Salesforce, Inc. patent applications on March 13th, 2025
Patent Applications by Salesforce, Inc. on March 13th, 2025
Salesforce, Inc.: 19 patent applications
Salesforce, Inc. has applied for patents in the areas of G06F40/40 (4), G06Q10/10 (2), G06N20/00 (2), H04L51/52 (2), G06F9/50 (2) G06F40/40 (3), G06F3/04842 (1), G06Q10/06316 (1), H04L51/48 (1), G07C5/006 (1)
With keywords such as: data, platform, communication, user, request, language, virtual, based, prompt, and receive in patent application abstracts.
Patent Applications by Salesforce, Inc.
20250085836. SYNTHESIZING VIRTUAL SPACE DATA_simplified_abstract_(salesforce, inc.)
Inventor(s): Melissa Aubrie Chan of San Francisco CA (US) for salesforce, inc., Anissa Cristerna of Chicago IL (US) for salesforce, inc., Adam Marinelli of Toronto (CA) for salesforce, inc.
IPC Code(s): G06F3/04842, G06N20/00, H04L51/02, H04L51/52
CPC Code(s): G06F3/04842
Abstract: techniques for generating synthesized data within a virtual space are discussed herein. a communication platform may receive a request from a user profile of a communication platform. the request may include one or more instructions for the communication platform to send a survey to one or more user profiles to provide data (e.g., feedback) to the virtual space. based on sending the request for feedback to the user profiles, the communication platform may receive feedback from the user profiles. upon receiving such feedback, the communication platform may receive a request from a user profile synthesize the data. upon receiving the request to synthesize the feedback, the communication platform may input the user feedback into a machine-learning model trained to output synthesized data. the communication platform may cause the synthesized data to be displayed via the virtual space.
20250086011. AUTOMATION WITH COMPOSABLE ASYNCHRONOUS TASKS_simplified_abstract_(salesforce, inc.)
Inventor(s): Richard Perry Pack, III of San Francisco CA (US) for salesforce, inc., Michael Triantafelow of Raleigh NC (US) for salesforce, inc., Dean Moses of San Francisco CA (US) for salesforce, inc., Caridy Patino of Miami FL (US) for salesforce, inc., Adheip Varadarajan of San Francisco CA (US) for salesforce, inc.
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5005
Abstract: systems, devices, and techniques are disclosed for automation with composable asynchronous tasks. a prompt may be received at a computing device. using a first large language model (llm) composable asynchronous tasks may be determined from the prompt. one of the composable asynchronous tasks may use a second llm. the composable asynchronous tasks may be performed. performing one of the composable asynchronous tasks may include generating a first output with the second llm based on the prompt and validating the first output of the llm. performing another of the composable asynchronous tasks may include generating a second output using the first output.
Inventor(s): Hadi Minooei of San Francisco CA (US) for salesforce, inc., Yazdan Jamshidi of Winter Springs FL (US) for salesforce, inc., Yanqi Luo of San Francisco CA (US) for salesforce, inc., Santiago Bassani of Dublin (IR) for salesforce, inc., Mofeyifoluwa Olaoluwa Oluwalana of San Francisco CA (US) for salesforce, inc., Shobana Ranganathan of Palo Alto CA (US) for salesforce, inc.
IPC Code(s): G06F16/33, G06N20/00
CPC Code(s): G06F16/3344
Abstract: methods, systems, apparatuses, and computer program products are described. a system may receive, via a cloud-based platform, user input comprising a request for generation of the integration flow. the system may generate a query based on the request and a query template including one or more example integration flows and a request to generate a natural language description of the integration flow. the system may transmit the query to the llm and may receive, from the llm, a response including the integration flow and the natural language description. the system may extract the integration flow and the natural language description from the response. the system may perform a validation process on the integration flow based at least in part on one or more integration flow validation rules.
20250086309. TRUST LAYER FOR LARGE LANGUAGE MODELS_simplified_abstract_(salesforce, inc.)
Inventor(s): Shashank Harinath of Palo Alto CA (US) for salesforce, inc., Eugene Wayne Becker of Menlo Park CA (US) for salesforce, inc., Subha Melapalayam of Bellevue WA (US) for salesforce, inc., Eric Brochu of Vancouver (CA) for salesforce, inc., Claire Cheng of Bellevue WA (US) for salesforce, inc., Mario Rodriguez of San Francisco CA (US) for salesforce, inc., Prithvi Krisnan Padmanabhan of San Francsico CA (US) for salesforce, inc., Kathy Baxter of Palo Alto CA (US) for salesforce, inc., Kin Fai Kan of () for salesforce, inc.
