International Business Machines Corporation patent applications on August 22nd, 2024
Patent Applications by International Business Machines Corporation on August 22nd, 2024
International Business Machines Corporation: 41 patent applications
International Business Machines Corporation has applied for patents in the areas of G06N20/00 (5), G06F9/50 (3), H01L23/00 (2), H01L23/532 (2), B60K35/00 (2) G06N20/00 (4), G06F9/5027 (2), B25J9/1682 (1), H01L21/76879 (1), G06T19/006 (1)
With keywords such as: embodiment, data, device, based, include, computer, object, task, user, and machine in patent application abstracts.
Patent Applications by International Business Machines Corporation
Inventor(s): Sarbajit K. Rakshit of Kolkata (IN) for international business machines corporation
IPC Code(s): B25J9/16
CPC Code(s): B25J9/1682
Abstract: a computer-implemented method, a computer program product, and a computer system for maximizing collaborative effectiveness among multi-robots with dynamic inter-exchangeability. a computer identifies inter-exchangeable parts among robots performing an activity in a multi-robotic ecosystem. a computer uses digital twin models to simulate scenarios of combining respective ones of the inter-exchangeable parts and respective ones of the robots. a computer identifies an optimum scenario in which collaborative effectiveness is maximized by exchanging the inter-exchangeable parts among the robots, based on results of digital twin model simulations. a computer, for the optimum scenario, identifies among the robots first robots whose inter-exchangeable parts are to be exchanged and one or more second robots that help the first robots exchange the inter-exchangeable parts. a computer instructs the first robots and the one or more second robots to perform physical exchange of the inter-exchangeable parts of the first robots.
Inventor(s): Jeremy R. Fox of Georgetown TX (US) for international business machines corporation, Tushar Agrawal of West Fargo ND (US) for international business machines corporation, Sarbajit K. Rakshit of Kolkata (IN) for international business machines corporation
IPC Code(s): B29C64/393, B29C64/209
CPC Code(s): B29C64/393
Abstract: according to one embodiment, a method, computer system, and computer program product for 3d printing is provided. the present invention may include analyzing a digital model of a 3d object; identifying stresses expected to be applied to the 3d object; performing digital twin simulation of the 3d object; simulating the identified stresses on the 3d object; determining one or more reinforcement materials for the 3d object based on the simulating of the identified stresses on the 3d object; modifying the digital model of the 3d object to include the one or more determined reinforcement materials; and printing the one or more determined reinforcement materials on and/or in the 3d object.
Inventor(s): Fang Lu of Billerica MA (US) for international business machines corporation, Jeremy R. Fox of Georgetown TX (US) for international business machines corporation, Tushar Agrawal of West Fargo ND (US) for international business machines corporation, Sarbajit K. Rakshit of Kolkata (IN) for international business machines corporation
IPC Code(s): B60K35/00
CPC Code(s): B60K35/00
Abstract: a computer-implemented method generates and updates a dashboard display on an augmented reality display within a vehicle. the method includes identifying a driver of a vehicle, where the vehicle is at least partially automated. the method further includes determining a set of conditions for the vehicle. the method also includes determining a driving mode for the vehicle, where the driving mode represents a level of automation for the vehicle. the method includes analyzing, by a learning model, the set of conditions and the driving mode. the method further includes determining, in response to the analyzing, a subset of components to add to a display, where each component is selected from a set of available components associated with the vehicle. the method also includes rendering the subset of components on the display on a user interface.
Inventor(s): Tushar Agrawal of West Fargo ND (US) for international business machines corporation, Martin G. Keen of Cary NC (US) for international business machines corporation, Jeremy R. Fox of Georgetown TX (US) for international business machines corporation, Sarbajit K. Rakshit of Kolkata (IN) for international business machines corporation
IPC Code(s): B60W50/14, B60K35/00, B60W30/095, B60W50/00, G06N20/00
CPC Code(s): B60W50/14
Abstract: a computer-implemented method, a computer system and a computer program product project incident information within an augmented reality environment based on vehicle movements. the method includes determining a predicted path of a vehicle based on telemetry data associated with the vehicle. the method also includes obtaining driving conditions associated with a surrounding environment using a sensor. in addition, the method includes identifying an object in the predicted path of the vehicle. the method further includes determining a collision zone on the object and a corresponding collision zone on the vehicle based on physical attributes of the object and the predicted path of the vehicle. lastly, the method includes generating a display of the driving conditions using an augmented reality device, where the display indicates the collision zone on the object and includes a virtual model of the vehicle that indicates the corresponding collision zone on the vehicle.
