Abstract: Forecasting solutions including customization of raw data using uncertainty coefficient and using ensemble neural network architecture. The raw data is customized by cleaning and augmenting to obtain a processed dataset that is non-discreet and continuous, and; the ensemble neural network architecture is customized to include plurality of dependent and independent features to obtain ensembled weights from ensemble recurrent neural network (RNN) type architecture, a one versus rest ensemble RNN architecture and a forest of ensemble, to obtain an appropriate forecasting model that includes dynamically adaptive weights from ground truth along with the ensembled weights to create a final weighted output such that the final weighted output/forecast result has more accuracy and reduced false positives. The present invention allows for feedback mechanism from disruptive forecasting results if any from query module to go back to training module that enhances the accuracy of the next result without re-training.

Abstract: A computer implemented method to identify and extract tables from semi structured documents with training mechanism and machine learning models, both in online and offline mode. The method comprises the steps of: extracting all relevant label-value pairs in said semi-structured document, computing dynamic split constants between the labels and values, merging all the identified labels and values to form lines by chaining, identifying cells based on moving average based split identification, generating cell mask and line mask based on the datatype pattern, grouping line masks in cluster lines based on the clustering pattern and grouping parameters, identifying child lines and merging them with the main line, identifying and mapping potential header line amongst the identified line masks in homogenous and non-homogenous table structure and grouping the clustered lines with the nearest header line to identify the table in the semi-structured document.

Abstract: A computer implemented method to identify and extract tables from semi-structured documents without any dependency on training mechanism, both in online and offline mode. The method comprises the steps of: extracting all relevant label-value pairs in said semi-structured document, computing dynamic split constants between the labels and values, merging all the identified labels and values to form lines by chaining, identifying cells based on moving average based split identification, generating cell mask and line mask based on the datatype pattern, grouping line masks in cluster lines based on the clustering pattern and grouping parameters, identifying child lines and merging them with the main line, identifying and mapping potential header line amongst the identified line masks in homogenous and non-homogenous table structure and grouping the clustered lines with the nearest header line to identify the table in the semi-structured document.

Abstract: A system and method for classification of spend data wherein the system comprises a user computer system, a processing unit, a communication interface, a first input receiving component, a second input receiving component, and a spend classification module further comprising a sentence tokenizer, a word tokenizer, a co-reference tagger, at least one language dictionary, and at least one standard taxonomy and/or custom taxonomy, a keyword sense tagger, and a sense scorer, such that the sense scorer further includes a category normalizer matrix, a category summarizer matrix and a heuristic learning matrix; and wherein the method comprises the steps of receiving a dataset of spend data from the user, transmitting the dataset to the spend data classification module, processing of the dataset by the spend data classification module, receiving a query term from the user, mapping the query term, and displaying the data so processed to the user.

Abstract: An invoice payment system involving smart electronic means which is enabled to read, reply, segregate, de-duplicate and appropriately mark undisputed emails with genuine payable invoice for payment; wherein the “payment query” emails are resolved by generating automated replies based on email content; and wherein the emails for payment marked “add invoice” include the steps of: (i) identification and classification of received emails; (ii) eradicating duplicate invoices; (iii) checking dispute if any with associated invoice or supplier; and (iv) if all checks are appropriate, then flagging the email with a green mark for further processing of the invoice by the smart electronic means.

Abstract: A complex sourcing system that collects data from bidders. The information which is collected from the suppliers is interpreted by applying several business constraints including supplier award value criteria, supplier award volume criteria, etc. on it for the selection of an optimal supplier for the allocation of lanes. A user will create a scenario with collection of these business constraints. Once the scenario is created and while solving it, there might be a situation where the specified constraints cannot be satisfied and conflict. At this point, there is a need to identify the root cause of the infeasibility and repair it. For this, a priority of constraints will be provided by the user on scenario creation page. Based on the priority, the solver will auto correct/eliminate the constraints and return the feasible solution along with the set of constraints that are removed.

Abstract: A complex sourcing system enabled to implement different permutations and combinations based on several different business constraints for optimal analysis, sourcing, multi-level negotiation, contracting, procurement and payment. The working of the complex sourcing system includes the steps of: (a) preparing for a bid; (b) creating a bid; (c) executing a bid; (d) selecting an optimal supplier; (e) storing the award and supplier details in the contract management module of the system; and (f) preparing a contract between the buyer and the supplier.

Abstract: An electronic procurement system (2) characterized by the presence of a virtual catalog (12) in addition to the internal hosted catalog (4), wherein the virtual catalog (12) is comprised of a list of items not found in the internal hosted catalog (4) of the electronic procurement system (2), wherein the list of items present in the virtual catalog (12) are fetched from punchout websites (8) connected with the electronic procurement system (2), wherein the process of creation of the virtual catalog (12) is facilitated by a processing means (6) and broadly comprises steps such as data search, data extraction, data storage, data alignment, data collation and data publishing, wherein the data refers to the query item name (3) entered by the requester (1), and wherein the electronic procurement system (2) is easy to use, convenient, efficient, user friendly and eliminates cumbersome data requisition steps.

