In the realm of business automation, digital assistants/chatbots are emerging as the primary method for making automation software accessible to users in various business sectors. Access to automation primarily occurs through APIs and RPAs. To effectively convert APIs and RPAs into chatbots on a larger scale, it is crucial to establish an automated process for generating data and training models that can recognize user intentions, identify questions for conversational slot filling, and provide recommendations for subsequent actions. In this paper, we present a technique for enhancing and generating natural language conversational artifacts from API specifications using large language models (LLMs). The goal is to utilize LLMs in the "build" phase to assist humans in creating skills for digital assistants. As a result, the system doesn't need to rely on LLMs during conversations with business users, leading to efficient deployment. Experimental results highlight the effectiveness of our proposed approach. Our system is deployed in the IBM Watson Orchestrate product for general availability.

Process automation has evolved from end-to-end automation of repetitive process branches to hybrid automation where bots perform some activities and humans serve other activities. In the context of knowledge-intensive processes such as IT operations, implementing hybrid automation is a natural choice where robots can perform certain mundane functions, with humans taking over the decision of when and which IT systems need to act. Recently, ChatOps, which refers to conversation-driven collaboration for IT operations, has rapidly accelerated efficiency by providing a cross-organization and cross-domain platform to resolve and manage issues as soon as possible. Hence, providing a natural language interface to bots is a logical progression to enable collaboration between humans and bots. This work presents a no-code approach to provide a conversational interface that enables human workers to collaborate with bots executing automation scripts. The bots identify the intent of users' requests and automatically orchestrate one or more relevant automation tasks to serve the request. We further detail our process of mining the conversations between humans and bots to monitor performance and identify the scope for improvement in service quality.

Accounts Payable (AP) is a resource-intensive business process in large enterprises for paying vendors within contractual payment deadlines for goods and services procured from them. There are multiple verifications before payment to the supplier/vendor. After the validations, the invoice flows through several steps such as vendor identification, line-item matching for Purchase order (PO) based invoices, Accounting Code identification for Non- Purchase order (Non-PO) based invoices, tax code identification, etc. Currently, each of these steps is mostly manual and cumbersome making it labor-intensive, error-prone, and requiring constant training of agents. Automatically processing these invoices for payment without any manual intervention is quite difficult. To tackle this challenge, we have developed an automated end-to-end invoice processing system using AI-based modules for multiple steps of the invoice processing pipeline. It can be configured to an individual client’s requirements with minimal effort. Currently, the system is deployed in production for two clients. It has successfully processed around ~80k invoices out of which 76% invoices were processed with low or no manual intervention.

Business processes in workflows comprise of an ordered sequence of tasks and decisions to accomplish certain business goals. Each decision point requires the input of a decision-maker to distill complex case information and make an optimal decision given their experience, organizational policy, and external contexts. Overlooking some of the essential factors or lack of knowledge can impact the throughput and business outcomes. Therefore, we propose an end-to-end automated decision support system with explanation for business processes. The system uses the proposed process-aware feature engineering methodology that extracts features from process and business data attributes. The system helps a decision-maker to make quick and quality decisions by predicting the decision and providing an explanation of the factors which led to the prediction. We provide offline and online training methods robust to data drift that can also incorporate user feedback. The system also support predictions with live instance data i.e., allow decision-makers to conduct trials on current data instance by modifying its business data attribute values. We evaluate our system on real-world and synthetic datasets and benchmark the performance, achieving an average of 15% improvement over baselines.

Accounts payable refer to the practice where organizations procure goods and services on credit which need to be reimbursed to the vendors in due time. Once the vendor raises an invoice, it undergoes through a complex process before the final payment. In this process, tax code determination is one of the most challenging steps, which determines the tax to be levied and directly influences the amount payable to a vendor. This step is also very important from a regulatory compliance standpoint. However, it is error-prone, labor (resource) intensive, and needs regular training of the resources as it is done manually. Further, an error in the tax code determination induces penalties on the organization. Automatically arriving at a tax-code for a given product accurately and efficiently is a daunting task. To address this problem, we present an automated end-to-end system for tax code determination which can either be used as a standalone application or can be integrated into an existing invoice processing workflow. The proposed system determines the most relevant tax code for an invoice using attributes such as item description, vendor details, shipping and delivery location. The system has been deployed in production for a multinational consumer goods company for more than 6 months. It has already processed more than 22k items with an accuracy of more than 94% and high confidence prediction accuracy of around 99.54%. Using this system, approximately 73% of all the invoices require no human intervention.