Inventor(s): Rudy J. Wojtecki of San Jose CA (US) for international business machines corporation, Nelson Felix of Slingerlands NY (US) for international business machines corporation, Krystelle Lionti of San Jose CA (US) for international business machines corporation, Noel Arellano of Gilroy CA (US) for international business machines corporation
IPC Code(s): G03F7/004, G03F7/16, G03F7/20
CPC Code(s): G03F7/0045
Abstract: a surfactant or photoacid generator (pag) that forms a self-assembled monolayer is deposited on a substrate surface. application of electron beam (e-beam) and/or extreme ultraviolet (euv) radiation to the substrate surface forms a negative or positive tone pattern on the monolayer. a hydroxamic acid may be used to form a negative tone self-assembled monolayer and a silane or pag may be used to form a positive tone self-assembled monolayer. area selective deposition of an euv absorbing material on the negative or positive tone patterned monolayer forms a negative or positive tone euv absorbing mask, respectively.
Inventor(s): Anujit Rajbangshi of Bangalore (IN) for international business machines corporation, Shailendra Moyal of Pune (IN) for international business machines corporation, Sarbajit K. Rakshit of Kolkata (IN) for international business machines corporation
IPC Code(s): G05D1/00, G05D1/02, G05D1/10
CPC Code(s): G05D1/0088
Abstract: according to one embodiment, a method, computer system, and computer program product for dynamic collaboration among vehicles is provided. the embodiment may include gathering information about one or more situation areas. the embodiment may also include identifying one or more tasks required for each situation area. the embodiment may further include gauging space available in each situation area. the embodiment may also include determining responding entity requirements to complete the one or more tasks in each situation area. the embodiment may further include locating one or more responding entities that are near enough to the one or more situation areas to perform a task from the one or more tasks. the embodiment may also include determining a collaboration plan for the one or more responding entities. the embodiment may further include directing the one or more responding entities according to the collaboration plan.
Inventor(s): PIOTR P. GODOWSKI of KRAKOW (PL) for international business machines corporation, Szymon Kowalczyk of KRAKOW (PL) for international business machines corporation, Kacper Krzyzak of Kraków (PL) for international business machines corporation, Lukasz Józef Matyasik of Kraków (PL) for international business machines corporation
IPC Code(s): G06F9/445, G06F16/908
CPC Code(s): G06F9/44505
Abstract: an example operation may include one or more of identifying a pod that is within a namespace of a host platform, reading a file from a metadata storage of the pod, wherein the file that includes software definition data of the pod, identifying a field within the configuration data of the pod that contains an invalid entry based on a comparison of a value stored in the field to a predefined list of annotations, and in response to the identification of the invalid field, generating and store a log entry into a log of the pod which identifies the invalid field.
Inventor(s): Charan Acharya Chandrashekar of Bangalore (IN) for international business machines corporation, Shwetha Gopalakrishna of Bangalore (IN) for international business machines corporation, Sudhakar T. Seshagiri of Bangalore (IN) for international business machines corporation, Prasanna Alur Mathada of Bangalore (IN) for international business machines corporation
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5027
Abstract: balancing computational loading across uav-mec devices by receiving information associated with a data processing task, determining a first computational loading associated with the data processing task relative to a capacity of a first device, sending the first computational loading and a first location to a second device, determining that the second device can support the first computational loading, deploying, the second device to the first location, and completing the first computational task using the first device and the second device.
Inventor(s): Swaminathan Balasubramanian of Troy MI (US) for international business machines corporation, Pierre C. Berlandier of San Diego CA (US) for international business machines corporation, Renganathan Sundararaman of Cary NC (US) for international business machines corporation, Gayatri Renganathan of Cary NC (US) for international business machines corporation, Rajiv Joshi of Yorktown Heights NY (US) for international business machines corporation
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5027
Abstract: an embodiment for maintaining service level objectives in container orchestration platforms using constraint propagation. the embodiment may receive a set of service level objectives associated with deployment of an application. the embodiment may determine a series of resource dependencies corresponding to the received set of service level objectives for the application. the embodiment may generate a first set of constraints corresponding to service requirements for the received set of service level objectives. the embodiment may generate a second set of constraints corresponding to relationships within a target cluster between the target cluster resources and the series of resource dependencies. the embodiment may detect violations of the first set of constraints, and then determine one or more remediation measures to restore the received set of service level objectives based on the second set of constraints to output the one or more remediation measures to an end user.
Inventor(s): Marcelo Carneiro Do Amaral of Tokyo (JP) for international business machines corporation, Huamin Chen of Westford MA (US) for international business machines corporation
IPC Code(s): G06F9/50
CPC Code(s): G06F9/5094
Abstract: computer-implemented methods for estimating energy consumption of a workload in a cloud computing system are provided. aspects include periodically collecting an energy consumption data for the workload, creating a first model based on the energy consumption data corresponding to a first duration, and creating a second model based on the energy consumption data corresponding to a second duration, wherein the second duration is longer than the first duration. aspects also include receiving a request for an estimated energy consumption of a workload during a time period and calculating a first estimated energy consumption of the workload during the time period based on the first model. aspects further include calculating a second estimated energy consumption of the workload during the time period based on the second model and calculating a combined estimated energy consumption of the workload based on the first estimate and the second estimate.