IPC Code(s): G06F21/62, G06F40/20
CPC Code(s): G06F21/6245
Abstract: a cloud platform may include a model interface that receives from a client and at an interface for accessing a large language model, a prompt for a response from the large language model, and the client is associated with a set of configuration parameters via a cloud platform that supports the interface. the cloud platform may modify, in accordance with the set of configuration parameters, the prompt that results in a modified prompt and transmit, to the large language model, the modified prompt. the cloud platform may receive the response generated by the large language model and provide the response to a model that determines one or more probabilities that the response contains content from one or more content categories. the cloud platform may transmit the response or the one or more probabilities to the client.
Inventor(s): Nate Nichols of Chicago IL (US) for salesforce, inc., Homer Wang of Seattle WA (US) for salesforce, inc., Caroline Sherman of San Francisco CA (US) for salesforce, inc., Lara Thompson of Vancouver (CA) for salesforce, inc., Jon Drake of San Francisco CA (US) for salesforce, inc., Ian Booth of San Francisco CA (US) for salesforce, inc.
IPC Code(s): G06F40/20, G06F16/383
CPC Code(s): G06F40/20
Abstract: a system obtains a bundle of insights generated based on insight templates and provides the bundle of insights as input to a machine learning model. the system then generates a summary of the bundle of insights using the machine learning model.
Inventor(s): Guillaume Kempf of San Francisco CA (US) for salesforce, inc., Georgios Balikas of Grenoble (FR) for salesforce, inc., Ghislain Brun of Grenoble (FR) for salesforce, inc., Darya Brazouskaya of Grenoble (FR) for salesforce, inc., Qianqian Shi of San Francisco CA (US) for salesforce, inc., Marjan Hosseinia of Houston TX (US) for salesforce, inc., Matthieu Landos of Grenoble (FR) for salesforce, inc., Médéric Carriat of Paris (FR) for salesforce, inc., Mukund Ramachandran of San Francisco CA (US) for salesforce, inc.
IPC Code(s): G06F40/284, G06F16/31, G06F16/33, G06F40/40
CPC Code(s): G06F40/284
Abstract: a method of data processing is described. the method includes converting a plain-text query into a vector-based object by using a text embedding function to process one or more tokens in the plain-text query. the method further includes retrieving a set of passages from a first datastore of the data processing system based on using one or more search indexes stored in a second datastore of the data processing system to compare the vector-based object and the one or more tokens in the plain-text query to vector-based objects and token-based objects associated with the set of passages. the method further includes generating a prompt that includes tokens from the plain-text query, tokens from one or more of the set of passages retrieved from the first datastore, and instructions for creating a response to the plain-text query. the method further includes transmitting the prompt to a large language model (llm).
Inventor(s): Ran Xu of Palo Alto CA (US) for salesforce, inc., Zeyuan Chen of Newark CA (US) for salesforce, inc., Yihao Feng of Palo Alto CA (US) for salesforce, inc., Krithika Ramakrishnan of New York NY (US) for salesforce, inc., Congying Xia of Palo Alto CA (US) for salesforce, inc., Juan Carlos Niebles Duque of Mountain View CA (US) for salesforce, inc., Vetter Serdikova of Mountain View CA (US) for salesforce, inc., Huan Wang of Palo Alto CA (US) for salesforce, inc., Yuxi Zhang of San Francisco CA (US) for salesforce, inc., Kexin Xie of Foster City CA (US) for salesforce, inc., Donglin Hu of Dublin CA (US) for salesforce, inc., Bo Wang of Fremont CA (US) for salesforce, inc., Ajaay Ravi of Dublin CA (US) for salesforce, inc., Matthew David Trepina of Indianapolis IN (US) for salesforce, inc., Sam Bailey of Newtownabbey (GB) for salesforce, inc., Abhishek Das of Bellevue WA (US) for salesforce, inc., Yuliya Feldman of Palo Alto CA (US) for salesforce, inc., Pawan Agarwal of Bellevue WA (US) for salesforce, inc.
IPC Code(s): G06F40/40, G06F9/451, G06F9/50, G06T11/00
CPC Code(s): G06F40/40
Abstract: methods, systems, apparatuses, devices, and computer program products are described. a flow generation service may receive a natural language input that indicates instructions for automating a task according to a first process flow. using a large language model (llm), the flow generation service may decompose the natural language input into a set of elements (e.g., logical actions) and connectors, where the llm may be trained on first metadata corresponding to a second process flow that is created manually by a user. in addition, using the llm, the flow generation service may generate second metadata corresponding to each of the set of elements based on decomposing the natural language input. the flow generation service may sequence and merge the set of elements to generate the first process flow. in some examples, the flow generation service may send, for display to a user interface of a user device, the first process flow.