Question answering is one of the primary challenges of natural language understanding. In realizing such a system, providing complex long answers to questions is a challenging task as opposed to factoid answering as the former needs context disambiguation. The different methods explored in the literature can be broadly classified into three categories namely: 1) classification based, 2) knowledge graph based and 3) retrieval based. Individually, none of them address the need of an enterprise wide assistance system for an IT support and maintenance domain. In this domain, the variance of answers is large ranging from factoid to structured operating procedures; the knowledge is present across heterogeneous data sources like application specific documentation, ticket management systems and any single technique for a general purpose assistance is unable to scale for such a landscape. To address this, we have built a cognitive platform with capabilities adopted for this domain. Further, we have built a general purpose question answering system leveraging the platform that can be instantiated for multiple products, technologies in the support domain. The system uses a novel hybrid answering model that orchestrates across a deep learning classifier, a knowledge graph based context disambiguation module and a sophisticated bag-of-words search system. This orchestration performs context switching for a provided question and also does a smooth hand-off of the question to a human expert if none of the automated techniques can provide a confident answer. This system has been deployed across 675 internal enterprise IT support and maintenance projects.

Location awareness of people inside commercial establishments can help with occupancy-based dynamic energy management and indoor navigation. In this paper, we propose MobiCeil, a novel phone-based indoor localization technique. The proposed technique is offline, automated, and uses image captured from phone's camera to identify the unique ceiling structure of any particular location in the office building. The proposed method is based on these assumptions: (a) in office, employees tend to keep their phones lying on the table, and (b) the layout of ceiling landmarks in a portion of the ceiling structure (as captured by the phone's camera on the table) is unique. We validated these assumptions by checking the phone placement of 47 employees randomly at their cubicle or meeting room, and collecting ceiling layout data from 18 meeting rooms and 6 cubicles in an IT office building. To evaluate the performance of MobiCeil, we collected images of the ceiling as seen by the phone (front and back) camera in three different rotations of the phone placed on the table, to capture a total of 960 ceiling images. Our approach achieved an accuracy of 88.2% for identifying locations, with a low computation time of 2.8s per image.

In this paper, we study the retiming problem of sequential circuits with net topology optimization. Both interconnect and gate delay are considered in retiming. Most previous retiming algorithms have assumed ideal conditions for the nonlogical portions of data paths, which are not sufficiently accurate to be used in high-performance circuits today. In our modeling, we assume that the delay of a wire is directly proportional to its length. This assumption is reasonable since the quadratic component of a wire delay is significantly smaller than its linear component when the more accurate Elmore delay model is used. A simple experiment was conducted to illustrate the validity of this assumption. We present two approaches to solve the retiming problem, both of which have polynomial time complexity. The first one can compute the optimal clock period, while the second one is an improvement over the first one in terms of practical applicability. The second approach gives solutions that are very close to the optimal (0.06% more than the optimal on average) but in a much shorter runtime. The optimally retimed circuit will then be realized physically by placing the registers and finding the net topologies. In contrast to many previous works [Proc. IEEE Int. Conf. Comput.-Aided Des., p. 136, 1998], [IEEE Trans. Comput.-Aided Design Integr. Circuits Syst., 22(7) Jul. 2003] that performed simple calculations to determine the register positions, our approach can preserve the optimal clock period that is obtained by the retiming step and utilize as few registers as possible. Minimization of register number saves both area and power in register and clock loading. Our topology optimization step is shown to be optimal for nets with four or fewer pins, and this type of nets constitutes over 90% of the nets in a sequential circuit on average. Using the ISCAS89 benchmark, we tested our algorithm with a 0.35-mum complementary metal-oxide-semiconductor standard cell library. Silicon Ensemble was used to layout the design with a row utilization of 50%. Experimental results showed that our algorithm could find the best sharing of registers for a net in most of the cases, i.e., using the minimum number of registers while preserving the target clock period that is obtained by the retiming step, within a minute run on an Intel Pentium IV 1.5 GHz PC with 512 MB RAM.

In this paper, we propose a fast algorithm to construct a performance-driven routing tree with simultaneous buffer insertion and wire sizing in the presence of wire and buffer obstacles. Recently, several algorithms have been published addressing the routing tree construction problem. However, all these algorithms are slow and not scalable. In this paper, we propose an algorithm which is fast and scalable with problem size. The main idea of our approach is to specify some important high-level features of the whole routing tree so that it can be broken down into several components. We apply stochastic search to find the best specification. Since we need very few high-level features, the size of stochastic search space is small and can be searched in very little time. The solutions for the components are either pre-generated and stored in lookup tables, or generated by extremely fast algorithms whenever needed. Since it is efficient to obtain solutions for components, it is also efficient to construct and evaluate the whole routing tree for each specification. Experimental results show that, for trees of moderate size, our algorithm out performs the previous algorithms in both quality and runtime.