Inventor(s): Reinhold Geiselhart of Rottenburg (DE) for international business machines corporation, Felix Beier of Haigerloch (DE) for international business machines corporation, Knut Stolze of Hummelshain (DE) for international business machines corporation, Luis Eduardo Oliveira Lizardo of Boeblingen (DE) for international business machines corporation
IPC Code(s): G06F9/54
CPC Code(s): G06F9/542
Abstract: modifying original computer-generated messages is provided. an original computer-generated message is modified by at least one of replacing text or appending text of the original computer-generated message according to instructions located in a structure of a selected modification layer to form a modified computer-generated message corresponding to a current user-system context of a user of the computer system. the modified computer-generated message corresponding to the current user-system context of the user is output.
Inventor(s): Louis P. GOMES of Poughkeepsie NY (US) for international business machines corporation, David Harold SURMAN of Milton NY (US) for international business machines corporation, Seth E. LEDERER of Staatsburg NY (US) for international business machines corporation, James H. MULDER of Wappingers Falls NY (US) for international business machines corporation
IPC Code(s): G06F11/14, G06F9/4401
CPC Code(s): G06F11/1438
Abstract: an instruction that includes an operation code indicating a diagnose operation is obtained and executed within a computing environment. the executing the instruction includes retrieving selected data from a dump save area to be used to restore machine state and restoring the machine state. the restoring includes storing the selected data in a selected location. one or more storage keys used to protect access to the selected data are restored.
Inventor(s): Hubertus Franke of Cortlandt Manor NY (US) for international business machines corporation, MARCIO AUGUSTO DE LIMA E SILVA of Mogi das Cruzes (BR) for international business machines corporation, Tobin Feldman-Fitzthum of New York NY (US) for international business machines corporation, Krishna Thangaraj of San Jose CA (US) for international business machines corporation
IPC Code(s): G06F16/215, G06F16/21
CPC Code(s): G06F16/215
Abstract: storing compressed data objects by decompressing a first data object, identifying, differences between the first and second data objects, creating a new version of the second data object according to the differences, the first data object, and a reference object, and storing the first data object and the new version of the second data object.
Inventor(s): Xiao Xiao CHEN of Beijing (CN) for international business machines corporation, Peng Hui JIANG of Beijing (CN) for international business machines corporation, Sheng Yan SUN of Beijing (CN) for international business machines corporation, Ying ZHANG of Beijing (CN) for international business machines corporation
IPC Code(s): G06F16/242, G06F16/28
CPC Code(s): G06F16/2433
Abstract: a method, system, and computer program product that are configured to: receive a structured query language (sql) statement including placeholders; generate sets of predicted values for the placeholders; generate candidate access paths in a database using the sets of predicted values; receive a query including the sql statement with actual values instead of the placeholders; select one of the candidate access paths based on determining similarities of the actual values to ones of the sets of predicted values; in response to the selected one of the candidate access paths being acceptable, execute the query using the selected one of the candidate access paths; and in response to the selected one of the candidate access paths not being acceptable, generate a new access path in the database using the actual values, and execute the query using the new access path.
Inventor(s): Bo-Yu Kuo of Kaohsiung (TW) for international business machines corporation, Yu-Jin Chen of New Taipei City (TW) for international business machines corporation, Yu-Chi Tang of New Taipei City (TW) for international business machines corporation, Shih Hsuan Lee of Zhuangwei (TW) for international business machines corporation
IPC Code(s): G06F21/55, G06N3/0442, G06N3/08
CPC Code(s): G06F21/552
Abstract: techniques are described with regard to addressing structured false positives in the context of detecting asset anomalies in a computing environment. an associated computer-implemented method includes applying an anomaly detection machine learning model to each of a plurality of assets in order to determine a plurality of anomaly assets among the plurality of assets. the plurality of anomaly assets are determined based upon a model anomaly risk score calculated for each of the plurality of assets consequent to asset event data analysis. the method further includes calculating a structured false positive score for each of the plurality of anomaly assets during a current structured false positive time window. the method further includes retraining the anomaly detection machine learning model responsive to determining that a threshold value of anomaly assets among the plurality of anomaly assets have a structured false positive score exceeding a structured false positive threshold value.
Inventor(s): Jin Shi of Ningbo (CN) for international business machines corporation, CHIH-YUAN LIN of New Taipei City (TW) for international business machines corporation, Shu-Chih Chen of New Taipei City (TW) for international business machines corporation, Chao Yuan Huang of Taipei (TW) for international business machines corporation, PEI-YI LIN of New Taipei City 234 (TW) for international business machines corporation
IPC Code(s): G06F40/35, G06F3/0481, G06F3/04842, G06F40/205
CPC Code(s): G06F40/35
Abstract: a method, computer system, and a computer program product for task assistance is provided. the present invention may include acquiring a request expression input by a user. the present invention may include identifying a request intent associated with a task based on the request expression. the present invention may include determining a response script corresponding to the request intent. the present invention may include executing the response script to complete the task and presenting the process of running the task in a user-interface (ui).
