52 results about "Artificial intelligence software" patented technology

Techniques for leveraging a large language model (LLM) in software development are described. A description of an error message associated with a software system hosted by the multi-tenant provider network is received. An LLM is prompted with an analysis prompt to generate an analysis of the error message, the analysis prompt including the description of the error message, and the analysis of the error message is received from the LLM. The LLM is prompted with a suggested resolution prompt to generate a suggested resolution to a cause of the error message, the suggested resolution prompt including the description of the error message and the analysis of the error message, and the suggested resolution is received from the LLM. A change to resolve the cause of the error message is sent to an originator of the received description, the change based at least in part on the suggested resolution.

Techniques for leveraging a large language model (LLM) in software development are described. A description of a software development task is received from a user. Data associated with the software system is obtained from a data source. An LLM is prompted to identify at least one aspect of the task which requires clarification from the user, at least partly by providing the obtained data to the LLM and asking the LLM to identify a question for the user which remains unanswered by the obtained data. The question is presented to the user. An answer to the question is received from the user. The LLM is prompted to respond to propose an implementation of the task at least partly based on the data associated with the software system and the answer received from the user. The proposed implementation is received from the LLM and caused to be displayed to the user.

Techniques for displaying a graphical user interface of a software development system are described. An initial description of an initial structure of a software system is obtained, the initial description including an identification of interconnections amongst provider network resources that form the initial structure. A modified description of a modified structure of the software system is obtained, the modified structure based on at least a change to the initial structure of the software system described in the initial description. A difference between the initial description and the modified description is determined. An electronic device is caused to display a graphical user interface including a visual depiction of the initial structure of the software system and an indication of the difference, the visual depiction based at least in part on the initial description.

A unified virtual background image is generated for multiple participants of a video conference to create an immersive conference experience based on its use within video streams of those multiple participants. Generative artificial intelligence software associated with a conferencing system obtains input associated with a video conference. The generative artificial intelligence software generates a virtual background image based on the input. The virtual background image is then for use within multiple participant video streams during the video conference

To reduce labor related to an update of an encryption key in response to an encryption request for the AI software specifying the third type key, encryption key leakage or the like.An information processing apparatus according to the present technology includes an encryption key creation part that creates an encryption key on a basis of a first type key stored in advance in an imaging apparatus, a second type key different from the first type key, and a third type key that is different from the first type key and the second type key and is a key multiplied with the second type key to create a combination key stored in the imaging apparatus, or is a key stored in the imaging apparatus together with the second type key, as an encryption key used by the imaging apparatus for encryption of artificial intelligence (AI) software including at least software of an artificial intelligence model, the imaging apparatus performing image recognition processing using the artificial intelligence model on a captured image obtained by capturing an image of a subject, the encryption key creation part creating, in response to specification of a key derived from new information different from original information as the third type key, a new encryption key based on the third type key derived from the new information, the first type key, and the second type key on a basis of the new information.

The invention provides a gray-based continuous deployment method, device and equipment, a medium and a program product, which can be applied to the technical fields of artificial intelligence and software development. The method comprises the following steps: acquiring a first deployment strategy corresponding to a first deployment task, wherein the first deployment strategy comprises the number of nodes participating in gray deployment and the proportion of nodes of different risk levels; selecting nodes from the node pools of different risk levels according to a first deployment strategy to obtain a target batch of nodes; executing the first deployment task in the target batch node; wherein the node pools with different risk levels are obtained by continuously updating according to a second trigger logic, and the updating process of the node pools with different risk levels comprises the following steps: dividing the plurality of nodes into the node pools with different risk levels based on the node features of the plurality of nodes by using a trained risk prediction model, wherein the node features of the plurality of nodes are obtained by continuously updating according to the first trigger logic.

A system and method of encoding and decoding using generative AI for compression of video stream uses the system for encoding and decoding using generative AI for compression of video stream that comprises a camera, an encoder comprising generative artificial intelligence (AI) software operative in the encoder to encode video data, a transmitter, a receiver, a processor, a decoder, and a visual display operatively in communication with the decoder. Using the system, video data obtained from the camera are provided to the encoder; the generative artificial intelligence (AI) software encodes the video data at encoder to produce a compressed data set; the compressed data set are transmitted in a kilobit per second range (kbps-range) bandwidth at a low bandwidth using transmitter and receiver and, subsequently, from the receiver to a distant site via a further data network; and the compressed data set decoded at the distant site.