Inventor(s): Scott PITKIN of Bloomington IN (US) for salesforce, inc., Michael AURELIO of Novato CA (US) for salesforce, inc., Jonathan BELKOWITZ of Brooklyn NY (US) for salesforce, inc., Allen HOEM of Indianapolis IN (US) for salesforce, inc., Amrutha KRISHNAN of San Bruno CA (US) for salesforce, inc., Abigail KUTRUFF of New York NY (US) for salesforce, inc.
IPC Code(s): G06F40/40, G06Q30/0242
CPC Code(s): G06F40/40
Abstract: a computing services environment may include a database system, a generative language model interface, a communication interface, and a messaging interface. the database system may store database records reflecting interactions between tenants of the computer services environment and individuals interacting with the tenants, and may determine an input description of a communication campaign between a tenant of the plurality of tenants and a corresponding segment of the individuals. the generative language model interface may determine a textual description of one or more elements of the communication campaign by completing a campaign brief generation prompt via a generative language model. the communication interface may transmit to a client machine authenticated to a database system account linked to the tenant an instruction to generate a graphical user interface at the client machine. the messaging interface may transmit messages based on the input description and the refinement.
Inventor(s): Andrew Fong of Menlo Park CA (US) for salesforce, inc.
IPC Code(s): G06F40/40, H04L67/306
CPC Code(s): G06F40/40
Abstract: techniques for displaying answers to questions via a user interface of a virtual space are discussed herein. a communication platform may receive text from a virtual space. in such examples, a user profile may be inputting the text to a compose pane such that the user profile may post the text to the virtual space. based on receiving the text, the communication platform may input the text into a machine-learning model trained to output key words and/or phrases included in the text. the communication platform may use the output from the machine-learning model to identify a question-answer pair contained in a canvas of the virtual space. in such instances, the communication platform may display the question-answer pair via the user interface of the user device associated with the user profile. based on the user profile selecting the question-answer pair, the communication platform may display the canvas including the question-answer pair.
20250086407. LARGE LANGUAGE MODEL DATA OBJECT GENERATION_simplified_abstract_(salesforce, inc.)
Inventor(s): Sundar Ram Vedula of Bangalore (IN) for salesforce, inc., Rajdeep Dua of Hyderabad (IN) for salesforce, inc., Akash Singh of Hyderabad (IN) for salesforce, inc., Manoj Kumar Subramaniyan of Bangalore (IN) for salesforce, inc., Ankit Oberoi of Hyderabad (IN) for salesforce, inc., Ajay Singh of Bangalore (IN) for salesforce, inc., Arpit Trivedi of Hyderabad (IN) for salesforce, inc.
IPC Code(s): G06F40/58, G06Q30/0203
CPC Code(s): G06F40/58
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.
Inventor(s): Nate Nichols of Chicago IL (US) for salesforce, inc., Dan Platt of Chicago IL (US) for salesforce, inc., Homer Wang of Seattle WA (US) for salesforce, inc.
IPC Code(s): G06N3/0455
CPC Code(s): G06N3/0455
Abstract: a plurality of data fields are obtained from a selected data source. a first subset of the plurality of data fields corresponds to a plurality of measures and a second subset of the plurality of data fields corresponds to a plurality of dimensions. a machine learning model is prompted to generate a plurality of suggested metric objects. in response to prompting the machine learning model, a respective metric definition is generated for each measure in the plurality of measures. each generated metric definition includes a plurality of data fields, including: (i) a name; (ii) a measure; (iii) a time dimension; and (iv) an aggregation type.
Inventor(s): Victor Yee of San Francisco CA (US) for salesforce, inc., Yiqiao Liu of Bellevue WA (US) for salesforce, inc., Shashank Harinath of Palo Alto CA (US) for salesforce, inc., Fermin Ordaz of San Francisco CA (US) for salesforce, inc., Adam Smith of Carmel IN (US) for salesforce, inc., Suhail Barot of Palo Alto CA (US) for salesforce, inc., Tuan Nguyen of San Francisco CA (US) for salesforce, inc.
IPC Code(s): G06N3/0895, G06N3/0475
CPC Code(s): G06N3/0895
Abstract: the described method may include receiving user input indicating a configuration identifying a large language model (llm) and a subset of documents indicated in the configuration as being available to a tenant. the method may include generating one or more vectorizations of content of the subset of documents. the method may include receiving a request to generate a generative response. the method may include generating the generative artificial intelligence (ai) prompt using the content to ground the generative ai prompt. the subset of documents may be identified based on a comparison between a vectorization of the request and the one or more vectorizations and based at least in part on a determination that a user associated with the tenant is permitted to access the subset of documents. the method may include presenting a response to the generative ai prompt, the response generated by the llm using the generative ai prompt.
