Abstract: Methods and systems are provided for blockchain-based social media commerce referral tracking system (BRTS). In one novel aspect, the blockchain is used to support traceability and transparency for the referral tracking system that monitors transactions of one or more user generated contents (UGCs) with one or more actionable items. Traceability and transparency foster trust among participants. In one embodiment, the BRTS tracks transactions of a UGC, updates a UGC record upon detecting one or more predefined transactions at a receiving node, detects one or more exit transactions at an ending node, and adds a UGC tuple of transactions from the originator node to the ending node based on the UGC record to a blockchain database upon detecting the one or more exit conditions. In another embodiment, the UGC record is updated using a recursive push procedure. In one embodiment, the BRTS generates one or more referral rewards for each UGC tuple record based on a configured rewarding scheme.

Abstract: A body of knowledge (BOK) in graphical structure is generated with a set of knowlets. The graphical BOK enables the platform to write up test questions with a RNN NLP writing system in runtime to support the adaptive recruitment process. In one embodiment, the system identifies a BOK with a graphical structure with a set of knowlets. Each knowlet represents a subset of knowledge within the BOK. The system identifies a set of intensional knowlets for the BOK, collects a set of extensional knowlets for the BOK, wherein an extensional knowlet represents the instantiation of an intensional knowlet, generates a BOK graph for the BOK with based on the set of intensional knowlets and the set of the extensional knowlets with each knowlet being a node of the BOK graph, wherein ontologies among knowlet nodes are generated, and generates a list of test questions based on the BOK graph.

Abstract: Methods and systems are provided for AI-based robotic automation for persuasive references. In one novel aspect, a robotic persuasive reference is generated based on a prospect product-service (P_PS) matrix, which is generated based on predictive analysis using DNN model and dynamically obtained feedbacks. In one embodiment, the DNN model is trained with customer personal profiles against associated PS revenues for each customer data set. In one embodiment, the predictive analysis uses a decision tree classifier. In one embodiment, the computer system detects one or more predefined triggering events comprising feedback information for the robotic persuasive reference and one or more predefined lifetime events, updates the P_PS matrix based and the robotic persuasive reference accordingly. In one embodiment, the feedback information is a sentiment analysis on responses from the prospect.

Abstract: Methods and systems are provided for blockchain-based social media commerce referral tracking system (BRTS). In one novel aspect, the blockchain is used to support traceability and transparency for the referral tracking system that monitors transactions of one or more user generated contents (UGCs) with one or more actionable items. Traceability and transparency foster trust among participants. In one embodiment, the BRTS tracks transactions of a UGC, updates a UGC record upon detecting one or more predefined transactions at a receiving node, detects one or more exit transactions at an ending node, and adds a UGC tuple of transactions from the originator node to the ending node based on the UGC record to a blockchain database upon detecting the one or more exit conditions. In another embodiment, the UGC record is updated using a recursive push procedure. In one embodiment, the BRTS generates one or more referral rewards for each UGC tuple record based on a configured rewarding scheme.

Abstract: Methods and systems are provided for blockchain-based social media commerce referral tracking system (BRTS). In one novel aspect, the blockchain is used to support traceability and transparency for the referral tracking system that monitors transactions of one or more user generated contents (UGCs) with one or more actionable items. Traceability and transparency foster trust among participants. In one embodiment, the BRTS tracks transactions of a UGC, updates a UGC record upon detecting one or more predefined transactions at a receiving node, detects one or more exit transactions at an ending node, and adds a UGC tuple of transactions from the originator node to the ending node based on the UGC record to a blockchain database upon detecting the one or more exit conditions. In another embodiment, the UGC record is updated using a recursive push procedure. In one embodiment, the BRTS generates one or more referral rewards for each UGC tuple record based on a configured rewarding scheme.

Abstract: Customer lifetime value (CLV)-base deep learning ensemble model for customer classification and multi-entity matching strategies is provided. In one novel aspect, the customer lifetime value (CLV)-base deep learning model (DNN) uses data mining and an ensemble of the recurrent neural network (RNN)-convolutional neural network (CNN) to identify potential prospects from lead generation, predicts churn/retention, predicts the next purchase, recommend strategies to keep and enhance existing customer relationships, and offer n-ary matching among prospects/customers, agents, products, and delivery strategies. In one embodiment, the CLV system obtains a CLV profile of a customer, generates, a CLV-based output for the customer using a DNN model, selects a n-ary matching for the customer based on the CLV-based output, and collects a feedback for the n-ary matching to update the n-nary matching until one or more exit conditions are met.