Inventor(s): Balaji Ganesan of Bengaluru (IN) for international business machines corporation, Muhammed Abdul Majeed Ameen of Kozhikode (IN) for international business machines corporation, Aniket Saxena of Ghaziabad (IN) for international business machines corporation, Arvind Agarwal of New Delhi (IN) for international business machines corporation, Priyanka Telang of Bengaluru (IN) for international business machines corporation, Soma Shekar Naganna of Bangalore (IN) for international business machines corporation
IPC Code(s): G06N3/08
CPC Code(s): G06N3/08
Abstract: a computer-implemented method, system and computer program product for performing semantic matching in a data fabric. knowledge graphs are populated with metadata enriched with master data. based on such knowledge graphs with the metadata enriched with the master data, a trained multi-layer graph neural network generates embeddings. furthermore, behavioral metadata from data stewards are monitored and collected. such behavioral metadata may be used to enrich metadata, which are populated in knowledge graphs which are inputted into the multi-layer graph neural network to generate embeddings. upon generating the embeddings discussed above, semantic matching of the data assets in the data fabric using the embeddings is performed. in this manner, semantic matching of the data assets in the data fabric is more effectively performed by utilizing master data and behavioral metadata.
Inventor(s): Bogdan Cezar Zota of Rueschlikon (CH) for international business machines corporation, Eunjung Cha of Adliswill (CH) for international business machines corporation, Thomas Morf of Gross (CH) for international business machines corporation, Mridula Prathapan of Adliswil (CH) for international business machines corporation, Peter Mueller of Zurich (CH) for international business machines corporation, Alberto Ferraris of Langnau am Albis (CH) for international business machines corporation
IPC Code(s): G06N10/40
CPC Code(s): G06N10/40
Abstract: embodiments including a semiconductor device circuit for biasing gates of a qubit device as well as a method for operating the device are disclosed. the embodiments may include a multiplexed array of capacitor cells, where each capacitor cell includes a transistor-controlled capacitor, where each capacitor is connected between a drain of a respective transistor and ground, where each source of all transistors of all capacitor cells are connected to a common control point, and where each gate of the transistors of the capacitor cells are individually voltage controllable. the embodiment may include a charging unit connected to the common control point, and a discharging unit connected to the common control point, where the charging unit and the discharging unit are alternatively activatable.
Inventor(s): Kushal S. Patel of Pune (IN) for international business machines corporation, Gandhi Sivakumar of Bentleigh (AU) for international business machines corporation, Sarvesh S. Patel of Pune (IN) for international business machines corporation
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: by analyzing a dataset usable to train a model to perform a task, metadata of the dataset is generated, the generating performed responsive to receiving the dataset. the dataset is classified into a domain using the metadata and a set of context definitions. responsive to receiving a request from the model for use of the dataset, the model is caused to be trained using the dataset, the training enabling the model to perform the task.
Inventor(s): Prem Piyush GOYAL of Hyderabad (IN) for international business machines corporation, Harivansh KUMAR of Hyderabad (IN) for international business machines corporation, Manish Anand BHIDE of Hyderabad (IN) for international business machines corporation
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: a machine learning model is trained. a set of drifted records are determined during payload time of the machine learning model. the determined set of drifted records are pruned to use in retraining of the machine learning model.
Inventor(s): Jeremy R. Fox of Georgetown TX (US) for international business machines corporation, Su Liu of Austin TX (US) for international business machines corporation, Tushar Agrawal of West Fargo ND (US) for international business machines corporation, Sarbajit K. Rakshit of Kolkata (IN) for international business machines corporation, Michael Boone of Lutz FL (US) for international business machines corporation
IPC Code(s): G06N20/00
CPC Code(s): G06N20/00
Abstract: managing machine layouts to improve machine activity workflows is provided. an analysis of a digital twin simulation of an environment is performed in accordance with a machine activity workflow corresponding to a plurality of machines located in the environment. a machine layout is generated for the environment that includes at least one of a particular set of machines having a determined amount of computational capability needed to analyze a type, volume, and frequency of data generated in each logical group of machines within the environment based on the analysis of the digital twin simulation. the machine layout is implemented automatically in the environment by positioning the at least one of the particular set of machines having the determined amount of computational capability needed to analyze the type, volume, and frequency of the data generated in each logical group of machines within the environment.
Inventor(s): Sathya Santhar of Chennai (IN) for international business machines corporation, Sridevi Kannan of Chennai (IN) for international business machines corporation, Suvedhahari Velusamy of Irving TX (US) for international business machines corporation, Samuel Mathew Jawaharlal of Chennai (IN) for international business machines corporation
IPC Code(s): G06N20/00, G06N7/01
CPC Code(s): G06N20/00
Abstract: one or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to a process to facilitate learning a model for clustered encoding and decoding from a latent probability distribution. a computer implemented method can comprise mapping, by a system operatively coupled to a processor, high-dimensional modalities of data from one or more latent probability distributions corresponding to a plurality of encoder and decoder pairs to a plurality of independent latent spaces. the computer implement method can also comprise mapping, by the system, the plurality of independent latent spaces to a common latent space representing one or more features of one or more input classes associated with the plurality of encoder and decoder pairs.
