公开(公告)号：US20250086735A1

公开(公告)日：2025-03-13

申请号：US18427275

申请日：2024-01-30

Applicant: Salesforce, Inc.

Inventor： Sundar Ram Vedula ,  Rajdeep Dua ,  Akash Singh ,  Amit Kumar Dash ,  Nimesh Gupta ,  Sourav Sipani ,  Ajay Singh ,  Khyati Garg ,  Sree Harini Soma

IPC: G06Q50/18

Abstract: Methods, systems, apparatuses, devices, and computer program products are described. A system may support a machine learning model for legal clause extraction. The machine learning model may receive, as an input, at least a portion of a document and may output an indication of one or more legal clauses included in the document. To train the model, the system may receive a document and an indication of ground truths (e.g., legal clauses) for the document. The system may determine one-to-one mappings between the legal clauses indicated by the ground truths and the legal clauses indicated by the output of the machine learning model. The system may perform a longest common substring analysis on the one-to-one mappings to determine an accuracy of the machine learning model and may iteratively update the model based on the analysis.

公开(公告)号：US20250086407A1

公开(公告)日：2025-03-13

申请号：US18412078

申请日：2024-01-12

Applicant: Salesforce, Inc.

Inventor： Sundar Ram Vedula ,  Rajdeep Dua ,  Akash Singh ,  Manoj Kumar Subramaniyan ,  Ankit Oberoi ,  Ajay Singh ,  Arpit Trivedi

IPC: G06F40/58 ,  G06Q30/0203

Abstract: Methods, apparatuses, systems, and computer-program products are disclosed. For example, a system may receive, via a cloud-based platform, first user input including a request for generation of the output data object. The system may generate a prompt based on the first user input and a prompt appendix that defines a response format for a plurality of responses to the prompt that are to be generated by a large language model (LLM). The system may transmit the prompt to the LLM and may receive, from the LLM, the plurality of responses formatted in the response format. The system may generate the output data object that comprises the plurality of responses.

公开(公告)号：US20240020479A1

公开(公告)日：2024-01-18

申请号：US17952155

申请日：2022-09-23

Applicant: Salesforce, Inc.

Inventor： Akash Singh ,  Rajdeep Dua ,  Arun Kumar Jagota

IPC: G06F40/295 ,  G06F40/284 ,  G06N3/063 ,  G06N3/08

CPC classification number: G06F40/295 ,  G06F40/284 ,  G06N3/063 ,  G06N3/084

Abstract: A cloud platform trains a machine-learned entity matching model that generates predictions on whether a pair of electronic records refer to a same entity. In one embodiment, the entity matching model is configured as a transformer architecture. In one instance, the entity matching model is trained using a combination of a first loss and a second loss. The first loss indicates a difference between an entity matching prediction for a training instance and a respective match label for the training instance. The second loss indicates a difference between a set of named-entity recognition (NER) predictions for the training instance and the set of NER labels for the tokens of the training instance.

公开(公告)号：US20240256824A1

公开(公告)日：2024-08-01

申请号：US18138969

申请日：2023-04-25

Applicant: Salesforce, Inc.

Inventor： Akash Singh ,  Rajdeep Dua

IPC: G06N3/04

CPC classification number: G06N3/04

Abstract: A method for using a neural network to generate node embeddings and edge embeddings for graphs. The neural network has K layers. The graph includes multiple nodes and edges linking the multiple nodes. The method includes determining a set of node features for the multiple nodes, and determining a set of edge features for the multiple edges. A first layer of the neural network is applied to the node features and the edge features to output a first set of node embeddings and a first set of edge embeddings. A k-th layer of the neural network is applied to (k−1)th set of node embeddings and (k−1)th set of edge embeddings to output a k-th set of node embeddings and a k-th set of edge embeddings, where the (k−1)th set of node embeddings and (k−1)th set of edge embeddings are output from (k−1)th layer of neural network.

公开(公告)号：US20240257160A1

公开(公告)日：2024-08-01

申请号：US18138962

申请日：2023-04-25

Applicant: Salesforce, Inc.

Inventor： Akash Singh ,  Rajdeep Dua

IPC: G06Q30/0201 ,  G06Q30/018

CPC classification number: G06Q30/0201 ,  G06Q30/0185

Abstract: A method or a system for predicting a likelihood of an occurrence of a transaction. The system accesses a graph including multiple nodes and multiple edges linking the nodes. The multiple nodes include a first type of nodes representing a first type of entities an a second type of nodes representing a second type of entities. The system extract a set of node features for each node, and a set of edge features for each edge. For an edge connecting a first node of the first type and a second node of the second type, the system generates a set of edge embeddings based in part on the node features and edge features, and computes a score based in part on the set of edge embeddings. The score indicates a likelihood of an occurrence of a transaction between the first node and the second node.

公开(公告)号：US20250087027A1

公开(公告)日：2025-03-13

申请号：US18394819

申请日：2023-12-22

Applicant: Salesforce, Inc.

Inventor： Sundar Ram Vedula ,  Rajdeep Dua ,  Mritunjay Kumar ,  Divya Rai ,  Rakesh Mondal ,  Nimesh Gupta

IPC: G07C5/00 ,  B60R16/023 ,  G05B23/02 ,  G06Q30/01 ,  G08B21/18

Abstract: A machine learning model hosted on a cloud platform may be used to proactively predict if a maintenance procedure should be performed for a vehicle. In some examples, to support the prediction, the machine learning model may be connected to a different cloud platform that includes a customer relationship management (CRM) system and receives data from sensors of the vehicle. As such, the cloud platform with the CRM data may transmit the CRM data and the sensor data of the vehicle to the cloud platform hosting the machine learning model to aid in generating the maintenance procedure predictions. Further, the maintenance procedure predictions may also include the generation of a prediction score associated with a maintenance procedure. In some examples, the prediction score may satisfy a prediction score threshold, thus a notification may be transmitted to a computing device that indicates the maintenance procedure to be performed for the vehicle.