A system and method for improving generative artificial intelligence (AI) software application response is provided. The method includes: receiving a query directed to a generative AI software application; receiving a response to the query, the response generated by the generative AI software application; generating a first contextual value based on the received query; generating a second contextual value based on the received response; generating a verification score based on the first contextual value and the second contextual value; and initiating a mitigation action in response to detecting that the verification score is below a predetermined threshold

Various embodiments of the present disclosure include systems, methods, and / or apparatuses for executing an agentic-AI-based software modernization system. An example system may be configured to receive one or more portions of monolithic legacy code of a legacy software program product, the monolithic legacy code comprising a plurality of code segments, group the monolithic legacy code by functionally related code segments of the plurality of code segments to define a plurality of groups, generate an API for each identified group, generate modern microservice code for each identified group to define a modernized software program product, and validate the modernized software program product.

A method for secure collection of sensitive data at a computer device includes receiving a request for sensitive data. The request indicates a set of parameters and a dynamic encryption key. The dynamic encryption key is generated by an authorized data requester based on a login session identifier. The method includes creating a user interface for collecting the set of parameters by an artificial intelligence (AI) software of the computer device. The method includes providing the user interface for collecting the set of parameters. Responsive to collecting the set of parameters from the user, the method includes encrypting the set of parameters using the dynamic encryption key and an encryption algorithm associated with the authorized data requester. The method includes transmitting the encrypted set of parameters to the authorized data requester to be decrypted.

A virtual background image used with a video stream of a conference participant during a video conference is updated to visually represent one or more key points of the video conference. Generative artificial intelligence software associated with a conferencing system evaluates content of a video conference to determine one or more key points related to the video conference. The generative artificial intelligence software updates a virtual background image of a participant of the video conference to include one or more visual elements representing the one or more key points. The updated virtual background image is then output for use within a video stream of the participant during the video conference.

An artificial intelligence (AI) software product for providing scalable intelligent video surveillance for the artificial intelligence of things. The AI software product performs operations including receiving, at an edge node, a sequence of images of a target environment, where the AI software product resides in the edge node, and where the edge node is local to the target environment. The AI software product further observes one or more target objects in the sequence of images of the target environment in real time. The AI software product further detects at the edge node one or more anomalies in the target environment based on the observing of the one or more target objects in real time, where the one or more anomalies are specific to the target environment.

The application relates to the technical field of artificial intelligence assisted software engineering, and discloses a management method and system based on artificial intelligence software development, which comprises the following steps: collecting multidimensional data in development, testing and running stages, constructing a unified software development knowledge graph, establishing a cross-stage time sequence causal diagram based on the graph, extracting a defect correlation mode by combining a time sequence convolution network and a causal discovery algorithm, capturing an operation context in real time when a developer codes, submits or tests, matching a historical defect mode through two-stage retrieval, dynamically generating intelligent guidance information, finally recording a developer adoption behavior and a subsequent verification effect, and continuously iterating model parameters and guidance generation strategies through a double-channel feedback optimization mechanism. The application associates development, testing and running stage data in real time, intelligently pushes an interpretable early warning and correction guidance, forms a closed-loop optimization system, and significantly improves the quality and efficiency of software development.

The present application relates to the technical field of display devices, and discloses an artificial intelligence interaction method and apparatus, a display device, a storage medium, and a product. The method is applied to a display device. The method comprises: in response to a wake-up instruction, displaying a preset interaction interface, and acquiring video information in real time; inputting the video information and interaction information into preset artificial intelligence software so as to obtain output information of the artificial intelligence software; and displaying the output information by means of the interaction interface.

The invention relates to the technical field of artificial intelligence and software engineering, and discloses a small sample individual fairness testing method based on a domain adaptive flow model. Aiming at the problems of difficulty in obtaining target model training set data, low discrimination sample generation efficiency, insufficient sensitive attribute decoupling and the like in the existing black box fairness test, the invention provides the following technical scheme: firstly, constructing a gating residual domain adaptive flow model, and performing dynamic fusion on a frozen source domain projection matrix and a trainable low-rank adapter to obtain an adaptive flow model; domain adaptation of the flow model is realized under the condition of not depending on a target model training set; secondly, a two-stage anti-fact generation strategy is adopted, a seed sample set is constructed by utilizing a dynamic radius attenuation mechanism, and discriminated samples are efficiently expanded in combination with triple disturbance; finally, gradient orthogonal constraint is applied to the hidden space of the flow model, and decoupling control over the sensitive attributes and the semantic features is achieved. The black box fairness testing method can be used for black box fairness testing of classification models such as tables, texts and images, and has good practical significance and actual effect.