Inventor(s): Seshu Tirupathi of Dublin (IE) for international business machines corporation, Amadou Ba of Navan (IE) for international business machines corporation, Marco Luca Sbodio of Castaheany (IE) for international business machines corporation, Yufang Hou of Dublin (IE) for international business machines corporation, Venkata Sitaramagiridharganesh Ganapavarapu of Elmsford NY (US) for international business machines corporation
IPC Code(s): G06N20/20
CPC Code(s): G06N20/20
Abstract: an embodiment for automatically forecasting and mitigating concept drift in machine learning models using natural language processing. the embodiment may automatically detect features and variables considered by a target machine learning model. the embodiment may automatically store and update a configurable corpus of relevant documents pertaining to a domain of the target machine learning model. the embodiment may automatically extract event types and corresponding time stamps from the configurable corpus of relevant documents. the embodiment may automatically correlate the extracted event types with drift detection probabilities to detect expected concept drift in the target machine learning model at a given timestamp. the embodiment may automatically generate an ensemble of replacement models based on probabilities derived from a historical database of models including corresponding keys given by event types. the embodiment may automatically retrain or replace the target machine learning model at the given timestamp.
Inventor(s): Bader Ali-Saleh of Houston TX (US) for international business machines corporation, Brent William Yardley of Hillsboro OR (US) for international business machines corporation, Matthew Husley Caughman of Houston TX (US) for international business machines corporation, Franck Excoffier of Katy TX (US) for international business machines corporation, Rayyan Memon of Fulshear TX (US) for international business machines corporation
IPC Code(s): G06Q10/0631, G06Q10/0635
CPC Code(s): G06Q10/06312
Abstract: transferring data workloads is provided. a factor comparison is performed between each of a plurality of site profiles and a customer profile. a factor matching score is generated for each respective site profile of the plurality of site profiles based on the factor comparison. it is determined whether the factor matching score corresponding to a particular site profile is greater than or equal to a predefined minimum factor matching score threshold level. the particular site profile having the factor matching score greater than or equal to the predefined minimum factor matching score threshold level is selected as a recommended site profile for transferring a data workload of a customer to a set of target sites from a current site running the data workload. the recommended site profile is sent to a client device corresponding to the customer via a network.
Inventor(s): Krishnasuri Narayanam of Bangalore (IN) for international business machines corporation, Vinayaka Pandit of Bangalore (IN) for international business machines corporation, Sandeep Nishad of Bangalore (IN) for international business machines corporation, Venkatraman Ramakrishna of Bangalore (IN) for international business machines corporation, Dhinakaran Vinayagamurthy of Erode (IN) for international business machines corporation
IPC Code(s): G06Q20/38
CPC Code(s): G06Q20/389
Abstract: a group of transactions to be rolled back in a blockchain ledger can be identified. whether the transactions in the group are eligible to be rolled back together can be determined. other transactions can be recommended, and the other transactions may be added to the group to be rolled back together. a rollback transaction can be added to the blockchain ledger that rolls back effect of the transactions, where the rollback transaction has zero or more inputs and zero or more output, the rollback transaction having at least one selected from at least one input and at least one output. an unspent output of a transaction in the group is provided as an input of the rollback transaction. input of a transaction in the group, that is not an output of another transaction in the group, is provided as an output of the rollback transaction.
Inventor(s): Hua Ni of Chantilly VA (US) for international business machines corporation, Yi-Hui Ma of Mechanicsburg PA (US) for international business machines corporation, Eugene Irving Kelton of Wake Forest NC (US) for international business machines corporation
IPC Code(s): G06Q20/40
CPC Code(s): G06Q20/4016
Abstract: an embodiment includes assigning an entity to a risk category group based on transaction data of a transaction alert associated with the entity, where the transaction alert is concerning potentially suspicious financial activities. the embodiment also identifies a relationship between the entity and another entity based on the transaction data. the embodiment determines a capability of an anti-money laundering (“aml”) analyst, where the capability includes a skill level of the aml analyst. the embodiment generates task allocation data by optimizing an objective function, where the optimizing includes solving the objective function subject to a set of optimization constraints, where the set of optimization constraints includes the risk category group, the relationship between the entities, and the capability of the aml analyst. the embodiment also includes routing the transaction data of the transaction alert to the aml analyst based on the task allocation data.
Inventor(s): Sarbajit K. RAKSHIT of Kolkata (IN) for international business machines corporation, Vinod A. VALECHA of Pune (IN) for international business machines corporation
IPC Code(s): G06T19/00, G06F3/16, G06T7/70, H04N23/23
CPC Code(s): G06T19/006
Abstract: a computational device of a virtual reality system receives a volumetric video that captures visual information of a physical environment. the computational device of the virtual reality system receives non-visual information of the physical environment. the volumetric video is integrated with the non-visual information to generate a volumetric video augmented with non-visual information in which navigation is performed in the virtual reality system.
