29 results about "Collective intelligence" patented technology

The application belongs to the technical field of industrial artificial intelligence, and discloses an AI-based industrial edge intelligent task cooperation method and system, which comprises the following steps: based on the probability distribution prediction of the future resource state, a main execution DAG and multiple or DAGs are automatically generated, instant switching is realized when a preset failure mode is detected, and the system robustness is greatly improved; a deep diagnosis is performed by using a causal inference engine, and the agent is guided to perform skill specialization and skill pruning, so that an intelligent ecology capable of self-purification and evolution is constructed; and a cross-topology meta-learning framework is adopted, so that the system can master the ability of quickly adapting to new and unseen tasks with few samples. Through the three innovations of multi-path or planning, skill life cycle management driven by causality and cross-topology meta-learning, the application brings the effects of nearly zero delay of task recovery, efficient evolution of collective intelligence and rapid generalization of new tasks, and enhances the application value of the system in complex and changeable industrial scenes such as flexible manufacturing.

Detection of abnormal node behavior and attacks by a node(s) can be enhancedly performed and managed. A security management component (SMC) of a collective node of a node group can analyze respective groups of residual vectors associated with respective features and associated with and received from respective nodes of the node group. Based on the analysis and defined security management criteria relating to abnormal node behavior and attacks, SMC can determine whether there is abnormal node behavior and / or an attack by one or more nodes. In response to detected abnormal node behavior and / or attack by a node(s), SMC can perform a desired mitigation action. Respective SMCs of the respective nodes of the node group also can perform respective determinations regarding whether an abnormal node behavior and / or attack by a respective node exists based on their respective analysis of their respective groups of residual vectors.

Methods and systems are disclosed for enabling AI-facilitated groupwise conversation among very large, networked human teams. For example, a very large human team is divided into a plurality of small parallel real-time conversations, each of said small conversations including at least one conversational AI agent. A hyperchat process connects the plurality of small conversations in real-time, thereby enabling the large, networked human team to hold a productive real-time conversation in which they collaboratively discuss issues, brainstorm ideas, debate options, rank alternatives, and converge on solutions with amplified collective intelligence. In this way, the methods and systems enable thoughtful and productive real-time conversations among networked human groups of unprecedented scale.

The invention belongs to the technical field of industrial artificial intelligence, and discloses an AI-based industrial edge intelligent task collaboration method and system, and the method comprises the steps: actively generating a main execution DAG and a plurality of probabilistic DAGs based on the probability distribution prediction of a future resource state, achieving the instant switching when a preset failure mode is detected, and greatly improving the system robustness; deep diagnosis is carried out by using a causal inference engine, an intelligent agent is guided to carry out skill specialization and skill pruning, and intelligent ecology capable of self-purification and evolution is constructed; and a cross-topology element learning framework is adopted, so that the system masters the ability of carrying out few-sample rapid adaptation on brand new and unseen tasks. According to the invention, through three innovations of multipath or natural planning, causal-driven skill life cycle management and cross-topology element learning, the effects of nearly zero delay of task recovery, collective intelligent efficient evolution and rapid generalization of new tasks are brought, and the application value of the system in flexible manufacturing and other complex and changeable industrial scenes is enhanced.

Techniques for multi-repository search enhancement and collective intelligence ensembling for artificial intelligence coding assistants are described herein. A code generation platform provides a user interface enabling selection of multiple code repositories, including repositories stored locally, hosted within enterprise environments, and configured for authenticated user access. The platform indexes selected repositories to extract contextual information by parsing source code files and generating structured data representations. When a user query directed to a generative artificial intelligence code generation agent is received, the platform transmits the extracted contextual information to generate a response. The platform leverages multiple code repositories to provide comprehensive context for code generation tasks, enabling the agent to access historical information about successful and unsuccessful approaches from related projects.

