the SFP+ device.

In-Vehicle Ultrasonic Monitoring System, D. Shin, Jian Guo, Wei Li

Defensive Publications Series

An in-vehicle monitoring system may use various vehicle speakers and various microphones to determine the presence and location of occupants within a vehicle (e.g., an automobile, a motorcycle, a bus, a recreational vehicle (RV), a semi-trailer truck, a tractor or other type of farm equipment, a train, a plane, a boat, a helicopter, a personal transport vehicle, etc.) using ultrasonic sound frequencies. The in-vehicle monitoring system may include a vehicle head unit, audio system, or other device, which may in turn cause vehicle speakers, such as one or more speakers built into the vehicle, other speakers located within the vehicle, …