Inventor(s): Takayuki Katsuki of Tokyo (JP) for international business machines corporation, Haoxiang Qiu of Tokyo (JP) for international business machines corporation, Tomoya Sakai of Tokyo (JP) for international business machines corporation, Tadanobu Inoue of Yokohama (JP) for international business machines corporation
IPC Code(s): G06V10/82, G06V10/774
CPC Code(s): G06V10/82
Abstract: a computer-implemented method for domain adaptation of an object detection model includes obtaining a domain vector for a domain from one or more images in the domain, the domain vector representing the property of the domain. the domain vector is input into a fully connected layers in the object detection model. a domain-specific result of the object detection model is provided as output. the method can further include computing a domain tensor and inputting the domain tensor into convolutional layers in the object detection model.
Inventor(s): Ying LI of SHANGHAI (CN) for international business machines corporation, Liu Yao HE of Beijing (CN) for international business machines corporation, Di HU of Zhuqiao (CN) for international business machines corporation, Xiao Feng JI of Shanghai (CN) for international business machines corporation
IPC Code(s): G06V30/416, G06F16/31
CPC Code(s): G06V30/416
Abstract: a present invention embodiment analyzes documents. a first document is received comprising a plurality of sentences that each include one or more words. a matrix is populated with the plurality of sentences, wherein each of the one or more words of each sentence in the matrix is encoded as a numerical value. the matrix is processed using a machine learning model to generate a first feature map. the first feature map is compared to a second feature map of a corresponding second document to identify a shared document element between the first document and the second document based on a common feature in the first feature map and the second feature map. the shared document element is indicated via a user interface.
Inventor(s): Sumeet Surendra Kapoor of Pune (IN) for international business machines corporation, Snehal U. Pansare of Pune (IN) for international business machines corporation, Rachana Vishwanathula of Hyderabad (IN) for international business machines corporation, Manoj Panda of Bangalore (IN) for international business machines corporation
IPC Code(s): G09B5/02
CPC Code(s): G09B5/02
Abstract: a computer-implemented method, according to one embodiment, includes collecting user data associated with a first user's thoughts and/or experience with a first activity, and receiving, from a neural device paired with the first user, cognitive information about the first activity. the method further includes generating, based on the collected user data and the cognitive information, a scene set in a training environment based on the first activity. the generated scene is output to a hologram device for displaying the scene for the first user. a computer program product, according to another embodiment, includes a computer readable storage medium having program instructions embodied therewith. the program instructions are readable and/or executable by a computer to cause the computer to perform the foregoing method.
Inventor(s): Michelle Brachman of Quincy MA (US) for international business machines corporation, James Johnson of Somerville MA (US) for international business machines corporation, Qian Pan of Canton MA (US) for international business machines corporation, Casey Dugan of Cambridge MA (US) for international business machines corporation
IPC Code(s): G10L15/22, G10L15/07
CPC Code(s): G10L15/22
Abstract: a present invention embodiment analyzes user input via natural language processing. a natural language utterance from a user is analyzed to determine one or more computing tasks. the natural language utterance is analyzed using a knowledge base to identify one or more modifications to the natural language utterance that are based on previous user modifications to a previous user utterance. an indication that the user accepted at least one modification of the one or more modifications is received, wherein the at least one modification modifies the one or more computing tasks. the modified one or more computing tasks are executed.
Inventor(s): Oscar van der Straten of Guilderland Center NY (US) for international business machines corporation, Shanti Pancharatnam of Albany NY (US) for international business machines corporation, Chih-Chao Yang of Glenmont NY (US) for international business machines corporation
IPC Code(s): H01L21/768, H01L23/522, H01L23/528, H01L23/532
CPC Code(s): H01L21/76879
Abstract: a semiconductor structure that includes: a plurality of metal wires, and at least one dielectric substrate surrounding the plurality of metal wires. each of the plurality of metal wires includes a tapered upper portion, a tapered lower portion, and a middle portion between the tapered upper portion and the tapered lower portion that is wider than the tapered upper and lower portions.
Inventor(s): John Knickerbocker of Monroe NY (US) for international business machines corporation, Mukta Ghate Farooq of HOPEWELL JCT NY (US) for international business machines corporation, Keiji Matsumoto of Yokohama-shi (JP) for international business machines corporation
IPC Code(s): H01L23/31, H01L21/56, H01L23/00, H01L23/29, H01L23/367
CPC Code(s): H01L23/3185
Abstract: a semiconductor integrated circuit device includes a first back-end-of-line region coupled to a first side of a front-end-of-line region, a second back-end-of-line region coupled to a second side of the front-end-of-line region, and a thermally conducting solder at least partially surrounding a perimeter of the front-end-of-line region, the first back-end-of-line region and the second back-end-of-line region.
