Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

224 results about "User agent" patented technology

In computing, a user agent is software (a software agent) that is acting on behalf of a user, such as a web browser that "retrieves, renders and facilitates end user interaction with Web content". An email reader is a mail user agent.

Logical text passage generation and retrieval for retrieval-augmented generation

Techniques for logical text passage generation and retrieval for retrieval-augmented generation. The techniques involve processing markup language documents to generate logical text passages and their corresponding embeddings. These embeddings are indexed for efficient retrieval. Upon receiving a user utterance, a user query is formed and transformed into an embedding to query the index. Relevant text passages are identified and used to prompt a large language model (LLM), which generates a completion. This completion is then sent as a response to the user. The process effectively bridges user queries with relevant information through advanced embedding and natural language processing techniques, enabling accurate and contextually appropriate interactions within a user-agent dialogue framework.
Owner:AMAZON TECH INC

Complex social behavior simulation and public opinion deduction method based on multiple agents

The invention relates to the technical field of social network analysis and generative artificial intelligence, and discloses a multi-agent-based complex social behavior simulation and public opinion deduction method, which comprises the following steps of: dividing social groups, and dividing users in a social network into key opinion leader communities and common user communities; respectively constructing a key opinion leader agent and a common user agent which are driven by the large language model; constructing a dynamic weighted directed network, taking each key opinion leader agent model as a node, calculating a network node neighborhood through opinion index and node influence weighting, calculating an emotion score based on a text emotion index, dynamically adjusting the network node neighborhood based on the emotion score, and performing loop iteration for several times to complete deduction and simulation of network public opinions; the problem that public opinion propagation modeling is difficult under the cross-domain dynamic background is solved, the difference of public opinion individuals and the complex social interaction relation can be simulated more accurately, and the method is feasible.
Owner:COMMUNICATION UNIVERSITY OF CHINA

Large language model agent for automated gene-editing experiment design

A platform for automated design of gene-editing experiments includes one or more processing units and a non-transitory computer-readable storage device. The storage device contains instructions that, when executed, configure the processing units to perform a method. The method includes receiving a meta request with information about a requested gene-editing experiment, configuring an ordered list of tasks via a reasoning framework, and implementing tasks via a Task Executor module utilizing state machines. The Task Executor connects to external APIs, provides instructions to a User-Proxy Agent module, and receives user input. The User-Proxy Agent forms prompts based on current state instructions, user requests, interaction history, and API results to determine appropriate actions. The platform outputs recommendations responsive to the meta request.
Owner:THE TRUSTEES OF PRINCETON UNIV +1

Exercise prescription recommendation method and device, electronic equipment and storage medium

The invention relates to an exercise prescription recommendation method and device, electronic equipment and a storage medium. The exercise prescription recommendation method comprises the following steps: constructing multiple agents at least integrated with a user agent, a doctor agent, a nutritionist agent and an exercise health agent, and providing an interactive interface to realize information sharing, competition or negotiation and decision and scheme generation between every two agents; pre-training is carried out based on the professional domain knowledge maps corresponding to the different agents, so that a multi-agent exercise prescription recommendation model is obtained; and inputting the obtained various related conditions of the metabolic disease patient into the exercise prescription recommendation model for reasoning to obtain a target exercise prescription. According to the invention, accurate and personalized exercise prescriptions can be formulated for patients with metabolic diseases.
Owner:SUZHOU YINGDI XINKANG NETWORK INFORMATION TECH +1

Sip services

A method is performed by a session initiation protocol (SIP) user agent or a SIP proxy. A SIP packet is received and parsed into fields. The fields are written into an outbound packet being a protocol packet or a protobuf packet, wherein writing the fields is dependent on an application programming interface (API) for integrating with the SIP user agent or SIP proxy, and wherein the API has restricted functionality as compared with SIP. The outbound packet is sent to a node that implements a service and which has access to the API definition. A response is received and the SIP packet is edited according to fields in the response to produce an edited SIP packet. An action is determined to apply to the edited SIP packet, according to the response. The action is applied to the edited SIP packet.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Gateway plug-in loading and optimizing method, device, equipment and medium

The invention discloses a gateway plug-in loading and optimizing method and device, equipment and a medium, and relates to the technical field of gateway plug-in management, and the method comprises the steps: collecting target information of a user request entering a gateway, so as to obtain corresponding collection data; the target information comprises a request source ip, a request path, parameter information, a request frequency, a user agent, a request method and a response state code; identifying the user request based on the collected data by using a pre-trained identification model so as to determine a request type of the user request according to a corresponding identification result; determining a target plug-in matched with the user request based on the request type, and loading the target plug-in to obtain a corresponding execution result; and optimizing a plug-in priority, a plug-in strategy parameter and an execution path of the target plug-in based on the execution result. Therefore, the gateway performance is improved, the maintenance cost is reduced, and the system stability is enhanced.
Owner:INSPUR ENTERPRISE CLOUD TECHNOLOGY (SHANDONG) CO LTD