20250086546. GENERATING WORKFLOWS USING MODULAR FUNCTIONS_simplified_abstract_(salesforce, inc.)
Inventor(s): Melissa Aubrie Chan of San Francisco CA (US) for salesforce, inc., Kristopher McKenney of Oakland CA (US) for salesforce, inc., Rafael Amsili of Mountain View CA (US) for salesforce, inc., Manju Vijayakumar of San Francisco CA (US) for salesforce, inc.
IPC Code(s): G06Q10/0631, G06Q10/0633, G06Q10/10
CPC Code(s): G06Q10/06316
Abstract: techniques for determining and/or utilizing various modular functions are discussed herein. in some examples, a communication platform may receive a request to generate or otherwise determine a workflow. upon receiving the request, the communication platform may display modular functions which may be used to build the workflow. in some examples, the communication platform may include modular functions specific to list virtual spaces, modular functions specific to canvas virtual spaces, and/or modular functions specific to any other type of virtual space. in some examples, a user may build a workflow using one or more modular functions corresponding to one or more virtual spaces and/or machine-learning modular functions. upon creating the workflow, a user of the communication platform may select or otherwise request that the communication platform performs the workflow. in such instances, performing the workflow may include executing the modular functions included in the workflow.
Inventor(s): Melissa Chan of San Francisco CA (US) for salesforce, inc., Jayant Tyagi of San Francisco CA (US) for salesforce, inc., Thomas Cook of San Francisco CA (US) for salesforce, inc., Rafael Amsili of Mountain View CA (US) for salesforce, inc., Horea Porutiu of Amsterdam (NL) for salesforce, inc., Manju Vijayakumar of San Francisco CA (US) for salesforce, inc., Esther Wolff of San Francisco CA (US) for salesforce, inc., Tong Yin of San Francisco CA (US) for salesforce, inc., Saurabh Sahni of Sunnyvale CA (US) for salesforce, inc., Chris Roberson of Webster NY (US) for salesforce, inc., Manuela Caicedo of New York NY (US) for salesforce, inc.
IPC Code(s): G06Q10/10, G06T17/00
CPC Code(s): G06Q10/103
Abstract: techniques for generating a structured data container configured to receive and present data associated with third-party applications are described herein. the structured data container may be shared and embedded within multiple surfaces associated with the communication platform, such as collaborative documents, virtual spaces, channels, etc. in some examples, data presented in association with the structured data container may be updated based at least in part on a triggering event such that data presented in association with the structured data container is accurate and up to date. additionally, techniques for generating templates with placeholders that can be utilized in a workflow are described herein.
20250086735. MACHINE LEARNING FOR LEGAL CLAUSE EXTRACTION_simplified_abstract_(salesforce, inc.)
Inventor(s): Sundar Ram Vedula of Bangalore (IN) for salesforce, inc., Rajdeep Dua of Hyderabad (IN) for salesforce, inc., Akash Singh of Hyderabad (IN) for salesforce, inc., Amit Kumar Dash of Bangalore (IN) for salesforce, inc., Nimesh Gupta of Bangalore (IN) for salesforce, inc., Sourav Sipani of Bangalore (IN) for salesforce, inc., Ajay Singh of Bangalore (IN) for salesforce, inc., Khyati Garg of Bangalore (IN) for salesforce, inc., Sree Harini Soma of Bangalore (IN) for salesforce, inc.
IPC Code(s): G06Q50/18
CPC Code(s): 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.
Inventor(s): Melissa Aubrie Chan of San Francisco CA (US) for salesforce, inc., Nikhil Rao of San Francisco CA (US) for salesforce, inc., Kevin Zhang of San Francisco CA (US) for salesforce, inc., David Barrett-Kahn of New York City NY (US) for salesforce, inc., Michael Hahn of San Francisco CA (US) for salesforce, inc.
IPC Code(s): G06T19/00, G06F40/166
CPC Code(s): G06T19/00
Abstract: techniques for modifying data within a virtual space are discussed herein. a communication platform may receive a request from a user profile associated with a virtual space. the request may include instruction(s) for the communication platform to perform a modifying operation on data within a virtual space. based on receiving the request, the communication platform may identify the data on which the operation is to be performed. the communication platform may input the data to one or more machine-learning models trained to output data that is a modified version of the data input to the machine-learning model (e.g., modified data). in such cases, the modified data may be modified consistent with the requested operation. the communication platform may receive the modified data from the machine-learning model and cause the modified data to be displayed via a user interface associated with the user profile.
