Abstract: An example operation may include one or more of acquiring, by a retailer node, an inventory data from a supplier node over a blockchain network, receiving, by the retailer node, outstanding orders data of the supplier node, generating, by the retailer node, an order distribution policy based on the inventory data and the outstanding orders data, and executing a smart contract to order goods from the supplier node based on the ordering policy.

Abstract: An example operation may include one or more of receiving, by a first node, a freshness of goods data from a second node over a blockchain, and executing, by the first node, a smart contract to: calculate an initial order quantity based on a pre-set critical order number and a non-expiring goods order quantity and alter a final order quantity based on the initial order quantity and the freshness of the goods data.

Abstract: An example operation may include one or more of receiving, by a retailer node, an encrypted inventory of goods data from a plurality of supplier nodes over a blockchain network, computing, by the retailer node, an ordering proportion based on the encrypted inventory of goods data, generating, by the retailer node, an ordering policy based on the ordering proportion, and executing a smart contract to order goods from the plurality of the supplier nodes based on the ordering policy.

Abstract: Techniques for mapping policy documents to regulatory documents to check for compliance between the policies and documents are provided. In one example, a computer-implemented method determining, by a system operatively coupled to a processor, an information input, a control framework, and a document from a first group consisting of a regulatory document and a policy document, wherein the information input is a corpora from a second group consisting of a domain corpora and a global corpora. The computer-implemented method can also comprise mapping, by the system, the received regulatory document or the received policy document to the control framework using a supervised machine learning technique.

Abstract: An example operation may include one or more of collecting, by a first node, a plurality of permissioned data inputs from a plurality of second nodes of a supply-chain, performing, by the first node, a granular simulation based on the permissioned data inputs to generate a plurality of key performance indicators (KPIs), and executing a smart contract to adjust order processes of the supply-chain based on the KPIs.

Abstract: An example operation may include one or more of collecting, by a first node, a subset of data inputs from a plurality of second nodes over a blockchain underlying a supply-chain, executing, by the first node, a smart contract to simulate a state of the supply-chain based on the subset of the data inputs, and generating, by the first node, at least one policy decision based on the simulated state of the supply-chain.

Abstract: Techniques for mapping policy documents to regulatory documents to check for compliance between the policies and documents are provided. In one example, a computer-implemented method determining, by a system operatively coupled to a processor, an information input, a control framework, and a document from a first group consisting of a regulatory document and a policy document, wherein the information input is a corpora from a second group consisting of a domain corpora and a global corpora. The computer-implemented method can also comprise mapping, by the system, the received regulatory document or the received policy document to the control framework using a supervised machine learning technique.

Abstract: Techniques for improving products based on data-driven models are provided. In one example, a system comprises a receiving component that receives product data representing information about a set of products, wherein a first product of the set of products comprises a first combination of a first set of ingredients, and wherein the product data comprises product composition data representing a composition of the first product. The system further comprises a learning component that generates product space data representing a product space that characterizes the set of products and respective degrees of similarity between members of the set of products, wherein a degree of similarity between the first product and a second product of the set of products is determined based on product distance data representing a determined distance metric resulting from a comparison of the first set of ingredients to a second set of ingredients combined to produce the second product.

Abstract: An example operation may include one or more of receiving supply chain states of a plurality of nodes of a supply chain, respectively, where the supply chain states have restricted visibility among the plurality of nodes, determining a modification to a supply chain state of a target node in the supply chain based on a supply chain state of at least one other node in the supply chain, transmitting the determined modification of the supply chain state to the target node, and storing a reason for modifying the supply chain state of the target node via a block included among a hash-linked chain of blocks.

Abstract: An example operation may include one or more of receiving a data file submitted by a node, the data file comprising information about an event-driven process for a chain of nodes, retrieving an entitlement mode of the data file from a data block that is stored among a hash-linked chain of data blocks on a distributed ledger, determining access rights of the data file with respect to another node in the chain of nodes based on the retrieved entitlement mode of the data file, and transmitting information about the event-driven process to the other node based on the determined access rights of the other node.

Abstract: Techniques for outside-in mapping for corpus pairs are provided. In one example, a computer-implemented method comprises: inputting first keywords associated with a first domain corpus; extracting a first keyword of the first keywords; inputting second keywords associated with a second domain corpus; generating an embedded representation of the first keyword via a trained model and generating an embedded representation of the second keywords via the trained model; and scoring a joint embedding affinity associated with a joint embedding.