Methods and systems for identifying and remediating poor user experiences on computing devices

This application relates to apparatus and methods for identifying and remediating poor user experiences on computing devices. In some examples, a user speed determination device is configured to receive a content delivery request for delivery of content to a user device. The computing is also configured to obtain user identification data, obtain user device data and determine a user device speed based on the user identification data and the user device data. The computing device then sends a user device speed indicator to a content delivery device to cause the content delivery device to deliver remediated content to the user device when the user device speed is determined to be less than a predetermined speed threshold. The user identification data can include an IP address and the user device data can include user agent data, user connection data and user resource timing data.
Owner:WALMART APOLLO LLC

Dynamic authorization and authority management system applied to agent application system

The invention relates to the technical field of authority management, and discloses a dynamic authorization and authority management system applied to an agent application system, and the system comprises a user agent module which receives an operation access request of a user for a resource, returns a result according to an authentication and authorization module, and allows or rejects the operation access request; the authentication and authorization module is used for receiving the operation access request, calling the role management module for verification and returning a result to the user agent module; the role management module is used for managing user information, roles and permissions and establishing association and corresponding permissions between the users and the roles or the virtual roles; the dynamic permission adjusting module is used for monitoring operation of the resources and adjusting the permission of the role or the virtual role; the data resource management module is used for operating and accessing data resources; the model management module is used for operating and accessing the model; the intelligent agent management module is used for operating and accessing the intelligent agent; according to the invention, the dynamic authorization of each resource in the intelligent agent application system and the independent management of the authority are realized.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Public facility reachability evaluation method and system based on geographical multi-agent

The invention discloses a public facility reachability evaluation method and system based on geographic multiple agents, and belongs to the field of urban calculation and geographic information. According to the method, a multi-agent system comprising a user agent and a facility agent is firstly constructed, and then a dynamic utility function combined with an evolutionary game theory is introduced to simulate the dynamic decision and congestion avoidance behavior of a user; and user strategies are balanced through multiple rounds of iterative evolution, so that a macroscopic reachability pattern emerging from a microcosmic game is obtained. According to the method, starting from the microscopic individual level, by simulating the dynamic game process of a large number of agents, the defects of a static calculation model are overcome, and dynamic evaluation and predictive simulation of reachability of public facilities are achieved. Compared with the prior art, the evaluation result is more accurate, dynamic feedback of the real world can be reflected, and a scientific decision support tool is provided for urban planning.
Owner:ZHEJIANG UNIV

Disaster reporting method, electronic equipment and computer readable storage medium

The invention discloses a disaster reporting method, electronic equipment and a computer readable storage medium, and relates to the field of disaster information collection, and the method comprises the steps: collecting original dialogue information through a dialogue agent; the dialogue agent preprocesses the original dialogue information to obtain target dialogue information; the information management agent is controlled to receive the target dialogue information in real time, feature extraction is carried out on the target dialogue information, and disaster information is obtained; respectively storing the disaster information and all the original dialogue information in a database; and controlling the information management agent to generate a report according to the disaster information. According to the application, by introducing the user agent and the disaster information management agent, multi-modal data acquisition, information extraction and multi-round interaction are realized. The system can automatically identify the type, the place and the severity of the disaster situation, and quickly screen and integrate key elements. By means of a multi-agent framework, a dialogue strategy and a data analysis process can be dynamically adjusted, the integrity and accuracy of information are ensured, and support is provided for disaster reporting and rescue decision making.
Owner:PEKING UNIV SHENZHEN GRADUATE SCHOOL

Network domain address translation implementation method suitable for multi-network domain scene

The invention belongs to the technical field of video monitoring platforms, and relates to a domain address translation implementation method suitable for a multi-domain scene, which at least comprises a client, a user agent module, a streaming media module and a domain agent module. After processing, the streaming media module returns a streaming URL address to the user agent module through response; the user agent module receives the response of the streaming media and transmits a streaming URL address and a network domain where the client is located to the network domain agent module; the original address can be converted into a target network domain address where the client is located through the network domain agent module, and the target network domain address is returned to the user agent module; and the user agent module returns the stream taking address to the client and pulls the audio and video streams from the streaming media. The method does not need to make special requirements for streaming media configuration, client configuration and network equipment, gets rid of dependence of specific network equipment, and ensures that domain address translation can be efficiently and smoothly executed in a multi-domain environment.
Owner:HANGZHOU ARTECH

