A method in a contact center for generating insights from conversation data derived from interactions and storing the insights in an index. The method may include: determining an insight type; based on the insight type, determining inputs including a question prompt, answer prefix, and relevant portion of the conversation data; inputting the inputs into a LLM configured to receive the inputs and generate output text answering a question contained in the question prompt pursuant to an answer form suggested by the answer prefix given content contained in the relevant portion of the conversation data; generating the output text via operation of the LLM; transforming the output text of the first insight via a sentence transformer into vector embedding representative of a semantic meaning of the output text; and storing the computed vector embedding of the first insight in the index.

This application is directed to implementing functions at a computer system automatically. The computer system receives a natural language query. In response to the natural language query, the computer system automatically applies a function determination model to generate function information of a target function based on the natural language query. The function information further includes identification information and one or more parameters of the target function. The target function is implemented based on the function information. One or more user applications are configured to implement a plurality of predefined functions including the target function.

A method and apparatus are disclosed for generating permission-based large language model responses by using a query received from a user to identify a plurality of documents that are semantically similar to the query, using an access token received from the user to identify user accessible documents from the plurality of documents that the user is permitted to access, processing the user accessible documents to define a context of user accessible documents that is associated with the query, and then submitting the query and the context of user accessible documents to a large language model (AI system) to generate an AI system response to the query.

Provided in the disclosure, a method, an apparatus a device, and a storage medium for processing a client-side problem are are provided. An example method includes: determining at least one information acquisition functional block from a plurality of information acquisition functional blocks based on a received user input, the user input indicating a client-side problem related to a client of a user, different information acquisition functional blocks of the plurality of information acquisition functional blocks configured to obtain different types of client-side information; obtaining target information related to the client-side problem of the client using the at least one information acquisition functional block; and providing a response to the client-side problem using a first machine learning model based on the user input and the target information.

Systems and methods are provided for automatic legal document generation. Input is received from a user, such as information on a type of document that the user intends to generate. The user is then prompted to enter a information to draft the document. Based on the interpretation of the user inputs, a generative AI document is produced. Quality checks are applied to the generative AI document product to ensure that any cases or references are properly cited and free of mistakes.

A system integrates an enhanced communication module within an online tutoring platform to establish a communication between the online tutoring platform and an AI tutoring system to enhances the learning experience on the online tutoring platform through contextual content delivery, adaptive and interactive problem-solving guidance, and personalized tutoring of the user. The AI tutoring system receives user data from the user and the ongoing session data. The system comprises a processor to receive the user data and the ongoing session data to parse the received user data and ongoing session data to extract one or more session events. The processor compares the one or more session events to a plurality of pre-defined rules to detect the session event. The AI tutoring system utilizes a LLM to generate a prompt. The chatbot window is used to display the generated prompt on a user interface of the online tutoring platform interface to the user.

An information processing apparatus according to the present application includes a generation unit, a reception unit, and a determination unit. The generation unit generates non-response target information indicating a non-response target. The reception unit receives information indicating a request of a user. The determination unit determines, based on a plurality of pieces of non-response target information generated by the generation unit, whether the request indicated by the information received by the reception unit is a request concerning a non-response target.

A learning system and an execution method thereof are provided. The execution method includes: displaying an option object through a graphical user interface of a display device, wherein the option object includes at least one option, and the at least one option is associated with course information; in response to one of the at least one option being selected, the graphical user interface displaying a user image and a virtual object; in response to the virtual object being triggered, the graphical user interface displaying a function window, and the function window at least partially overlapping with the user image, wherein the function window has at least one learning option; in response to one of the at least one learning option being triggered, the graphical user interface displaying a question-and-answer window; the question-and-answer window of the graphical user interface displaying a templated answer corresponding to the input data.

A system answers natural language questions using retrieval-augmented generation. The system stores a set of domain specific documents in a vector database. The system receives a natural language question. The system retrieves a subset of documents relevant to the natural language question from the vector database. The system determines prior knowledge information required in addition to the subset of documents retrieved from the vector database for answering the natural language question. The system generates a prompt for a machine learning based language model including instructions to the machine learning based language model to refrain from using prior knowledge obtained by the machine learning based language model during training of the machine learning based language model. The receives a response generated by executing the machine learning based language model based on the prompt. The system performs an action based on the response.

Systems and methods are described for obtaining accurate responses from large language models (LLMs) and chatbots, including for question and answering, exposition, and summarization. These systems and methods accomplish these objectives via use of noun phrase avoiding processes such as a noun phrase collision detection process, a query splitting process, and a topical splitting process as well as by use of formatted facts, formatted fact model correction interfaces (FF MCIs), bounded-scope deterministic (BSD) neural networks, processes and methods, and intelligent storage and retrieval (ISAR) systems and methods. These systems and methods avoid and bypass noun phrase collisions and correct for errors caused by noun phrase collisions so that hallucinations are eliminated from LLM responses.