Abstract: Techniques for outside-in mapping for corpus pairs are provided. In one example, a computer-implemented method comprises: inputting first keywords associated with a first domain corpus; extracting a first keyword of the first keywords; inputting second keywords associated with a second domain corpus; generating an embedded representation of the first keyword via a trained model and generating an embedded representation of the second keywords via the trained model; and scoring a joint embedding affinity associated with a joint embedding.

Abstract: A shared ledger of transactions may be used for various purposes and may be later accessed by interested parties for ledger verification. Authenticity of transactions requires active measures to ensure transaction participants including parties to the transactions, observers to the transaction, etc., are providing accurate information for each transaction.

Abstract: A computer system, method, and computer-readable product for automatically generating a hierarchy of concepts described in a video using semantic concept matching that assists persons in searching for specific types of content within videos. A video segment is obtained, with the segment having a distinct running time with discrete information related to one or more topics within its content. The discrete information of the video segment is then parsed out and related to a predetermined relevant topic, and then one or more attributes for weighting each discrete information relevant topic within the video segment are determined. A hierarchy of concepts of the video segments is then created, based upon, at least, the weighting of the information topic within the running time of the video segment based upon the presence of the one or more attributes. Other information related to the video segment can also be used to modify the hierarchy.

Abstract: Techniques for outside-in mapping for corpus pairs are provided. In one example, a computer-implemented method comprises: inputting first keywords associated with a first domain corpus; extracting a first keyword of the first keywords; inputting second keywords associated with a second domain corpus; generating an embedded representation of the first keyword via a trained model and generating an embedded representation of the second keywords via the trained model; and scoring a joint embedding affinity associated with a joint embedding.

Abstract: A computer system, method, and computer-readable product for automatically generating a hierarchy of concepts described in a video using semantic concept matching that assists persons in searching for specific types of content within videos. A video segment is obtained, with the segment having a distinct running time with discrete information related to one or more topics within its content. The discrete information of the video segment is then parsed out and related to a predetermined relevant topic, and then one or more attributes for weighting each discrete information relevant topic within the video segment are determined. A hierarchy of concepts of the video segments is then created, based upon, at least, the weighting of the information topic within the running time of the video segment based upon the presence of the one or more attributes. Other information related to the video segment can also be used to modify the hierarchy.

Abstract: Techniques for outside-in mapping for corpus pairs are provided. In one example, a computer-implemented method comprises: inputting first keywords associated with a first domain corpus; extracting a first keyword of the first keywords; inputting second keywords associated with a second domain corpus; generating an embedded representation of the first keyword via a trained model and generating an embedded representation of the second keywords via the trained model; and scoring a joint embedding affinity associated with a joint embedding.

Abstract: An example operation may include one or more of generating a hashed summary including hashes of one or more of a validation data set and hashes of data points chosen in previous iterations from producer nodes, and exposing the hashed summary to a plurality of producer nodes, receiving, iteratively, a plurality of requests from the plurality of producer nodes, respectively, where each request identifies a marginal value provided by a hash of a data sample available to a producer node, selecting a request received from a producer node based on a marginal value associated with the request, retrieving hashed data of the producer node associated with the selected request, and aggregating the hashed data of the producer node with the summary of hashes generated at one or more previous iterations to produce an updated summary, and storing the updated summary via a data block of a distributed ledger.

Abstract: An example operation may include one or more of partitioning a data set from a data provider into a training data set and a test data set, exposing the training data set to a learning service provider while preventing the learning service provider from being able to access the test data set, wherein the preventing comprises encrypting the test data set and storing the encrypted test data set in an immutable ledger, receiving a learning model that is generated by the learning service provider based on the exposed training data set, executing the received learning model using the test data set as input to verify whether the learning model satisfies a predefined performance threshold, and in response to verifying the learning model satisfies the predefined performance threshold, outputting information about the verification to a computing node.

Abstract: A system and method dynamically provisions resources in a virtual environment. A current resource requirement is determined based on a current workload demand using one or more computer systems providing resources and access to the resources. The method and system includes comparing the current resource requirement with a current resource allocation using an engine communicating with resources. The engine is configured to allocate the resources, and the engine determines the resource requirement responsive to communications with a plurality of library instances. The library exposes a single-node interface for use by a user-application. The current resource allocation is modified based on the comparison of the current resource requirement with the current resource allocation, and in response to the current resource requirement, using the engine.