Sap Se

Jan Schrage

Changqing Liu

Weicheng Wang

Oleg Bolgarin

Neelesh Kamath

Yalan Gong

Priyanka Porwal

Karthik S

Alexander Bolgarin

Access to blockchain data may be removed by deleting an encryption key held in a remote server. Incoming data is stored in the blockchain after being encrypted at the key server. An ordinary blockchain user gains access to the data, after forwarding the encrypted data to the remote key server for decryption. Upon receipt of an input (e.g., time stamp), the key server deletes the key. Thereafter, the encrypted data on the blockchain is rendered inaccessible to the ordinary blockchain data user. At no point, does the ordinary data user have access to the key stored in the remote server. Embodiments may find particular use in removing access to personal data stored in a blockchain following the elapse of a predetermined amount of time, as may be required by privacy laws. Granular control over data access can may be afforded through the use of composite keys and/or key hierarchies.

Removing access to blockchain data

Search assistance personalized to a user, may be afforded by combining the application of scoring functions, with the training a Machine Learning (ML) model based upon feedback from that user. A plurality of scoring functions are applied to query results to calculate a plurality of score vectors. The ML model is then applied to generate a ranked list of vectors. Feedback from the user, is incorporated to develop an evolving memory. The feedback may be explicit, or may be implicit&#x2014;e.g., based upon user selection of particular score vector(s) from the list or based upon user selection of particular query results corresponding to the score vectors. Embodiments may enhance relevance of search assistance by removing past feedback from the evolving memory that is used to retrain the ML model. Embodiments can provide assistance to search text corpuses utilizing scoring functions considering frequency of occurrence of particular words or terms.

Personalized evolving search assistance

Provided is a system and method for matching documents by line item. In one example, the method may include receiving a target document from a target system and a source document from a source system which are linked, identifying a set of lines in the target document and a set of lines in the source document which cannot be matched based on initial conditions, determining, via a machine learning model, a target line from the identified set of lines in the target document matches a source line from the identified set of lines in the source document based on descriptions included in the target line and the source line, and updating the source system to indicate that the target line from the target document and the source line from the source document are a match.

Line based matching of documents

Systems, methods, and computer media are described for storing and analyzing locally configured data. Both locally configured data and the corresponding data configurations are stored in a distributed storage platform (e.g., a blockchain). Using an accompanying data configuration to interpret and analyze stored data, accurate and meaningful local and global analyses can be performed, across data from different domains, without prior knowledge or external definition of the data. Storage in a distributed storage platform ensures that data cannot be modified and that all transactions are recorded. Example analyses that can be conducted on the stored locally configured data include audits, searching for variances, general queries for data having certain parameters or values, etc.

Blockchain-based analysis of locally configured data

Computer-implemented machine learning (ML)-based techniques for detecting payroll fraud are provided. In one set of embodiments, these techniques employ a number of ML algorithms to evaluate different types of fraud-relevant data in different ways, such as outliers in salary increases, payment patterns, and so on. In some cases, the ML algorithms may be chained such that the output of one ML algorithm feeds as input into another. The results of these ML algorithms (or chains of algorithms) are fed into a neural network-based final evaluation engine that outputs an indication of whether a given employee is suspicious and should be audited as a potential payroll fraud case.

Machine learning-based techniques for detecting payroll fraud

Various embodiments of systems and methods for integrated services for form generation and maintenance on cloud are described herein. The method includes receiving a request for a form-related service from a client. The form-related service may comprise at least one of generating a form, printing the form, extracting one or more form templates, extracting one or more form schemas, and uploading one or more tenant-created form templates onto a cloud template store. The received request is authenticated. Upon a successful authentication, one or more actions may be performed to render an output based upon the request. The output may include one of a form, the one or more form templates, the one or more form schemas, and a notification for successful or unsuccessful uploading of the one or more tenant-created form templates onto the cloud template store. Upon unsuccessful authentication, an error message may be displayed.

Growing community of inventors

Helmstadt-Bargen, Germany

Jan Schrage