Attribute based encryption key based third party data access authorization

ActiveUS12250314B2Third partyAttribute-based encryption
Mechanisms are provided for computing resource access security in which a credential of a user agent is authenticated to determine if the user agent is associated with an entity for which an attribute based encryption (ABE) key is to be generated. If so, an ABE key is generated and provided which corresponds to a set of attributes of the entity. Token issuance logic receives a token request and the ABE key from a relying party computing device and executes a decryption operation on locking metadata associated with at least one attribute value based on the ABE key. The token issuance logic, in response to the decryption operation successfully decrypting the locking metadata, issues a generated token to the relying party computing device based on the at least one attribute value. The relying party computing device accesses the computing resources using the generated token.
Owner:INTERNATIONAL BUSINESS MACHINE CORPORATION

User verification systems and methods

This disclosure relates to systems and methods for verifying the presentation of content to a target audience using generated metrics indicative of a likelihood that the content was presented to actual human individuals within the target audience. In some instances, such a metric may be associated with a probability model estimating that a user (e.g., a user of a device) is human and not a bot and / or other automated service. Metrics consistent with aspects of the disclosed embodiments may be generated based, at least in part, on user information received from a user and / or associated devices and / or associated services. Consistent with various disclosed embodiments, metrics indicative of whether a user is human, content distribution decisions and user agency decisions may use such metrics.
Owner:INNOVATION TECHNOLOGIES PARTNERS LP

Key information extraction and mass attitude evaluation method based on large language model

The invention provides a key information extraction and mass attitude evaluation method based on a large language model. The method comprises the following steps: collecting comment texts of the masses on a target decision, and extracting known keywords; screening a comment text related to the known keyword by utilizing a search model; further screening a comment text related to the known keyword by utilizing a semantic understanding model; rechecking the correlation between the comment texts and the known keywords by using a large language model, and filtering out the comment texts which are misjudged to be related to the known keywords to obtain a key comment set; and a multi-agent system is constructed, each agent independently evaluates the attitude of each comment text in the key comment set to the target decision, and the user agent integrates the evaluation results of all agents and outputs the evaluation results. According to the method, a multi-level screening mechanism and an attitude evaluation mechanism based on multi-agent consensus are adopted, the calculation amount in the similarity judgment process is reduced, and the attitude evaluation accuracy and the system processing efficiency are improved.
Owner:ZHEJIANG UNIV

Man-machine interaction method of charging station management system, electronic equipment and storage medium

The invention relates to the field of intelligent interaction, and discloses a man-machine interaction method of a charging station management system, electronic equipment and a storage medium. The method comprises the following steps: a user intelligent agent obtains a user demand input by a user through a user terminal, and converts the user demand into structured data carrying a context identifier; the coordination agent carries out task allocation through an agent group configuration strategy based on the structured data, and functional agents in an agent group are scheduled to execute the allocated tasks; the functional agent executes the task allocated by the coordination agent and returns a completed task result to the coordination agent; and the coordination agent performs consistency verification on the task result returned by the function agent, and performs man-machine interaction with the user through the user agent based on the consistency verification result. Therefore, by constructing multi-agent collaborative man-machine interaction, the charging station management system has higher flexibility, expandability and higher intelligent level.
Owner:AUTEL UNITED CREATION SOFTWARE DEV CO LTD

Methods and systems for query decomposition, agent ranking, and execution of selected agents from a plurality of agents

A method for verifying a user agent includes transmitting, by a core node, to a user agent, a predefined set of user requests. For each user request in the predefined set of user requests, the core node receives an embedding generated based on the user request, thereby receiving a plurality of embeddings based on the predefined set of user requests. The core node determines whether the plurality of generated embeddings satisfy a similarity criterion. The core node transmits, to the user agent, a task to generate a query plan and receives a query plan generated by the user agent for processing a user request identified in the task. The core node determines whether the query plan satisfies a query plan criterion, thereby producing query plan adequacy output. The core node determines whether to approve the user agent based on the similarity output and the query plan adequacy output.
Owner:PORTAL AI INC

Methods and apparatus to credit media presentations for online media distributions

Methods and apparatus to credit media presentations for online media distributions are disclosed. Example methods and apparatus determine a presenter of a media session based on a user agent identifier extracted from a proxy record associated with the media session, and in response to determining that the user agent identifier does not identify a publisher, identify a first domain referenced by a URL associated with the media session, and, in response to determining that the first domain matches a domain pattern associated with a publisher and does not match a domain in a list of hosting domains, classify the media of the media session as being published by the publisher associated with the matching domain pattern, the publisher being different from the presenter.
Owner:THE NIELSEN CO (US) LLC

