15853results about "Natural language translation" patented technology

Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and / or request bodies, structuring user-generated content, and / or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

Various embodiments discussed herein are directed to improving existing technologies by detecting a likelihood of hallucination arising from one-shot, few-shot, or outside knowledge contexts. For example, regarding the one-shot or few-shot contexts, some embodiments determine a set of tokens in a language model output that are not found in target content but are found in at least one example. When such phrases are not very common words, this is highly indicative that the model is hallucinating because these phrases should be located in the target content but are not, but are instead located in the examples.

An example operation may include one or more of receiving a sequence of inputs from a user during a conversation between the user and a chatbot within a chat window of a software application, executing a large language model (LLM) on each input from the user to determine a next prompt to output via the chatbot, respectively, wherein each execution of the LLM includes a new chat input from the user and a most-recent state of the conversation between the user and the chatbot within the chat window, and displaying the next prompt within a chat window on a user device.

Embodiments of the disclosed technologies include receiving a first query including at least one first query term and configuring at least one prompt to cause a large language model to translate the at least one first query term into a set of functions that can be executed to obtain at least one second query term and generate and output a plan that is executable to create a modified version of the first query based on the at least one second query term. The plan is obtained by applying the large language model to the at least one prompt as configured. The plan is executed to determine the at least one second query term and create the modified version of the first query. The modified version of the first query is executed to provide, via the user interface, a response to the first query.

The present disclosure relates to methods and systems for using large language models to support research activities. The methods and systems include a copilot engine that creates input prompts to provide to the large language model to use in generating responses to input messages. The copilot engine infers an intent of the input messages and sends the intent with the input message in the input prompt to the large language model. The large language model generates different types of responses for different intents.

A Generative Artificial Intelligence (Gen. AI) based chatbot apparatus implements classical AI models and Generative AI models to answer user queries with results retrieved from relational databases and unstructured knowledge bases. When a user query is received, it is determined if the intent of the user query can be determined with a confidence greater than a configured confidence limit. If yes, a structured query mapped to the intent is employed to answer the user query. If the intent determination confidence is less than the configured confidence limit then Gen. AI-based techniques using a plurality of LLMs are used to respond to the query. A Gen. AI switch is also implemented to switch between the plurality of LLMs to answer user queries with greater accuracy.

Systems and methods are provided for implementing automatic prompt optimization using textual gradients. In various embodiments, a feedback prompt, input into a large language model (“LLM”), is used to generate textual gradients that criticize a current prompt. The feedback prompt includes the current prompt and predictions that are incorrect compared with corresponding labels associated with minibatch data processed by the LLM using the current prompt. The textual gradients and current prompt are used in an editing prompt to the LLM to obtain a set of optimized prompts, which may be expanded using a paraphrasing prompt that is input into the LLM to generate a set of paraphrased prompts. A selection algorithm is used to select one or more optimized prompts from the set of optimized prompts and / or the set of paraphrased prompts, and the process is repeated with the selected one or more optimized prompts replacing the current prompt.

A customized prompt generation service automates prompts to a large language model to perform a specified software engineering task. The service stores the custom data of a client that includes code diff hunks, source code segments, code reviews, repaired code, and unit tests from a code base or repository of the client. Prompt templates are associated with each software engineering task that include the requisite information needed for the large language model to perform the target task. A prompt to a large language model includes examples of the software engineering task from the custom data of the client of the service.

Network infrastructure for user-specific generative intelligence. Providing user-specific context to a generically trained LLM introduces a variety of complications (privacy, resource utilization, training costs, etc.). Various aspects of the present disclosure provide novel user-specific data structures, privacy and access control, layers of data, and session management, within a network infrastructure for generative intelligence. For example, user-specific embedding vectors may be used to provide user context to a generically trained foundation model. In some variants, edge devices capture multiple modalities of user context (images, audio; not just text). Privacy and access control mechanisms also allow a user to control information that is captured and sent to the foundation model. Session management further decouples a user's conversational state from the foundation model's session state. These concepts and others may be used to emulate e.g., a chatbot based virtual assistant that responds based on user context.

