Salesforce, Inc. patent applications on December 12th, 2024
Patent Applications by Salesforce, Inc. on December 12th, 2024
Salesforce, Inc.: 9 patent applications
Salesforce, Inc. has applied for patents in the areas of G06F40/284 (2), G06F16/23 (2), G06N3/08 (2), G06F16/215 (1), G06F40/186 (1) G06F40/284 (2), G06F16/23 (1), G06F16/2365 (1), G06F16/287 (1), G06F40/35 (1)
With keywords such as: data, based, application, user, training, input, service, time, specific, and language in patent application abstracts.
Patent Applications by Salesforce, Inc.
Inventor(s): Eldor Khalyknazarov of Allen TX (US) for salesforce, inc., Puneet Dhaliwal of Dublin CA (US) for salesforce, inc., Dai Duong Doan of Alameda CA (US) for salesforce, inc.
IPC Code(s): G06F16/23
CPC Code(s): G06F16/23
Abstract: database systems and methods are provided for initiating an action at a database system by an instance of a native application at a client device coupled to the database system over a network. one method involves a service associated with a field service application at a client device monitoring a location of the client device to determine the location satisfies update criteria including a field of a data record associated with a service appointment when the location is within a threshold distance of a value for the field of the data record corresponding to an address for the service appointment. the service automatically provides an indication to automatically update a status field of the data record associated with the service appointment at the database system in accordance with a configuration associated with the instance of the field service application when the location of the client device satisfies the update criteria.
Inventor(s): Gang Shu of San Francisco CA (US) for salesforce, inc.
IPC Code(s): G06F16/23, G06F16/215, G06F40/186
CPC Code(s): G06F16/2365
Abstract: in some embodiments, a method selects a set of fields for a record in a database system. a set of prompt templates is retrieved that is associated with the set of fields. a prompt template comprises text and a variable. the method searches information that is associated with the record to determine context information and inserts the context information into the prompt templates to generate a set of prompts. the set of prompts is input into a generative model to output a generated result. the generative model is trained to output text based on prompts. the method outputs enrichment data for the record on an interface, wherein the enrichment data is based on the text of the generated result.
Inventor(s): Paymon TEYER of San Ramon CA (US) for salesforce, inc., Jackson HERRICK of San Francisco CA (US) for salesforce, inc.
IPC Code(s): G06F16/28, G06F11/34, G06F16/2458
CPC Code(s): G06F16/287
Abstract: a method and apparatus for collecting and supporting querying of multi-dimensional data pertaining to usage of software and/or hardware to service tenant requests in a multi-tenant cloud computing system where the multi-dimensional data is initially captured on a per request basis and recorded in objects of a first type that store data pertaining to a specific request, specific tenant, specific host and specific time. the objects of the first type are combined by time windows to form objects of a second type. the objects of a second type are stored in another system as separate text files. responsive to a query for multi-dimensional data for a specific tenant that spans an interval of multiple time windows, the objects of the second type for the specific tenant and time interval are combined across all hosts to generate a query result, and the query result is returned.
Inventor(s): Shiva Kumar Pentyala of Mountain View CA (US) for salesforce, inc., Prafulla Kumar Choubey of San Jose CA (US) for salesforce, inc., Shashank Harinath of Mountain View CA (US) for salesforce, inc., Sitaram Asur of Newark CA (US) for salesforce, inc., Chien-Sheng Jason Wu of Mountain View CA (US) for salesforce, inc., Zachary Alexander of Berkeley CA (US) for salesforce, inc., Caiming Xiong of Menlo Park CA (US) for salesforce, inc.
IPC Code(s): G06F40/284
CPC Code(s): G06F40/284
Abstract: embodiments described herein provide a training framework for generative nlp models that operate on previously learnt knowledge from pretrained large language models. specifically, to train an nlp model to generate a response to a user utterance (e.g., “resolve login issue”), document embeddings of support it documents encoded by a pretrained llm are fed to an nlp decoder together with a training dialogue (e.g., a dialogue between the chat agent on how to “resolve login issue”). the nlp decoder can thus be trained by a causal language modeling loss computed based on the predicted next token and the ground-truth token from the training dialogue.