Methods and systems for honeyfile creation, deployment, and management

A method of automatically manipulating a lifecycle of a honeyfile on a file system, includes: implementing a learning algorithm on a file system; identifying a real file; training the learning algorithm by observing temporal events involving the real file; training a model with the learning algorithm; implementing a user agent on the file system; creating a honeyfile on the file system; deploying the honeyfile on the file system; using the trained model to generate user agent actions; evaluating the honeyfile; and either: deleting the honeyfile; or re-using the trained model to generate user agent actions to automatically modify the honeyfile.
Owner:PENTEN PTY LTD

User agent inference and active endpoint fingerprinting for encrypted connections

A cyber security appliance can inoculate a fleet of network devices by analyzing each endpoint of a secure connection. The appliance can receive a hostname for a malicious web server. The appliance can generate an unencrypted target fingerprint based on sending a series of unencrypted connection protocol requests to the malicious web server and an encrypted target fingerprint based on sending a series of encrypted secure connection protocol requests to the malicious web server. The appliance can build a combined web server fingerprint for the malicious web server based on both the encrypted target fingerprint derived and the unencrypted target fingerprint. The appliance can determine a set of suspicious IP addresses based on the combined web server fingerprint for the malicious web server. The appliance can inoculate a fleet of network devices against a cyberattack using the IP addresses to preemptively alert the fleet of cyber-attack.
Owner:DARKTRACE HLDG LTD

Methods and systems for ranking a plurality of worker agents based on a user request

A method for identifying and clustering worker agents for processing requests includes receiving, by a core node, from a user agent, a user request. The core node updates, for each of the plurality of worker agents, an availability status, thereby producing a plurality of availability statuses. The core node computes, for each of the plurality of worker agents, a value of a drift metric. The core node clusters the plurality of worker agents to produce a plurality of clusters of worker agents, wherein each of the plurality of clusters contains worker agents that have similar semantic capabilities. Based at least on the user request, the plurality of availability statuses, and the plurality of clusters, the core node identifies a subset of the plurality of worker agents that are both available to process the user request and that are suitable for processing the user request.
Owner:PORTAL AI INC

Methods and systems for enhancing a context for use in processing, by a plurality of artificial intelligence agents, a request

A method for identifying and clustering worker agents for processing requests includes receiving, by a core node, from a user agent, a user request. The core node updates, for each of the plurality of worker agents, an availability status, thereby producing a plurality of availability statuses. The core node computes, for each of the plurality of worker agents, a value of a drift metric. The core node clusters the plurality of worker agents to produce a plurality of clusters of worker agents, wherein each of the plurality of clusters contains worker agents that have similar semantic capabilities. Based at least on the user request, the plurality of availability statuses, and the plurality of clusters, the core node identifies a subset of the plurality of worker agents that are both available to process the user request and that are suitable for processing the user request.
Owner:PORTAL AI INC

Multi-terminal and multi-size page adaptation method

The invention provides a multi-terminal multi-size page adaptation method, which comprises the following steps of: accessing a unified page URL (Uniform Resource Locator) through a browser of terminal equipment, entering a view control component, and determining a page adaptation mode according to service requirements; calling a corresponding adaptation mode function based on the page adaptation mode, and calculating a view component type matched with the terminal equipment; and controlling the page to load the matched view component, and displaying the corresponding page view to the user through the client browser. According to the embodiment of the invention, a uniform access path URL is provided, two adaptation modes of a user agent identifier and a screen size are provided, the adaptation scheme is flexible to select and easy to expand, a uniform control function is provided, adaptation control logic is uniformly arranged at a client, front and rear ends are separated more thoroughly, UI coupling of multi-end, multi-device and multi-size page adaptation is reduced, and the user experience is improved. And the cross-end multiplexing of the logic layer improves the development and maintenance efficiency, and each end is loaded as required, so that the network flow is saved, and the page loading speed is improved.
Owner:CHINA SHIPBUILDING LINGJIU HIGH TECH (WUHAN) CO LTD +1

Multi-agent deep reinforcement learning method considering user-power distribution network cooperation under topology reconstruction