Techniques are disclosed herein for implementing digital assistants using generative artificial intelligence. An input prompt comprising a natural language utterance and candidate agents and associated actions can be constructed. An execution plan can be generated using a first generative artificial model based on the input prompt. The execution plan can be executed to perform actions included in the execution plan using agents indicated by the execution plan. A response to the natural language utterance can be generated by a second generative artificial intelligence model using one or more outputs from executing the execution plan.

A system comprises a communications module; at least one processor coupled with the communications module; and a memory coupled to the at least one processor and storing processor-executable instructions which, when executed by the at least one processor, configure the at least one processor to provide, via the communications module, a first encryption key of an encryption key pair to a client device; receive, via the communications module and from a conversation agent server, a fulfillment request based on a natural language input transmitted from the client device to the conversation agent server; determine that the fulfillment request includes a request for personal data; obtain the requested personal data; encrypt the personal data with a second encryption key of the encryption key pair; and provide, via the communications module and to the conversation agent server, the encrypted personal data for transmission to the client device.

The present disclosure generally relates to systems, software, and computer-implemented methods for using generative artificial intelligence to improve user interactions. One example method includes identifying, in a contact center application of an agent, a start of an assisted leg of an interaction of a user with a system. A user interaction summary is retrieved that summarizes events that have previously occurred in the interaction. A generative large language model (LLM) artificial intelligence (AI) context prompt is extracted based on the user interaction summary. The context prompt is provided to a generative LLM AI engine to set a context for the generative LLM AI engine. Event information is received that includes a query for the generative LLM AI engine. The query is provided to and a query response is received from the generative LLM AI engine. The contact center application is updated in response to the query response.

Systems and methods for building an application incorporating AI functionality include enabling access to a developer application framework associated with a SaaS platform, receiving application code for generating an application, and receiving a selection of an AI assistant add-on provided by the SaaS platform. A link is established between the selected AI assistant add-on and a SaaS platform element, permission is provided to access data from the at least one of the plurality of linked SaaS platform elements. Based on the permissions, data is transferred from the at least one of the plurality of linked SaaS platform elements, and AI integration code is received including at least one reference to the transferred data and at least one call to an AI agent. The application is published for selective use with SaaS platform elements and is configured to exchange data with the at least one of the plurality of SaaS platform elements.

The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.

A database system may include one or more relational databases storing information for a plurality of tenants in accordance with database object definitions. The database system may also include a communication interface providing the plurality of tenants with access to web applications through which to access the information and configured to receive an indication of one or more of the database object definitions from a tenant. The database system may also include a storage device storing a prompt template specific to the tenant and that includes one or more natural language instructions for generating text and a reference to the one or more database object definitions. The database system may also include a processor configured to retrieve a database record associated with the tenant and corresponding to the one or more database object definitions and to determine a text generation prompt based on the database record and the prompt template.

A system comprises a communications module; at least one processor coupled with the communications module; and a memory coupled to the at least one processor and storing processor-executable instructions which, when executed by the at least one processor, configure the at least one processor to provide, via the communications module, a first encryption key of an encryption key pair to a client device; receive, via the communications module and from a conversation agent server, a fulfillment request based on a natural language input transmitted from the client device to the conversation agent server; determine that the fulfillment request includes a request for personal data; obtain the requested personal data; encrypt the personal data with a second encryption key of the encryption key pair; and provide, via the communications module and to the conversation agent server, the encrypted personal data for transmission to the client device.

The present disclosure is directed to systems and methods to enhance the process of creating an artificial intelligence (AI) generated content or content items, such as images, text, video, sounds, etc., using a text or other suitable prompt, such as via voice input. The systems and methods disclosed provide streamlined content generation with, e.g., reduced processing power and computing time. In an embodiment the systems and methods receive a prompt for generating a first content item using a generative artificial intelligence (AI) model and retrieve, based on the prompt, a collection of matching content items. The systems and methods may then receive input selecting one of the content items from the collection and identify a prompt used to generate the selected content item. The systems and methods may then merge using a trained natural language processing model, the received prompt with the prompt of the selected content item to create a third prompt. In an embodiment the systems and methods may modify the third prompt based on additional input and, based on the modified third prompt, generate a second content item.