Abstract: Methods and systems are provided for blockchain-based social media commerce referral tracking system (BRTS). In one novel aspect, the blockchain is used to support traceability and transparency for the referral tracking system that monitors transactions of one or more user generated contents (UGCs) with one or more actionable items. Traceability and transparency foster trust among participants. In one embodiment, the BRTS tracks transactions of a UGC, updates a UGC record upon detecting one or more predefined transactions at a receiving node, detects one or more exit transactions at an ending node, and adds a UGC tuple of transactions from the originator node to the ending node based on the UGC record to a blockchain database upon detecting the one or more exit conditions. In another embodiment, the UGC record is updated using a recursive push procedure. In one embodiment, the BRTS generates one or more referral rewards for each UGC tuple record based on a configured rewarding scheme.

Abstract: Methods and systems are provided for blockchain-based credential vault system (CVS). In one novel aspect, the CVS identifies a set of credential of a trustor, verifies each credential, and stores the verified credentials to a CVS blockchain database such that the authorized beneficiary can obtain the trustor credentials from the CVS. In one embodiment, the CVS authenticates a trustor request from a trustor, wherein a trustor record in the CVS is uniquely identified by a trustor identification in a blockchain-based database of the CVS, processes submission from the authenticated trustor to generate a set of canonical credentials using a recurrent neural network (RNN) model, performs credential verification for each generated canonical credential in the authenticated trustor submission, and appends each verified canonical credential to the trustor record in the blockchain-based database of the CVS.

Abstract: Methods and systems are provided for the AI-based computer-aided persuasion system (CAPS). The CAPS obtains inputs from both the target and the agent for an object, dynamically generates persuasion references based on analysis of the input. The CAPS obtains content output by analyzing the agent audio stream and the target audio stream using a recurrent network (RNN) model, obtains sentiment classifiers based on a convolutional neural network (CNN LSTM) model, updates a conversation matrix, and generates a persuasion reference based on the updated conversation matrix. The persuasion reference is based on an acceptance likelihood result generated from the conversation matrix using the RNN model. The CAPS further generates a target profile using DNN (deep neural net) with input of target Big Data, wherein the target profile includes one or more objects, and wherein the agent is selected based on the generated profile and one or more selected objects.

Abstract: Methods and system are provided for multi-channel video stream summarization in real time. In one novel aspect, live video streams of objects of interest are transmitted on CDN channels associated with corresponding object of interest. In one embodiment, a plurality of CDN channels is created for a plurality of corresponding objects of interest. A sensor signal is received, which associates an identified input live video stream with a monitored object of interest. The identified video stream is transmitted in real time to a corresponding CDN channel associated with the monitored object of interest. The sensor signal is electrical or any type of signal from ID markers attached to the object of interest or is based on a result of real-time image recognition. An alert is generated for a CDN channel upon detecting one or more alerting triggering events.

Abstract: Methods and systems are provided for adaptive recruitment computer system. In one novel aspect, the adaptive recruitment computer system generates a question bank based on a job description, selects adaptively questions from the question bank for an interview, and generates a feedback report for the candidate based on the evaluation of the candidate's answer. In one embodiment, the computer system categorizes a job requirement based on a body of knowledge (BOK) skill knowledge base, generates a question bank, selects adaptively a subset of questions from the generated question bank, wherein each question selected is based on evaluations of candidate's answers to corresponding prior questions using a recurrent neural network (RNN) model, and generates a feedback report for the candidate, wherein the feedback report using the RNN model based on evaluations of answers and a BOK candidate knowledge base, wherein the BOK candidate knowledge base receives updates from the computer system.

Abstract: Methods and systems are provided for AI-based robotic automation for persuasive references. In one novel aspect, a robotic persuasive reference is generated based on a prospect product-service (P_PS) matrix, which is generated based on predictive analysis using DNN model and dynamically obtained feedbacks. In one embodiment, the DNN model is trained with customer personal profiles against associated PS revenues for each customer data set. In one embodiment, the predictive analysis uses a decision tree classifier. In one embodiment, the computer system detects one or more predefined triggering events comprising feedback information for the robotic persuasive reference and one or more predefined lifetime events, updates the P_PS matrix based and the robotic persuasive reference accordingly. In one embodiment, the feedback information is a sentiment analysis on responses from the prospect.