The invention discloses a multi-agent deep reinforcement learning method considering user-power distribution network cooperation under topology reconstruction, and the method comprises the steps: carrying out the modeling of an independent interaction user agent through a multi-agent reinforcement learning MADDPG algorithm, enabling a user to make a decision independently according to the state of the user, enabling the user to interact with a power distribution network, and carrying out the topology reconstruction through the power distribution network. A virtual power flow method is adopted to maintain radial operation of the power distribution network, power and voltage balance of the power distribution network under topology reconstruction is considered, and a new method for interactive operation of independent users and the power distribution network under the extreme disaster condition is provided. According to the method, the current practical situations of frequent occurrence of extreme events with high influence and low probability and improvement of distributed photovoltaic permeability are considered, and through independent scheduling of independent users and reconstruction of the topology of the power distribution network, the power supply reliability and safety of the power distribution network under extreme disasters are guaranteed, and the privacy of the users is protected.
Owner:HOHAI UNIV

Large language model reasoning system and method of self-adaptive input window in RAG scene

The invention relates to a large language model reasoning system and method of a self-adaptive input window in an RAG scene. The system comprises a user agent part used for obtaining a query request of a user; the vector database VDB part is connected with the user agent part and the large language model part, and the vector database VDB part is used for obtaining large language model input window parameters according to the large language model part, receiving a query request of a user, querying candidate text block groups from a local knowledge base, and sending the candidate text block groups to the user agent part; filling the query request of the user and the candidate text block group into a prompt template to obtain a prompt template containing a context; and the large language model part is used for performing content reasoning on the prompt template containing the context by adopting a corresponding large language model and returning a reasoning result to the user agent part. Compared with the prior art, the method has the advantages that a large window of a large language model is fully utilized, and more local knowledge is conveyed and reasoned.
Owner:SHANDONG BRANCH OF BEST TONE INFORMATION

Methods, Systems, and Devices for an Evaluation Platform

In one aspect, an example computer-implemented method includes (a) receiving user activity data, (b) receiving user agency data, (c) generating a user profile, wherein the user profile is based on the received user activity data and user agency data, and wherein the user profile contains personal information associated with the user, (d) issuing a digital representation, wherein the digital representation does not contain the personal information associated with the user, (e) receiving a plurality of predetermined persona profiles, (f) identifying a persona match using one or more machine learning models, (g) based on the identified persona match, identifying a suggested action for the user of the client computing device, and (g) transmitting instructions that cause the client computing device to display, via the user interface of the client computing device, a graphical indication of the suggested action to the user of the client computing device.
Owner:GTN HUMAN SERVICES LLC

Management of connector services and connected artificial intelligence agents for message senders and recipients

Systems and methods are described for a messaging agent for managed multidimensional search based on an electronic message and management policies. A messaging application at a client device can send a new electronic message, such as an email, to a connector service. An attachment can be ingested and stored in a vector database. Then one or more artificial intelligence (“AI”) agents can be selected for responding to the body of the email, such as a query in the body. The responses can be formatted and sent to multiple users, such as a sending user of the electronic message and a recipient user that was copied or also sent the new electronic message. The AI agents can use different AI models, prompts, and vector databases depending on user permissions. This allows for building up vector databases with relevant content items and answering user questions based on those vector databases.
Owner:AIRIA LLC

Identity provider (IDP) agnostic authentication enforcement

An intermediary server operates an application proxy. An access request is received for access to an application, where an access policy is associated with the application that specifies authentication method(s) acceptable for satisfying an authentication requirement enforced by the application proxy. The user agent is redirected to submit an authentication request to an identity provider for identity verification. An authentication response generated by the identity provider is received and includes information that specifies authentication method(s) used during the identity verification. If the authentication method(s) used during the identity verification match the authentication method(s) acceptable for satisfying the authentication requirement, the user will not be prompted to perform those authentication method(s) and the authentication requirement enforced by the application proxy is met. If they do not match, the user will be prompted to perform the authentication method(s) as a condition to access the application.
Owner:CLOUDFLARE INC

Active chat robot construction method, device and medium

The invention discloses an active chat robot construction method, device and equipment and a medium, and the method comprises the steps: constructing a chat quality evaluator taking a user as a center, and enabling the chat quality evaluator to be used for evaluating the active perception capability of a chat robot for user background information and chat preferences; constructing a user background data set for enabling the large model to play a user agent with different background identities, and carrying out multiple rounds of dialogue chats with the chat robot; dialogue corpus collection and iterative curriculum learning are used for generating high-quality dialogue corpus, and a large model corresponding to the chat robot is finely adjusted by using an iterative curriculum learning method so as to improve the active perception ability of the model to user background information and chat preference. According to the method, the chat robot can actively pay attention to the background information and chat interests of the user and give answers meeting the chat preferences of the user, so that the dialogue participation degree and satisfaction degree of the user are improved, and the man-machine interaction experience is improved. The method can be widely applied to the technical field of artificial intelligence.
Owner:SUPER ROBOT RESEARCH INSTITUTE (HUANGPU) +1