Inventor(s): Yann Mignot of Slingerlands NY (US) for international business machines corporation, Chanro Park of Clifton Park NY (US) for international business machines corporation, Koichi Motoyama of Clifton Park NY (US) for international business machines corporation, John Christopher Arnold of North Chatham NY (US) for international business machines corporation
IPC Code(s): H01L23/528, H01L21/768, H01L23/522, H01L23/532
CPC Code(s): H01L23/5283
Abstract: a semiconductor structure is presented including a metal layer having a first pattern, a metal bridge located within the first pattern, at least one via disposed on a portion of the metal layer such that the metal bridge extends to a top surface of the at least one via, and a metal cap disposed directly on top of the at least one via disposed on the portion of the metal layer.
Inventor(s): Toyohiro Aoki of Yokohama (JP) for international business machines corporation, Katsuyuki Sakuma of Fishkill NY (US) for international business machines corporation, Hiroyuki Mori of Yasu-shi (JP) for international business machines corporation, Koki Nakamura of Kawasaki (JP) for international business machines corporation, Takashi Hisada of Hachiouji-shi (JP) for international business machines corporation
IPC Code(s): H01L23/00, H01L21/48, H01L23/498
CPC Code(s): H01L24/13
Abstract: methods, systems, and structures relating to flip-chip bonding are described. a processor can determine a plurality of target solder volumes to be deposited on a plurality of pads on a surface of a substrate. the plurality of target solder volumes can be variable among the plurality of pads. the processor can determine different thicknesses of different portions of a layer of resist to be deposited across the surface of the substrate. the different thicknesses can define a plurality of solder resist openings having sizes that comply with the plurality of target solder volumes.
20240282860. NONLINEAR CHANNEL_simplified_abstract_(international business machines corporation)
Inventor(s): Ruilong Xie of Niskayuna NY (US) for international business machines corporation, Julien Frougier of Albany NY (US) for international business machines corporation, Susan Ng Emans of Albany NY (US) for international business machines corporation, Andrew M. Greene of Slingerlands NY (US) for international business machines corporation
IPC Code(s): H01L29/78, H01L21/308, H01L29/66
CPC Code(s): H01L29/7853
Abstract: a finfet that includes a nonlinear channel is presented. the nonlinear channel includes one or more arced, curved, segmented, or the like, sidewall(s) that define a channel width and a channel length. the nonlinear channel provides a relatively increased channel length compared to a linear fin that is orientated orthogonal to the gate width. as such, channel length of the nonlinear channel may be relatively increased within the confines of the gate. in other words, short channel effects may be limited due to a reduced electric field along the nonlinear channel due to the relatively increased channel or fin length within the footprint of the gate.
Inventor(s): Su Liu of Austin TX (US) for international business machines corporation, Jeremy R. Fox of Georgetown TX (US) for international business machines corporation, Tushar Agrawal of West Fargo ND (US) for international business machines corporation, Zachary A. Silverstein of Georgetown TX (US) for international business machines corporation
IPC Code(s): H04B7/0426, H04W16/18, H04W16/22
CPC Code(s): H04B7/043
Abstract: a method for configuring beamforming for a network device is disclosed. in one embodiment, such a method includes creating a map of an area in which a network device that supports beamforming is placed. the method shows, on an interactive display device, the network device on the map. the method shows, on the interactive display device, one or more beams emanating from the network device on the map. the method enables a user to manipulate the beams on the interactive display device to create a desired beamforming pattern that takes into account the map and receiving devices located in the area. the claimed method is advantageous in that it may enable a user to establish or modify a beamforming pattern in a more intuitive, visual way. a corresponding system and computer program product are also disclosed.
Inventor(s): Su Liu of Austin TX (US) for international business machines corporation, John A. Walicki of Ridgewood NJ (US) for international business machines corporation, NEIL DELIMA of Scarborough (CA) for international business machines corporation, David Jason Hunt of Kirkwood MO (US) for international business machines corporation
IPC Code(s): H04L41/0806
CPC Code(s): H04L41/0806
Abstract: according to one embodiment, a method, computer system, and computer program product for managing application deployment among edge devices is provided. the embodiment may include identifying respective computing characteristics of all edge devices of a network. the embodiment may include categorizing the edge devices into one or more categories based on identified respective computing characteristics. the embodiment may include classifying a type of a computing task to be deployed to one or more of the edge devices. the embodiment may include mapping the computing task to a category of the one or more categories. the embodiment may include calculating a respective computing score for each edge device of the category. the embodiment may include ranking edge devices of the category based on their respective computing scores. the embodiment may include deploying the computing task to a top-ranked edge device of the category.