Abstract: Methods and systems are provided for skill-based/JHE credential verification using robotic contact and analysis, social media search, and/or peer affirmation within a blockchain-based database that holds verified trustor records. In one embodiment, a credential vault system (CVS) identifies a set of skill-based canonical JHEs for a trustor based on a description of job history and experience (JHE) of the trustor using a recurrent neural network (RNN) model with natural language process/natural language understanding (NLP/NLU), wherein a trustor record in the CVS is uniquely identified by a trustor identification in a blockchain-based database of the CVS, collects one or more corroborations for each canonical JHE by the CVS, evaluates each canonical JHE based on the collected one or more corroborations using a deep learning model to verify the corresponding canonical JHE, and appends each verified canonical JHE to the trustor record in a blockchain-based database of the CVS.

Abstract: Methods and systems are provided for the AI-based computer-aided persuasion system (CAPS). The CAPS obtains inputs from both the target and the agent for an object, dynamically generates persuasion references based on analysis of the input. The CAPS obtains content output by analyzing the agent audio stream and the target audio stream using a recurrent network (RNN) model, obtains sentiment classifiers based on a convolutional neural network (CNN) model, updates a conversation matrix, and generates a persuasion reference based on the updated conversation matrix. The persuasion reference is based on an acceptance likelihood result generated from the conversation matrix using the RNN model. The CAPS further generates a target profile using CNN with input of target Big Data, wherein the target profile includes one or more objects, and wherein the agent is selected based on the generated profile and one or more selected objects.

Abstract: Methods and systems are provided for adaptive recruitment computer system. In one novel aspect, the adaptive recruitment computer system generates a question bank based on a job description, selects adaptively questions from the question bank for an interview, and generates a feedback report for the candidate based on the evaluation of the candidate's answer. In one embodiment, the computer system categorizes a job requirement based on a body of knowledge (BOK) skill knowledge base, generates a question bank, selects adaptively a subset of questions from the generated question bank, wherein each question selected is based on evaluations of candidate's answers to corresponding prior questions using a recurrent neural network (RNN) model, and generates a feedback report for the candidate, wherein the feedback report using the RNN model based on evaluations of answers and a BOK candidate knowledge base, wherein the BOK candidate knowledge base receives updates from the computer system.

Abstract: Methods and system are provided for tagging scheme for blockchain-based provenance system. In one novel aspect, a unique signature is created based on a polygonized unique object ID. The polygonized unique ID is randomly placed in an authentication area of an ID tag, where vertex coordinates of the ID polygon can be obtained. The signature information of the authentication area of the ID tag is recorded in blockchain. New ID polygons are associated with the tagged object in one or more ID tags. The new authentication area or the newly updated authentication area are appended to the blockchain. In one embodiment, the ID polygon is obtained by polygonizing the associated unique operator ID. In another embodiment, the ID polygon is an ID code of the associated unique operator ID superposed on a predefined polygon, and wherein the ID code is one of a QR code and a bar code.

Abstract: Methods and systems are provided for speech emotion recognition interview process. In one novel aspect, in addition to contents assessment to an answer audio clip, the concurrent sentiment classifier is generated based on emotion classifier of the answer audio clip. In one embodiment, the computer system obtains a sentiment classifier of an audio clip of a first answer to the first question, wherein the sentiment classifier is derived from an emotion classifier resulting from a convolutional neural network (CNN) model analysis of the audio clip; obtains an assessment result to the first question by analyzing the audio clip of the first answer to the first question using a recurrent neural network (RNN) model; and generates a first emotion response result to the first question based on the sentiment classifier and the assessment result, wherein the first emotion response result presents a sampling experience factor to the response assessment result.

Abstract: A method for preparing a purple sweet potato concentrate that is free from starch, rich in anthocyanins, phenolic compounds, minerals, and soluble dietary fiber with low viscosity, attractive color, and with natural sweetness is presented. The method first prepares and liquefies the purple sweet potatoes and fixes the colorization by adjusting the pH value. Next, amylase and an enzyme complex of hemicellulase, pectinase, cellulase, glucoamylase and protease are added in sequence under conditions effective to produce the juice with the above mentioned properties. The juice is then centrifuged and membrane-filtered to produce a purified purple sweet potato juice which is vacuum-concentrated to yield a purple sweet potato concentrate. Purple sweet potato powder can be obtained by vacuum drying the sediment and concentrate mixture.