The present application belongs to the technical field of artificial intelligence, robots and network communication, and particularly relates to a multi-agent interaction method and system based on layered negotiation and semantic driving, which can realize robust, reliable and highly adaptive collective intelligence. The present application has the semantic richness of LLM protocol, the real-time reliability of IUS protocol, supports dynamic negotiation ability of decentralization, and contains a security mechanism to deal with semantic attacks. The three mechanisms of layered decoupling, dynamic negotiation and endogenous security are integrated into one, which can produce a synergistic effect of 1+1+1>3, and solves the problem that the prior art cannot simultaneously satisfy semantic richness, execution reliability, dynamic adaptability and communication security.

The application discloses a traditional Chinese medicine component online detection and analysis system and a system, and relates to the technical field of traditional Chinese medicine quality analysis.The system comprises a data acquisition module, a fusion identification module, a consensus verification module and a model optimization module.The data acquisition module is used for acquiring multi-modal data of traditional Chinese medicine samples.The fusion identification module is used for performing fusion analysis on the multi-modal data and directly outputting a structured identification conclusion.The consensus verification module is used for realizing cross-terminal data consensus verification by using an intelligent contract.The model optimization module is used for realizing continuous co-evolution of a global identification model.The application significantly improves the comprehensiveness and accuracy of traditional Chinese medicine identification by means of multi-modal data fusion and deep learning analysis, provides tamper-proof, traceable and cross-terminal mutually-recognized credible records for detection results, greatly enhances the public credibility and legal effectiveness of the results, and enables the whole network to have self-adaptive and collective intelligent improvement capabilities, so that the core bottlenecks of information isolation, model solidification, lack of credible cooperation and evolution power in the prior art are systematically solved.

Methods and systems for AI-mediated groupwise conversation are described. For example, a collaboration server is in networked communication with a plurality of computing devices, each running a local application that enables a real-time conversation among at least one human member and at least one AI agent. This facilitates a plurality of parallel real-time conversations among human members and AI agents. In some cases, a repeatedly executed data sharing process shares conversational content among parallel real-time local conversations, thereby connecting conversations into a single larger-scale discussion. In some cases, a content extraction process extracts ideas and reasons from the conversational data. Each participant's exposure to extracted ideas or reasons may be tracked to coordinate the optimized sharing of ideas and reasons aimed at increasing each participant's exposure to ideas and reasons that have not yet been discussed their local real-time conversation. This increases large-scale deliberative efficiency and boosts collective intelligence.

A digital assistant on a user interface, employing the trained human-emulative digital model is determined for a team to engender synchronization. The collective interactions between members of the team are analyzed. The customers associated with the first data center are identified. The share goal and interaction pattern based on the analyzed collective interactions are identified. The human-emulative digital model, using a deep learning algorithm, based on the at least one share goal and interaction pattern is trained.

This invention discloses a learning resource selection method and system based on collective intelligence and individual differences. The method includes: calculating a dynamically updated collective intelligence index representing universal quality for each learning resource in the resource library; responding to the learning request of a target user; evaluating the personalized suitability of each learning resource in the resource library with the target user in the current scenario based on individual feature data using a user-resource matching model; weighting and fusing the collective intelligence index and personalized suitability of each learning resource in the resource library based on a fusion strategy to generate a comprehensive recommendation score; and ranking the learning resources according to the comprehensive recommendation score to generate and output a personalized learning resource recommendation list for the target user. This fundamentally avoids resource recommendation bias caused by simply relying on popularity, achieving a balance between recommendation quality and personalization.

A smart, human-centered technique that uses artificial intelligence and mixed reality to accelerate essential tasks of the inspectors such as defect measurement, condition assessment and data processing. For example, a bridge inspector can analyze some remote cracks located on a concrete pier, estimate their dimensional properties and perform condition assessment in real-time. The inspector can intervene in any step of the analysis / assessment and correct the operations of the artificial intelligence. Thereby, the inspector and the artificial intelligence will collaborate / communicate for improved visual inspection. This collective intelligence framework can be integrated in a mixed reality supported see-through headset or a hand-held device with the availability of sufficient hardware and sensors. Consequently, the methods reduce the inspection time and associated labor costs while ensuring reliable and objective infrastructure evaluation. Such methods offer contributions to infrastructure inspection, maintenance, management practice, and safety for the inspection personnel.