20250087027. MACHINE LEARNING MODEL DEPLOYMENT FOR EQUIPMENT_simplified_abstract_(salesforce, inc.)
Inventor(s): Sundar Ram Vedula of Bangalore (IN) for salesforce, inc., Rajdeep Dua of Hyderabad (IN) for salesforce, inc., Mritunjay Kumar of Bangalore (IN) for salesforce, inc., Divya Rai of Bangalore (IN) for salesforce, inc., Rakesh Mondal of Bangalore (IN) for salesforce, inc., Nimesh Gupta of Bangalore (IN) for salesforce, inc.
IPC Code(s): G07C5/00, B60R16/023, G05B23/02, G06Q30/01, G08B21/18
CPC Code(s): G07C5/006
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.
Inventor(s): Melissa Aubrie Chan of San Francisco CA (US) for salesforce, inc., James Barnes of San Francisco CA (US) for salesforce, inc., Maya Aditi Holikatti of San Francisco CA (US) for salesforce, inc., Rohan Kumar Reddy Venapusala Alavalapati of Roseville CA (US) for salesforce, inc.
IPC Code(s): H04L51/48, H04L51/52
CPC Code(s): H04L51/48
Abstract: techniques for updating and/or maintaining a header of a virtual space are described herein. a communication platform may receive a request from a user profile associated with a virtual space. the request may include instructions for the communication platform perform various header updating operations. in some examples, upon receiving the request, the communication platform may identify the data (e.g., virtual space data (e.g., administrative data, user posts and/or responses, files, etc.), user data, etc.) on which to perform the header updating operation. based on identifying the data, the communication platform may input such data to one or more machine-learning models trained to output the data consistent with the requested operation. in some examples, the communication platform may receive the data from the machine-learning model and cause the data to be displayed to the associating header of the canvas.
20250088509. SYSTEM AND METHOD FOR GLOBAL RATE LIMITING_simplified_abstract_(salesforce, inc.)
Inventor(s): Daeki CHO of Bellevue WA (US) for salesforce, inc., Ran YAO of San Francisco CA (US) for salesforce, inc., Xiaoyuan ZHOU of Bellevue WA (US) for salesforce, inc., Alekhaya KONDAPURAM of San Francisco CA (US) for salesforce, inc., Tony WONG of San Francisco CA (US) for salesforce, inc., Pratima NAMBIAR of San Francisco CA (US) for salesforce, inc., Rama CHAVALI of San Francisco CA (US) for salesforce, inc.
IPC Code(s): H04L9/40, H04L69/22
CPC Code(s): H04L63/10
Abstract: disclosed herein are system, method, and computer program product embodiments for implementing global rate limiting of an api cluster capable of dynamically implementing updates without a restart of any instantiation within the api cluster. a local service includes an envoy and a customer resource definition. when an update is received, the customer resource definition identifies changes to be made to a global rate limiting service and dynamically injects those changes into the global rate limiting service. the changes can be instance-specific, with multiple different versions stored for the various instantiations within the cluster. the envoy also extracts and converts header information from a received request into one or more descriptor keys. the global rate limiting service determine global rate limiting based on a set of rules applied to the descriptor keys.
- Salesforce, Inc.
- G06F3/04842
- G06N20/00
- H04L51/02
- H04L51/52
- CPC G06F3/04842
- Salesforce, inc.
- G06F9/50
- CPC G06F9/5005
- G06F16/33
- CPC G06F16/3344
- G06F21/62
- G06F40/20
- CPC G06F21/6245
- G06F16/383
- CPC G06F40/20
- G06F40/284
- G06F16/31
- G06F40/40
- CPC G06F40/284
- G06F9/451
- G06T11/00
- CPC G06F40/40
- G06Q30/0242
- H04L67/306
- G06F40/58
- G06Q30/0203
- CPC G06F40/58
- G06N3/0455
- CPC G06N3/0455
- G06N3/0895
- G06N3/0475
- CPC G06N3/0895
- G06Q10/0631
- G06Q10/0633
- G06Q10/10
- CPC G06Q10/06316
- G06T17/00
- CPC G06Q10/103
- G06Q50/18
- CPC G06Q50/18
- G06T19/00
- G06F40/166
- CPC G06T19/00
- G07C5/00
- B60R16/023
- G05B23/02
- G06Q30/01
- G08B21/18
- CPC G07C5/006
- H04L51/48
- CPC H04L51/48
- H04L9/40
- H04L69/22
- CPC H04L63/10