Abstract: A method of extracting meta-data from semi structured documents, by using area and cone orientation as relevance between words/phrases is described. It also a computer implemented system to handle OCR errors with respect to the coordinates interpreted for each word and user corrections both in online and offline mode. The method is carried out by the steps as follows: converting scanned or digital document to a readable format with coordinates using OCR; scanning the coordinates obtained through OCR for each character; marking all potential labels and values with a bounding box; searching for relevant labels for the particular value by using default control parameters and adjusting trainable parameters; mapping a cone region for the labels and values using the upper and lower angles along x-axis and the scope box and formulating the score area to get the confidence percentage which is used as measure to extract all relevant label-value pairs.

Abstract: A system and method for assisting in negotiations for commercial transactions is described. This computer implemented system and method assists in negotiations with multiple negotiating parties on various parameters to collaboratively come to a conclusion beneficial to the Buyer organization during sourcing event. The system begins by receiving a quote from a negotiating party in the form of a message on a device. The system then prepares to initiate the negotiation response suitable for a particular negotiating party based on various operating parameters such as time parameters, sentiment parameters, item and price parameters, culture parameters and also negotiating party database. Based on all these parameters, the systems prepares a counter negotiation response which is sent to the negotiating party on behalf of the buyer and negotiating party further responds to the message. It provides productive, adaptive, secure and efficient negotiation skills for conducting commercial transactions.

Abstract: A system and method for aggregation of procurement requisitions including tiered pricing module is described in the present invention. The computer implemented system aggregates the approved procurement requisitions in real time from different business departments. They are then kept in a gestation period for channelizing the aggregated quantity of the aggregated requisitions into one common purchase order to avail bulk discounts or to avail tiered pricing discounts from the supplier. Once the aggregation of requisitions is done, accordingly based on the decision rules, the tiered pricing catalogue is triggered to select the right catalogue and the quantity/volume and its related price. If the aggregated requisitions do not match the tiered pricing catalogue then the system directs the user to negotiate discount with the supplier for the requisitions. The user thus avails maximum discounts on the aggregated requisitions.

Abstract: A method of extracting meta-data from semi structured documents, by using area and cone orientation as relevance between words/phrases is described. It also a computer implemented system to handle OCR errors with respect to the coordinates interpreted for each word and user corrections both in online and offline mode. The method is carried out by the steps as follows: converting scanned or digital document to a readable format with coordinates using OCR; scanning the coordinates obtained through OCR for each character; marking all potential labels and values with a bounding box; searching for relevant labels for the particular value by using default control parameters and adjusting trainable parameters; mapping a cone region for the labels and values using the upper and lower angles along x-axis and the scope box and formulating the score area to get the confidence percentage which is used as measure to extract all relevant label-value pairs.

Abstract: Systems, and methods for using same, are described for changing categorization data, in relation to spend analysis reports, in real time. The systems include a processor unit, and a computer readable medium storing instructions executable by the processor unit including a client side processing system adapted to transmit a user generated request for change, in real time, and a server side processing system adapted to receive the transmitted requested change, in real time, for effecting the requested change.

Abstract: A centralized, computer implemented system is provided for request management within an organization, wherein the request management system is capable of performing the following functions: gathering user generated requests; sorting user generated requests; prioritising the requests; transferring the requests to the necessary person/department; updating the requester with the status of the request; linking related documents; matching requests relating to the same and/or similar items; and rejecting requests which are in violation of any pre-configured rules/limits.

Abstract: A system is described for configuring subsets in a Japanese reverse auction. The advantage of the system is that the bidding on a particular auction item does not necessarily have to end, even when there are no bidders at that price. The system provides for a solution that allows the auction to continue by creating subsets on the original auction item or on the price of the original auction item.

Abstract: The present invention describes a system for automated pause of an E-auction process, the said pause triggered based on preconfigured E-auction pause Rule Creation Engine to pause E-auction at least once during the E-auction process. The automated pause of E-auction includes a status wherein the said E-auction is at hold and not ended, once the hold period for the automated pause of the E-auction is over, the said E-auction shall resume.

Abstract: A computer based system and method for contract authoring. The method may receive an external contract document in electronic form, wherein the external contract document comprises a plurality of text portions relating to a plurality of contract component types, respectively. The method may access a knowledge base describing a plurality of text patterns that identify with the plurality of the contract component types, respectively. Moreover, the method may process the external contract document utilizing the knowledge base to automatically identify the plurality of the contract component types for the plurality of the text portions in the contract document, respectively.

Abstract: A computer based system for changing categorization data, in relation to spend analysis reports, in real time, the system comprising a processor unit; and a computer readable medium storing instructions executable by the processor unit comprising a client side processing means adapted to transmit a user generated request for change, in real time and a server side processing means adapted to receive said transmitted requested change, in real time, for effecting said requested change.

Abstract: The present invention provides for a method and system for the classification of electronic catalogs. The method provided has a lot of user-configured features and also provides for constant interaction between the user and the system. The user can provide criteria for the classification of catalogs and subsequently manually check the classified catalogs.

Abstract: A method and system for context based searching of category wise arranged electronic catalog database is provided. The confidence value for each of the retrieved categories is displayed graphically as an indication of the relevance of that category. The percentage impact of each of the query terms on the search result is also shown in a graphical format. Various search strategies and algorithms are used and the output is ranked according to the user relevance. The system is intelligent in the sense that it suggests user with spellings, uses word morphing, synonymous words to user query etc. The user can define weightage to be given to various attributes and also refine his search by searching in particular segments.