The invention discloses an intelligent early warning method for flow risk assessment in digital supervision business, which belongs to the technical field of risk early warning of supervision business, and comprises the steps of constructing a risk feature system, constructing a basic assessment decision risk tree, assessing a random forest integration risk and performing intelligent early warning. According to the random forest algorithm, the defect that a single decision-making tree is prone to overfitting is effectively overcome through ensemble learning, decision making is conducted through collective intelligence of multiple trees, and the accuracy of risk assessment is remarkably improved; the risk tree provides a clear white-box model, so that a reasoning path from risk characteristics to a final conclusion can be intuitively displayed; and along with continuous accumulation of new process data and risk cases in the digital supervision service, the algorithm model can be retrained periodically, so that the evaluation performance is continuously optimized, and the adaptability is high.

The invention discloses a hybrid worker-oriented crowd sensing online capability assessment method and device, a medium and equipment. The method comprises the following steps: constructing a hybrid worker-oriented mobile crowd sensing system model; constructing an optimization function for maximizing long-term cumulative utility as a target based on a mobile crowd sensing system model; the time-space trajectory prediction module based on Transform predicts the success probability of the opportunity worker completing the task in the future time window; evaluating the same-stage capabilities of the mixed workers by using an urgency degree weighted capability scoring framework; the weight adaptive adjustment module based on deep reinforcement learning processes the real-time state of the dynamic crowd sensing system model to output the ability evaluation score of the mixed workers, and distributes the current task to the worker with the highest score; according to the invention, the problems of low efficiency, poor cost control and poor environmental adaptability caused by adopting a two-stage distribution strategy in the prior art can be solved.

The present disclosure describes systems and methods for amplified collective intelligence across large networked human populations by using deadbands and interconnected sub-groups. Disclosed are methods and systems for computer moderated collaboration among the population of human participants using a plurality of networked computing devices. A prompt may be presented to participants for collecting collaborative responses. Individuals within the population may each provide an initial response to the prompt during an initial time period. During a second time period, participants are enabled to update their responses while content is shared across participants. A forbidden deadband region defines an area around each participant's initial responses that updated responses must fall outside of, Sub-populations are defined for sharing initial and / or updated responses, enabling coherent interactions among manageable sized groups while leveraging the full benefits of the whole population. Changes in initial responses are used as a factor in deriving amplified collective intelligence.

The present disclosure describes systems and methods for enabling real-time conversational dialog among a large population of networked human users while facilitating convergence on groupwise decisions, insight extraction, and solutions, and amplifying collective intelligence. A plurality of computing devices associated with members of a population of participants is provided, wherein the plurality of computing devices is networked via a computer network and in communication with a central server. In some cases, the central server divides the population into a plurality of subgroups and enables an LLM-powered conversational surrogate agent associated with each subgroup. The conversational surrogate agent is configured to repeatedly observe a conversation among members of its assigned subgroup and store content of the conversation to extract insights from the conversation at appropriate intervals. The conversational surrogate agent assesses a numerical measure of conviction, confidence, or scope associated with each unique insight within the conversation, passes the insights and the numerical measure to other subgroups and modulates a strength of the insights based on the numerical measures.

The invention discloses a multi-agent self-adaptive decision-making method based on collective evolution and a related device, and relates to the technical field of agent decision-making, and the method comprises the steps: taking the task description of a to-be-executed task and the local observation data of each agent as the input, and generating a task graph and global observation data through a multi-modal large model, based on a task graph, global observation data and a long-term memory library, generating a global strategy, decomposing the global strategy into a local strategy of each agent, based on a local state and the local strategy of the agent, determining a local action of the agent, obtaining a local reward of the agent, and based on the local reward of all the agents, calculating to obtain an expected return; and judging whether the expected return is smaller than a preset trigger threshold, if yes, generating a global strategy again, and if not, issuing the local action of each agent to each agent to complete the task to be executed. The method can realize collective intelligent evolution and improve the task execution effect.

