Computer implemented reconstruction of compliance mapping due to an update in a regulation in the compliance mapping by a computing device includes comparing a first version of a regulation in the compliance mapping to a second, updated version of the first regulation. A change in the second version with respect to the first version is identified. The change may be an added control description, a deleted control description, or an updated control description. Upon determining that the change is an updated control description, the updated control description is analyzed to determine a type of update. The mapping of the regulation is reconstructed based on the change and, if the change is an updated control description, the type of update, using at least one of natural language processing and/or machine learning. The risk of the reconstructed mapping is assessed, and a service owner is notified about the risk of the changes.

Techniques for targeted partial re-enrichment include determining that at least one natural language processing (NLP) request is associated with at least one surface form, the NLP request being for a corpus, a database comprising preexisting annotations associated with the corpus. An index query related to the at least one surface form is performed to generate index query results, the index query results including identification of portions of the corpus affected by the NLP request. A scope of the NLP request related to the database is determined based on the index query results, the scope including identification of impacted candidate annotations of the preexisting annotations affected by the NLP request. An NLP service is performed on the corpus according to the scope and the portions, thereby resulting in updates. The updates are committed to the database associated with the corpus.

Data warehousing solutions utilize lengthy and complex SQL instructions. These SQL instructions are difficult to parse and understand underlying logic/transformations performed. Conventionally, extensive analysis, time and effort needs to be spent to understand such SQL instructions and detect any data abnormalities in the SQL instructions. This technical challenge is exacerbated in high-volume production systems that include multiple systems that each utilize their own sets of SQL instructions. Apparatus and methods described herein take as input a natural language inquiry received from a user. The system attempts to parse the natural language inquiry to identify one or more relevant SQL instructions. Apparatus and methods may utilize AI and natural language processing to locate relevant SQL instructions, deconstruct them into subqueries and map a logical operational flow. Based on the mapped logic flow, a natural language response may be formulated to the user inquiry.

Methods, systems, and devices for generating a unique resource identifier are described. According to the techniques described herein, a device (e.g., an application server) may receive a natural language query indicating a query for a value of one or more data records stored in a database table. The database table may be accessible via a target application program interface (API) that is configured as a resource-oriented API. The device may parse the natural language query to identify a set of resources and a set of values corresponding to the set of resources. The device may then identify a hierarchy of the set of resources of the target API and generate the unique resource identifier for the target API to access the value of the one or more data records. The device may generate the unique resource identifier based on the hierarchy of the set of resources.

An embodiment for creating a dialog based on anticipated questions for database driven conversations is provided. The embodiment may include receiving content from a database. The embodiment may also include identifying one or more schemas, one or more entities, and relational data in the content. The embodiment may further include identifying a semantic type and a number of distinct entries for each entity. The embodiment may also include presenting choices for one or more query targets and one or more filtering conditions to a user. The embodiment may further include prompting the user for one or more annotations and one or more clarifying questions for each chosen query target and filtering condition. The embodiment may also include generating a plurality of modular phrases. The embodiment may further include combining the plurality of modular phrases into one or more sentences and paraphrases of the one or more sentences.

Categorical data transformation and clustering techniques and systems are described for machine learning using natural language processing. These techniques and systems are configured to improve operation of a computing device to support efficient and accurate use of categorical data, which is not possible using conventional techniques. In an example, categorical data is received by a computing device that includes a categorical variable having a non-numerical data type for a number of classes. The categorical data is then converted into numerical data using natural language processing. Data is then generated by the computing device that includes a plurality of latent classes. This is performed by clustering the numerical data into a number of clusters that is smaller than the number of classes in the categorical data.

A system, method and computer program product, which given in input a question in natural language format, delivers personalized insights related to the answer. Personalized insights are selected among candidate insights mined from the data and ranked based on closeness to (mined) user-preference, relevance to the question, and surprise factor. Two core components include: Question analysis and meaningful insight look up and Multi-dimensional insight ranking. The Question analysis and meaningful insights lookup module performs a semantic analysis of the questions and, uses techniques including “templates” to build new questions which could uncover insights from the data. The Multi-dimensional insight ranking module takes in input a list of insights returned from Question analysis and meaningful insights lookup and rank such insights based on such factors as: relevance to the query, surprise factor, and user preferences.

A search apparatus includes a memory and circuitry. The memory is configured to store second sentences in association with past-input first sentences, and store synonyms corresponding to each of a plurality of words. The circuitry is configured to divide each of the past-input first sentences into words and divide a newly-input first sentence into words; select, from the synonyms corresponding to each of the plurality of words, synonyms corresponding to each of the words obtained by dividing each of the past-input first sentences, in descending order of appearance frequency of the words; store the selected synonyms; detect, from the selected synonyms, synonyms corresponding to each of the words obtained by dividing the newly-input first sentence; and retrieve, from the memory storing the second sentences, at least one of the second sentences corresponding to the newly-input first sentence based on the detected synonyms and the words of the newly-input first sentence.

A method, system, and computer program product for improving the possibilities to retrieve data from a database, includes receiving instructions from a user interface and providing data to the user interface, wherein the database contains a plurality of datasets and a plurality of relationships of the datasets. The database provides a search interface based on graph query language. Data is exchanged by the search interface based on the graph query language. Instructions entered in the user interface being at least partially not in graph query language are processed and/or data retrieved from the database being in graph query language are processed.

A computerized personal assistant communicatively couples to a computer database including a plurality of available skills for the computerized personal assistant. The computerized personal assistant recognizes a current context of the user. The computerized personal assistant operates a previously-trained machine learning classifier to assess a match confidence for a candidate skill, the match confidence indicating a quality of match between the current context and a reference context previously associated with the candidate skill. The computerized personal assistant executes instructions defining an assistive action associated with the candidate skill responsive to the match confidence exceeding a predefined match confidence threshold. The computerized personal assistant executes the instructions defining a complementary help action associated with the candidate skill responsive to the match confidence not exceeding the predefined match confidence threshold.