The application provides an intelligent grading and early warning system for intraoperative bleeding of a medical endoscope based on artificial intelligence and a working method thereof, and has the characteristics that the system comprises a medical endoscope catheter, a medical endoscope image processor, a medical lavage pump, a medical high-definition highlight liquid crystal display and end-side artificial intelligence software; the working method comprises real-time image recognition, bleeding point monitoring and early warning, automatic regulation of lavage and negative pressure suction; and the bleeding can be monitored in real time, intelligently and efficiently during surgery, and innovative medical technology support is provided for the surgery.The application has the advantages of convenient, intelligent and reliable surgical treatment effect.

The invention discloses a credibility evaluation method for artificial intelligence software. The credibility evaluation method comprises the steps of 1, full-life-cycle data acquisition and preprocessing, 2, multi-dimensional collaborative evaluation, 3, scenarized rule adaptation, 4, comprehensive credibility analysis and early warning and 5, visual output of evaluation results. According to the method, traditional dimensions, a large model and multi-mode special evaluation are integrated, the credibility verification problem of an emerging AI technology is solved, and real-time monitoring and collaborative verification of credibility are achieved through full-life-cycle data collection and cross-dimension linkage logic.

An artificial intelligence (AI) software product for providing scalable intelligent video surveillance for the artificial intelligence of things. The AI software product performs operations including receiving, at an edge node, a sequence of images of a target environment, where the AI software product resides in the edge node, and where the edge node is local to the target environment. The AI software product further observes one or more target objects in the sequence of images of the target environment in real time. The AI software product further detects at the edge node one or more anomalies in the target environment based on the observing of the one or more target objects in real time, where the one or more anomalies are specific to the target environment.

This invention relates to a method (100) for transferring emotional state and facial texture between two human face photographs using optimization techniques, without requiring any dataset. It can be utilized in forensic investigations, the entertainment and social media sectors, pre-procedural studies in medical aesthetics, synthetic dataset generation for 0 artificial intelligence software, and identity anonymization in images.

A system, computer program product, and method comprising the steps of tracking a work or school performance and an interaction at work or participation in an educational program at an educational institution with at least one tracking module; learning a physical movement or interaction, with at least one self-learning and analytics module, derived from the work or school performance and interaction at work or participation in an educational program at an educational institution; identifying a behavioral anomaly pattern, with an AI software module, founded on the physical movement or interaction; associating a predetermined movement value as measure to the behavioral anomaly pattern; generating a digital work or school performance review by the AI software module; generating a digital resume, with a resume module, based at least on one of, the digital work or school performance review, a work or school history and a place of employment or educational institution.

A method for using artificial intelligence software to manage and optimize the energy consumption of a vertical farm and greenhouse, comprising a grid of solar panels supplying solar power, solar cells, and sensors throughout the vertical farm, which can heat or cool the greenhouse, with heating and cooling controlled according to plant species and growth stage, and comprising a composite cycle sensor and instrumentation, to which data from both the vertical farm and greenhouse is fed; an outdoor light measuring sensor that measures and estimates the conditions of solar power in the solar grid and transmits the data to the artificial intelligence software; and the artificial intelligence software determines how much light various plants in the hydroponic greenhouse require to maximize the yield from those plants.

The invention relates to the field of artificial intelligence, discloses an artificial intelligence software operation management platform detection method and system and a storage medium, and aims to solve the problems that in the prior art, the operation behavior monitoring granularity is rough, a cross-dimension linkage detection mechanism is lacked, a static rule is relied on and no closed-loop response capability exists. The method comprises the steps that user operation behavior data flow and platform operation state data are collected in real time; performing multi-modal feature coding on the heterogeneous data to generate an operation behavior semantic representation vector and a platform state dynamic representation vector; an operation-state joint representation vector is generated through cross-modal association analysis; and outputting an abnormal confidence score by using a pre-trained abnormal discrimination model based on the joint representation, and triggering a grading response mechanism. According to the scheme, accurate identification and automatic closed-loop disposal of the abnormal operation are realized, and the detection accuracy and the platform safety are remarkably improved.

Apparatus and methods are provided in relation to an autonomous computer system that can defend against known and unknown virus and malware attacks. Various embodiments include a Virus Autonomous Defense System (VADS) can on its own without human intervention once it is turned on. Embodiments can incorporate hardware coupled with various types of artificial Intelligence software and systems to perform response functions including closing ports that are being compromised, analyze an attack, and develop software scripts (signatures) to defend against future attacks, and create responses which defeat an attack that can include a follow on response of freeing up an attacked port for continual operation.