A prediction processing system, method, and method for doing business is disclosed. The prediction processing system can collect, process and publish event-outcome information. The prediction processing system can dynamically filter participants into groupings and iteratively optimize odds calculations over time. A proposal framework consisting of a various abstract proposal types can model and settle propositions. Game propositions can be automatically generated based on event categorization relationships. The prediction processing system can provide game players or others with access to collective intelligence, including prediction information and information derived from prediction information. The prediction processing system can create groupings of better-performing predictors and provide them with additional information not generally available. Better-performing predictors can be provided with additional stakes to increase the weight of their predictions in odds calculations. The prediction processing system can provide access to event-outcome information on a for-fee subscription basis.

Methods and systems for AI-mediated groupwise conversation are described. For example, a collaboration server is in networked communication with a plurality of computing devices, each running a local application that enables a real-time conversation among at least one human member and at least one AI agent. This facilitates a plurality of parallel real-time conversations among human members and AI agents. In some cases, a repeatedly executed data sharing process shares conversational content among parallel real-time local conversations, thereby connecting conversations into a single larger-scale discussion. In some cases, a content extraction process extracts ideas and reasons from the conversational data. Each participant's exposure to extracted ideas or reasons may be tracked to coordinate the optimized sharing of ideas and reasons aimed at increasing each participant's exposure to ideas and reasons that have not yet been discussed their local real-time conversation. This increases large-scale deliberative efficiency and boosts collective intelligence.

Techniques for multi-repository search enhancement and collective intelligence ensembling for artificial intelligence coding assistants are described herein. A code generation platform provides a user interface enabling selection of multiple code repositories, including repositories stored locally, hosted within enterprise environments, and configured for authenticated user access. The platform indexes selected repositories to extract contextual information by parsing source code files and generating structured data representations. When a user query directed to a generative artificial intelligence code generation agent is received, the platform transmits the extracted contextual information to generate a response. The platform leverages multiple code repositories to provide comprehensive context for code generation tasks, enabling the agent to access historical information about successful and unsuccessful approaches from related projects.

The present disclosure describes systems and methods for enabling real-time conversational dialog among a large population of networked human users while facilitating convergence on groupwise decisions, insights, and solutions, and amplifying collective intelligence. A collaboration server running a collaboration application is provided, wherein the collaboration server is in communication with the plurality of the networked computing devices and each computing device is associated with one user of the population of human participants. In some cases, the collaboration server defines a plurality of sub-groups of the population of human participants. A local chat application configured for displaying a conversational prompt received from the collaboration server is provided on each networked computing device. The local chat application enables real-time chat communication with other users of a sub-group assigned by the collaboration server. According to some embodiments, the computer mediated collaboration enables through communication between the collaboration application and the local chat applications.

The application discloses a device field collective intelligence representation and hidden Markov prediction method, comprising the following steps: step S1, constructing a data acquisition terminal; step S2, constructing a collective intelligence feature evaluation system based on viscosity indexes, uniformity indexes and flexibility indexes; step S3, constructing a candidate index set, screening the candidate indexes based on log-likelihood values, and fusing the final indexes screened; step S4, constructing and screening a group hidden Markov model; step S5, feature migration and state prediction of new group data; and step S6, an intervention mechanism based on hidden state semantic labels. The application can be used for real-time evaluation and prediction of team cooperation and collective intelligence of a group, and further guides external intervention and intervention. The application scheme can also collect feature indexes through a non-contact acquisition model, and has the advantages of strong popularization and no excessive interference on a process.

The present invention provides an information processing system using collective intelligence, and a method therefor. The present invention labels one or more pieces of raw data related to specific content provided from a user, performs a learning function on the labeled raw data through a preset classification model and prediction model, additionally labels a first image, which is an output value of the prediction model, performs an additional learning function on the additionally-labeled first image through the classification model and the prediction model, so as to output a second image, and thus provides an avatar and / or an item related to the raw data to the user, and can improve the reasoning ability of artificial intelligence through labeling of the raw data.