Inventor(s): Marc Velasco of Orange CA (US) for international business machines corporation, Rafael Fernandez of Durham NC (US) for international business machines corporation, James Hutchison of tonawanda NY (US) for international business machines corporation, Kassandra Aysh Perez of Austin TX (US) for international business machines corporation
IPC Code(s): H04L9/40
CPC Code(s): H04L63/083
Abstract: an embodiment includes extracting network layer information and application layer information from within a network packet. the embodiment determines a context of a network connection with a client device from which the network packet originated based at least in part on the network layer information and determines an identity of an end user with whom the network packet is associated based at least in part on the application layer information. the embodiment performs a sign-on process that authenticates the identified end user and authorizes, at a session level, the identified end user to access a particular resource of the network. the embodiment also performs a program-level authorization process that determines whether to provide program-level authorization to the identified end user based on a comparison of the context of the network connection with a context policy of the particular resource of the network.
Inventor(s): Sudheesh S. Kairali of Kozhikode (IN) for international business machines corporation, Sarbajit K. Rakshit of Kolkata (IN) for international business machines corporation
IPC Code(s): H04L67/101, H04L67/1008
CPC Code(s): H04L67/101
Abstract: a computer-implemented method for distributing packets for smart switching is provided. the computer-implemented method includes checking whether an edge device will complete a task relative to a data warehouse while having networking availability, deciding to proceed with the task using an extract, transform, load (etl) strategy based on a determination that the edge device will complete the task while having the networking availability, checking whether the edge device will complete data extraction of the task while having the networking availability based on a determination that the edge device will not complete the task while having the networking availability and deciding to proceed with the data extraction using an extract, load, transform (elt) strategy based on a determination that the edge device will complete the data extraction of the task while having the networking availability.
Inventor(s): Min Gyu Sung of Latham NY (US) for international business machines corporation, Julien Frougier of Albany NY (US) for international business machines corporation, Ruilong Xie of Niskayuna NY (US) for international business machines corporation, Chanro Park of Clifton Park NY (US) for international business machines corporation, Juntao Li of Cohoes NY (US) for international business machines corporation
IPC Code(s): H10B99/00
CPC Code(s): H10B99/22
Abstract: a semiconductor structure includes an access transistor, a first memory device connected to a first side of the access transistor, and a second memory device connected to a second side of the access transistor. in some embodiments, the first memory device is connected to a first end of a first source/drain region of the access transistor and the second memory device is connected to a second end of the first source/drain region of the access transistor. in other embodiments, the first memory device is connected to a first source/drain region of the access transistor and the second memory device is connected to a second source/drain region of the access transistor.
International Business Machines Corporation patent applications on August 22nd, 2024
- International Business Machines Corporation
- B25J9/16
- CPC B25J9/1682
- International business machines corporation
- B29C64/393
- B29C64/209
- CPC B29C64/393
- B60K35/00
- CPC B60K35/00
- B60W50/14
- B60W30/095
- B60W50/00
- G06N20/00
- CPC B60W50/14
- G03F7/004
- G03F7/16
- G03F7/20
- CPC G03F7/0045
- G05D1/00
- G05D1/02
- G05D1/10
- CPC G05D1/0088
- G06F9/445
- G06F16/908
- CPC G06F9/44505
- G06F9/50
- CPC G06F9/5027
- CPC G06F9/5094
- G06F9/54
- CPC G06F9/542
- G06F11/14
- G06F9/4401
- CPC G06F11/1438
- G06F16/215
- G06F16/21
- CPC G06F16/215
- G06F16/242
- G06F16/28
- CPC G06F16/2433
- G06F21/55
- G06N3/0442
- G06N3/08
- CPC G06F21/552
- G06F40/35
- G06F3/0481
- G06F3/04842
- G06F40/205
- CPC G06F40/35
- CPC G06N3/08
- G06N10/40
- CPC G06N10/40
- CPC G06N20/00
- G06N7/01
- G06N20/20
- CPC G06N20/20
- G06Q10/0631
- G06Q10/0635
- CPC G06Q10/06312
- G06Q20/38
- CPC G06Q20/389
- G06Q20/40
- CPC G06Q20/4016
- G06T19/00
- G06F3/16
- G06T7/70
- H04N23/23
- CPC G06T19/006
- G06V10/82
- G06V10/774
- CPC G06V10/82
- G06V30/416
- G06F16/31
- CPC G06V30/416
- G09B5/02
- CPC G09B5/02
- G10L15/22
- G10L15/07
- CPC G10L15/22
- H01L21/768
- H01L23/522
- H01L23/528
- H01L23/532
- CPC H01L21/76879
- H01L23/31
- H01L21/56
- H01L23/00
- H01L23/29
- H01L23/367
- CPC H01L23/3185
- CPC H01L23/5283
- H01L21/48
- H01L23/498
- CPC H01L24/13
- H01L29/78
- H01L21/308
- H01L29/66
- CPC H01L29/7853
- H04B7/0426
- H04W16/18
- H04W16/22
- CPC H04B7/043
- H04L41/0806
- CPC H04L41/0806
- H04L9/40
- CPC H04L63/083
- H04L67/101
- H04L67/1008
- CPC H04L67/101
- H10B99/00
- CPC H10B99/22