Inventor(s): Shiva Kumar Pentyala of Mountain View CA (US) for salesforce, inc., Prafulla Kumar Choubey of San Jose CA (US) for salesforce, inc., Shashank Harinath of Mountain View CA (US) for salesforce, inc., Sitaram Asur of Newark CA (US) for salesforce, inc., Chien-Sheng Jason Wu of Mountain View CA (US) for salesforce, inc., Zachary Alexander of Berkeley CA (US) for salesforce, inc., Caiming Xiong of Menlo Park CA (US) for salesforce, inc.
IPC Code(s): G06F40/284, G06N3/08
CPC Code(s): G06F40/284
Abstract: embodiments described herein provide a training framework for generative nlp models. specifically, the training input, e.g., in the form of a sequence of tokens representing a user-agent dialogue, may be randomly masked for a few spans, which can be one or more tokens, one or more words, one or more sentences, or one or more paragraphs. these masked spans are replaced with their embeddings generated from pre-trained large language models are then used for training the nlp model.
20240412000. LARGE LANGUAGE MODEL CONTROLLER_simplified_abstract_(salesforce, inc.)
Inventor(s): Lik Mui of San Carlos CA (US) for salesforce, inc.
IPC Code(s): G06F40/35, G06F16/953, G06F40/279
CPC Code(s): G06F40/35
Abstract: an application server or other processing entity may receive, via a cloud-based platform, user input that may include at least one request for data. the application server may classify the user input into a first of a plurality of deterministic-stochastic spectrum classifications based on the user input and a probability of mapping the at least one request for data to at least one data location. the application server may retrieve the data from the at least one data location and based on the first deterministic-stochastic spectrum classification. the application server may transmit, based on the first deterministic-stochastic spectrum classification and the user input, an input to a large language model. the application server may present a response to the user input, where the response is based on a combination of an output of the large language model and the data retrieved from the at least one data location.
Inventor(s): Regunathan Radhakrishnan of San Francisco CA (US) for salesforce, inc., Zachary Alexander of Berkeley CA (US) for salesforce, inc., Sitaram Asur of Newark CA (US) for salesforce, inc., Shashank Harinath of Mountain View CA (US) for salesforce, inc., Na Cheng of Yarrow Point WA (US) for salesforce, inc., Shiva Kumar Pentyala of Mountain View CA (US) for salesforce, inc.
IPC Code(s): G06N3/08
CPC Code(s): G06N3/08
Abstract: embodiments described herein provide a method for training a neural network based model. the methods include receiving a training dataset with a plurality of training samples, and those samples are encoded into representations in feature space. a positive sample is determined from the raining dataset based on a relationship between the given query and the positive sample in feature space. for a given query, a positive sample from the training dataset is selected based on a relationship between the given query and the positive sample in a feature space. one or more negative samples from the training dataset that are within a reconfigurable distance to the positive sample in the feature space are selected, and a loss is computed based on the positive sample and the one or more negative samples. the neural network is trained based on the loss.
20240412157. NO-CODE GENERATION OF INTEGRATION APPLICATIONS_simplified_abstract_(salesforce, inc.)
Inventor(s): Ignacio Manzano of Buenos Aires (AR) for salesforce, inc., Diego LARRALDE of Buenos Aires (AR) for salesforce, inc., Tomas Fernandez MARTINEZ of Buenos Aires (AR) for salesforce, inc.
IPC Code(s): G06Q10/087
CPC Code(s): G06Q10/087
Abstract: disclosed herein are system, method, and device embodiments for programmatically generating and deploying an integration application based on a natural language request without requiring any coding by a user. the application generator infers the sources, targets, connectors, operations, entities, and data mappings needed to build the requested integration application. an exposed web service or api may receive natural language input, determine the meaning of the request, and generates and deploys the resulting integration application without requiring any coding by a user.
Inventor(s): Max Baez of Portola Valley CA (US) for salesforce, inc., Pooja Menta of San Francisco CA (US) for salesforce, inc., Stephen Michael Hamrick of Redwood City CA (US) for salesforce, inc.
IPC Code(s): H04L51/18
CPC Code(s): H04L51/18
Abstract: techniques for modifying a period of time that data, associated with a characteristic, transmitted via a communication platform is retained are described. a data retention rule can include a first period of time for retaining data transmitted via the communication platform, in association with an organization. the first user can additionally establish a specific data retention rule associated with data associated with a particular characteristic. the specific data retention rule can include an instruction to store communications including the particular characteristic for a second time period that is different from the first time period associated with the data retention rule. the communication platform can receive data from a second user computing device associated with the second user of the organization. based on a determination that the data is associated with the characteristic, the communication platform can store the data according to the data retention rule specified for such data.