Techniques are described that provide self-service functionality for data analytics with built-in support guidance. The techniques include a collective intelligence system coupled with a centralized analytics support and enablement (CASE) system. The collective intelligence system is configured to build an indexed database based on documentation from disparate internal and external data sources. The CASE system provides a self-service function that includes a user interface as a search function and a chatbot, each configured to receive user queries regarding at least one of data or data analytics and return answers or results in response to the user queries based on the indexed database. Based on an inability of the chatbot and / or the search function to return an answer or result in response to a user query, the CASE system is configured to route the user query to a selected agent for either asynchronous or synchronous support for the user query.

A smart, human-centered technique that uses artificial intelligence and mixed reality to accelerate essential tasks of the inspectors such as defect measurement, condition assessment and data processing. For example, a bridge inspector can analyze some remote cracks located on a concrete pier, estimate their dimensional properties and perform condition assessment in real-time. The inspector can intervene in any step of the analysis / assessment and correct the operations of the artificial intelligence. Thereby, the inspector and the artificial intelligence will collaborate / communicate for improved visual inspection. This collective intelligence framework can be integrated in a mixed reality supported see-through headset or a hand-held device with the availability of sufficient hardware and sensors. Consequently, the methods reduce the inspection time and associated labor costs while ensuring reliable and objective infrastructure evaluation. Such methods offer contributions to infrastructure inspection, maintenance, management practice, and safety for the inspection personnel.

We collect parts information in a distributed manner from multiple locations and build a database using collective intelligence. [Solution] The information processing device comprises a communication unit that communicates with multiple user terminals via a network, a reception unit that receives registration requests for component information transmitted in a distributed manner from user terminals, and a registration unit that stores attribute information included in the registration request in a component management database and builds or updates correspondence relationships when the same component is registered multiple times. The registration unit improves the reliability of correspondence relationships when the same correspondence relationship is registered from multiple user terminals.

The present disclosure describes systems and methods for enabling real-time conversational dialog among a large population of networked human users while facilitating convergence on groupwise decisions, insights, and solutions, and amplifying collective intelligence. A collaboration server running a collaboration application is provided, wherein the collaboration server is in communication with the plurality of the networked computing devices and each computing device is associated with one user of the population of human participants. In some cases, the collaboration server defines a plurality of sub-groups of human participants. A local video conferencing application on each networked computing device enables real-time communication with other users of a sub-group assigned by the collaboration server. According to some embodiments, an AI-mediated process enables communication to propagate across a plurality of parallel subgroups using simulated participants within each subgroup. In some embodiments, this provides a scalable video-conferencing process for real-time conversational deliberation among large human groups.

The invention discloses an AR remote cooperation method and system based on consensus-driven annotation management, and relates to the technical field of AR remote collaboration.The method comprises the steps that a temporary discussion layer isolated from a field AR visual field is provided for a remote expert and used for carrying out annotation and discussion of an undetermined state, relevant annotations are structured into discussion threads, and the discussion threads are used for carrying out discussion on the undetermined state; through consensus mechanisms such as first-place judgment or voting timeout, collective intelligence of expert teams is fused into a unique final labeling scheme, and only a final labeling party is sent to AR equipment of field personnel. Meanwhile, a complete decision-making process is stored for tracing, so that the problem of information conflict caused by guidance of multiple parties is fundamentally solved, the clarity of the field view is ensured, and the cooperation efficiency and the operation safety are improved.

Embodiments of the present disclosure disclose optimizing model performance of a UE based on collective intelligence at a base station. The base station transmits a first segment of CSI-RS to the plurality of UEs via a DL channel corresponding to each of the plurality of UEs in the area. The base station receives a compressed CSI feedback from each of the plurality of UEs, the compressed CSI feedback including the second segment of the predicted CSI-RS, and the one or more CSI parameters. The base station reconstructs a CSI-RS associated with each of the plurality of UEs based on the CSI feedback received from the corresponding UE and the first segment. The base station identifies one or more UEs from the plurality of UEs that provide the optimized CSI based on a predefined threshold using the reconstructed CSI-RS. Thereafter, the base station sends assistance information and model parameters associated with one or more UEs to each of the plurality of UEs for training the corresponding model. Thus, the present disclosure improves the KPI of the UE based on the model parameters and assistance information of the best performance UE (s).