An angioplasty system is provided. The system comprises an inflation device for angioplasty devices within a blood vessel presenting stenosis, and includes a contrast fluid reservoir with a pressure-adjusting device; a connector; a pressure sensor; an electronic-actuation valve; safety features; powering features; a digital interface; a microprocessor with a first software; a memory; a connection of the microprocessor to the Internet or an intranet; a second artificial intelligence software; a database; and a radiological arch to acquire and process images of the blood vessel or the area where the blood vessel is located. The microprocessor is connected to the radiological arch and to the database, in such a way that the inflation device may learn to operate autonomously and adjust itself automatically taking into account previous data or treatment models.

Aspects of the subject disclosure may include, for example, receiving, over a communication network, a query for a first artificial intelligence (AI) software application from a client computing device associated with a first user, determining a client identifier associated with the query, wherein the client identifier is associated with the first user, and determining a group of characteristics associated with user based on the client identifier. Further embodiments can include generating query metadata based on the group of characteristics, providing the query and the query metadata to the first AI software application, generating a query response utilizing the first AI software application based on the query and the query metadata, and providing, over the communication network, the query response to the client computing device. Other embodiments are disclosed.

This invention provides a Turing test method for artificial intelligence software, comprising: acquiring the output data of the artificial intelligence software to be tested; comparing the output data with data in a preset knowledge base to determine the accuracy of the results of the artificial intelligence software; when the accuracy of the results of the artificial intelligence software is higher than a predefined accuracy threshold, calculating whether the passability of the output data of the artificial intelligence software in a preset learning model reaches a cross-entropy threshold; if the passability reaches the cross-entropy threshold, then using a clustering analysis algorithm to group the cases corresponding to the output data, and calculating the ratio of manually labeled case groups; if the ratio of manually labeled case groups is higher than a predefined Turing test threshold, then determining that the artificial intelligence software has passed the Turing test of artificial intelligence, and generating a test report. This invention provides a complete and reliable intelligent testing scheme for medical artificial intelligence software products, achieving effective testing of the accuracy of AI diagnostic system judgment results.

This invention discloses a large-model-driven multi-dimensional intelligent detection method and apparatus for software defects, belonging to the field of artificial intelligence software testing technology. It includes generating abstract syntax trees, control flow graphs, and data flow graphs from source code through static analysis, and matching and filtering relevant historical defect knowledge. By combining multi-dimensional code representation with historical knowledge, a multi-level prompt input pre-trained large language model is constructed to generate an initial draft report containing the location, type, and context of potential defects. A strategy consisting of dynamic symbolic execution path verification, historical defect pattern matching verification, and code change impact scope verification is employed to verify the authenticity and prioritize the draft report, outputting the final report. This method can deeply understand code semantics and combine historical experience, improving the accuracy of defect detection and effectively reducing false positives through multi-source verification.

A virtual background image used with a video stream of a conference participant during a video conference is updated (1306) to visually represent one or more key points of the video conference. Generative artificial intelligence software associated with a conferencing system evaluates content of a video conference to determine (1304) one or more key points related to the video conference. The generative artificial intelligence software updates (1306) a virtual background image of a participant of the video conference to include one or more visual elements representing the one or more key points. The updated virtual background image is then output (1308) for use within a video stream of the participant during the video conference.

A system and method of encoding and decoding using generative AI for compression of video stream uses the system for encoding and decoding using generative AI for compression of video stream that comprises a camera, an encoder comprising generative artificial intelligence (AI) software operative in the encoder to encode video data, a transmitter, a receiver, a processor, a decoder, and a visual display operatively in communication with the decoder. Using the system, video data obtained from the camera are provided to the encoder; the generative artificial intelligence (AI) software encodes the video data at encoder to produce a compressed data set; the compressed data set are transmitted in a kilobit per second range (kbps-range) bandwidth at a low bandwidth using transmitter and receiver and, subsequently, from the receiver to a distant site via a further data network; and the compressed data set decoded at the distant site.

The invention provides a file marking method, a marking information identification method, a file identification method and device, electronic equipment and a readable storage medium, and is applied to the technical field of data processing. The to-be-marked file is generated through artificial intelligence software; the to-be-marked file is composed of original digital content, and the original digital content corresponds to the type of the to-be-marked file; obtaining first mark information; the first mark information comprises a software identifier of the artificial intelligence software; converting the first mark information into target mark information matched with the format of the original digital content; embedding the target mark information into the original digital content to obtain target digital content; according to the embodiment, the target digital content is used for forming the marked file, the target software information is embedded into the original digital content forming the to-be-marked file, the target digital content used for forming the marked file is obtained, and the file marking safety is improved.