A method is provided for estimating the number of distinct tokens in a text stream using a modified text-to-text variational autoencoder (T5VQVAE) model. The method includes receiving a continuous input of a text stream; dynamically maintaining a buffer that stores a probabilistic subset of tokens from the text stream; calculating a sampling probability for each token based on a condition related to the current state of the buffer; updating the buffer based on the sampling probability to include or exclude tokens; encoding the buffered tokens into a latent space using the T5VQVAE model; and estimating the number of distinct tokens in the text stream based on the tokens in the buffer and the corresponding sampling probabilities.

An example operation may include one or more of receiving an identifier of a product from a digital wallet on a user device, identifying one or more payment cards stored within the digital wallet on the user device, determining benefits that will be obtained by using each of the one or more payment cards to purchase the product via execution of an LLM on the identifier of the product and a corpus of credit card documents, and displaying a chat message within a chat window on the user device with a description of the determined benefits that will be obtained.

Approaches presented herein provide for the ability to process, store, index, and search geospatial information such as maps with flexible granularity. A set of observations, such as may include sensor data captured for a region of an environment, can be fed as input to a language model. The language model can generate a tokenized description of the region, as may include a text string of tokens encapsulating semantics, topology, geometry, and / or other aspects of the region. A feature vector or embeddings for the region can be generated based on the tokenized description, and a similarity search performed against a vector database, for example, to identify similar feature vectors corresponding to similar regions or domains. Labels or other information associated with these similar feature vectors can be automatically applied to the example region. Clustering of feature vectors or other embeddings can also be performed based in part on the similarity.

An example operation may include one or more of training a large language model (LLM) to learn credit card data via execution of the LLM on content from one or more credit card documents, executing the LLM to generate a sequence of prompts which are output to a user via a chatbot within a chat window of a software application, receiving responses to the sequence of prompts for the user via the chat window of the software application, and retraining the LLM model to further learn credit card data via execution of the LLM on a combination of the sequence of prompts and the received responses.

A novel method provides an AI language virtual agent having self-improvement features and which uses language modeling and tree search techniques. The AI language virtual agent exchanges textual discussion with users and other simulated agents. The method includes receiving a current situational description depicting natural language user input, temperament qualities and textual tendencies of the virtual agent, and indicia regarding subject matter context of a present conversation. The indicia regarding subject matter context include textual logs from recent conversational exchanges. The current situational description includes audio, visual, and tactile inputs collected proximate to the virtual agent. The method preferably utilizes an MCTS tree search in combination with self-moving modules, one or more language models, tree search techniques outputting textual responses to the current situation description, and the virtual agent responding with textual expression to verbal input in combination with the audio, visual, tactile, and other sensory inputs.

An example operation may include one or more of receiving a current status of a portfolio of a user and previous actions taken on the portfolio of the user over a predetermined period of time, determining a goal for the user based on execution of a generative artificial intelligence (GenAI) model on the current status of the portfolio of the user and the previous actions taken, receiving a request for the portfolio of the user via a user device, and in response to the request, generating a text-based description of the goal and displaying the text-based description of the goal with portfolio content from the portfolio of the user on a user interface of the user device.

The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.

An example operation may include one or more of identifying a first topic from a call actively in progress, displaying a dashboard on a user device on the call, wherein the dashboard comprises content related to the first topic, receiving discussion data from the call, determining that a focus of the call has shifted from the first topic to a second topic, executing an artificial intelligence (AI) model on the second topic, dynamically generating dashboard content based on the execution, and displaying the dynamically generated dashboard content to the dashboard on the user device.

Embodiments described herein relate to systems and methods for automatically generating content, generating API requests and / or request bodies, structuring user-generated content, and / or generating structured content in collaboration platforms, such as documentation systems, issue tracking systems, project management platforms, and other platforms. The systems and methods described use a network architecture that includes a prompt generation service and a set of one or more purpose-configured large language model instances (LLMs) and / or other trained classifiers or natural language processors used to provide generative responses for content collaboration platforms.

Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

Embodiments described herein provide systems and methods for retrieval augmented generation. A neural network based language model may be provided a question as a user input. Based on the user input, semantically diverse queries may be generated for retrieval from diverse data sources. For example, a structured data source (e.g., database or knowledge base) and unstructured data (e.g., text articles) may be used to retrieve information relevant to the user input. The retrieve information may be ranked so that the most relevant information is used by the language model in generating an answer to the question in the user input. A non-retrieval based answer generated by the language model may be utilized in some embodiments in generating the final answer.