18 results about "Tacit knowledge" patented technology

The present disclosure herein addresses the problem of synthesizing a series of documents and extracting or summarizing meaningful information or content embedded as tacit knowledge in the series of documents. The embodiment of the present disclosure provides a system and method for tacit knowledge generation using large language model (LLM) in document synthesis. The method of the present disclosure performs intelligent document generation orchestrating a generative artificial intelligence solution workflow. In the present disclosure, tacit knowledge of subject matter experts in a knowledge base or in a series of documents is extracted. Further a content capturing the tacit knowledge is generated leveraging a large language models (LLMs) framework as the underlying architecture. The system of the present disclosure is artificial intelligence (AI) accelerated, cloud agnostic, latency defined, and security enabled.

Business rules are currently not documented and are present only as knowledge with subject matter experts (SMEs). The knowledge can be lost with time if it is not extracted or recorded. Existing techniques are unable to extract tacit knowledge and to retain the domain flavor in extracted information. Present disclosure provides a method and a system for extracting tacit knowledge from historical data. The system represents each point in historical data as a large dimensional hyperspace which contains all unstructured information where tacit knowledge can exist. Then, system maps large dimensional hyperspace to smaller dimensional hyperspace using pre-trained large language model (LLM). Thereafter, system, based on the series of downstream tasks, generates a feedback loop to optimally compute dimension of the smaller dimensional hyperspace. Once reduced dimensional space containing effective tacit knowledge information is available, system performs a downstream task based on the extracted tacit knowledge using another pre-trained LLM.

The invention belongs to the technical field of enterprise knowledge management, and particularly relates to a loose coupling type knowledge management system comprising a resource layer used for collecting knowledge on departments and personal computers, including structured and unstructured data, converting the unstructured data into structured data for preliminary storage, and storing the structured data in a database; and meanwhile, an interface is designed for recording and synchronizing data. According to the system, efficient integration and sharing of knowledge are achieved, the quality and efficiency of enterprise knowledge management are remarkably improved, all kinds of knowledge are collected through the resource layer and converted into structured data to be stored, unified classification processing is conducted through the resource integration layer, dominant and implicit knowledge is stored through the resource library layer in a classified mode, employees can conveniently obtain the needed knowledge, and the enterprise knowledge management efficiency is improved. The knowledge searching time is shortened, the service layer provides multiple knowledge service functions, repeated labor and loss of knowledge are avoided, rich intangible knowledge assets are accumulated for enterprises, and the core competitiveness of the enterprises is enhanced.

As an expert gives instructions to cause movements of their own hands transferred directly as tactile force sense while perceiving surrounding information of a collaborator on a real-time basis and watching the collaborator's line-of-sight end and movements of the collaborator's hands, the collaborator indirectly receives the instructions of the expert's manual skills, which are the expert's tacit knowledge, on a real-time basis while sharing realistic sensations with the expert who is at a remote location when the collaborator performs an act of working with their own hands.

This invention discloses a system for converting tacit knowledge into explicit knowledge based on knowledge graphs and large models. It includes a knowledge system ontology modeling and management module for constructing and maintaining the knowledge system ontology model in large model applications; a data access and knowledge graph construction module for mapping and loading multi-source heterogeneous data onto the knowledge system ontology; an ontology virtual business environment engine module; a tacit knowledge mining and explicit knowledge generation module that, in a virtual environment, uses graph analysis and large model reasoning to mine tacit knowledge and generate explicit knowledge; and a business strategy planning and workflow orchestration module that transforms explicit knowledge into executable business strategy plans and workflow orchestrations. Through the knowledge system ontology modeling and management module, a systematic knowledge framework is constructed, achieving systematic accumulation of enterprise tacit knowledge, effectively preventing knowledge loss, and improving knowledge reusability and scalability.

This invention discloses a method, apparatus, device, and medium for solidifying tacit knowledge, relating to the field of artificial intelligence technology. The method includes: acquiring the current task context; using a generative agent to determine unprocessed items; and having the generative agent search for these unprocessed items in a preset factual knowledge base and / or normative knowledge base to generate valid search records; assembling first prompt words and invoking a large language model to reason about the first prompt words, obtaining preliminary results; comparing the preliminary results with standard examples in the current task context to generate a difference report; assembling second prompt words and invoking a large language model to reason about the second prompt words; extracting tacit knowledge based on the difference report; and solidifying the tacit knowledge contained in the standard examples. This invention mines and extracts the tacit knowledge of experts, achieving the solidification of tacit knowledge and realizing the accumulation, reuse, and structured management of enterprise knowledge assets.

Examples described herein provide a method for capturing and representing tacit knowledge to enhance artificial intelligence (AI) aided decision making. The method includes capturing raw data from the user interaction and extracting a tacit knowledge representation from the raw data. The method also includes generating recorded tacit knowledge by systematically recording tacit knowledge representations in the knowledge management system, the tacit knowledge representations including individual actions and decisions taken during the particular task. The method also includes classifying the recorded tacit knowledge to create a structured knowledge representation. The method also includes integrating the structured knowledge representation into the AI system, wherein the AI system utilizes implicit knowledge to improve the quality of the data input and enhance decision making ability. The method also includes providing a personalized knowledge management system that allows individuals to record their decision making processes.

A processing device (10) comprises: a question extraction unit (11) that, using an LLM (20), extracts, from a plurality of dialogues between an expert and a user, questions asked by the expert in order to elicit information from the user; a proposal extraction unit (12) that, using the LLM (20), extracts, from the plurality of dialogues, proposals made by the expert in order to solve the problem of the user; a structuring unit (13) that, using the LLM (20), converts a dialogue between the expert and the user into a flow having information indicating a question, the user's answer to the question, and the proposal accepted by the user; and a chart construction unit (14) that statistically constructs, on the basis of a plurality of the flows, one flowchart indicating the tacit knowledge and judgment of the expert.

The invention discloses a course recommendation method based on a learning track and a knowledge graph, relates to the technical field of course recommendation, and systematically overcomes the implicit knowledge fault problem in English course recommendation through a deep coupling mechanism of a dynamic knowledge graph and the learning track. Persistent application errors, such as tense confusion in writing, which cannot be captured by a traditional system are converted into negative feedback signals of a knowledge graph, and a knowledge point association path is compensated and reconstructed through local sub-graph weight, so that recommended contents are upgraded from repeated question brushing to link repair, and a direct click test is high in score but low in application efficiency; aiming at cross-skill migration obstacles, a reduced-order expression sub-graph technology is initiated, a cognitive step is established through simplified paraphrasing of terms and scenarized case nodes, migration faults which cannot be scared and understood are cracked, and the method is particularly suitable for complex context scenes such as business English and the like.

The invention discloses a method, a device, equipment and a medium for solidifying implicit knowledge, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring a current task context, determining an unprocessed item by utilizing a generation agent, and performing retrieval in a preset fact knowledge base and / or a standard knowledge base by the generation agent according to the unprocessed item, generating an effective retrieval record; assembling the first cue word, and calling a large language model to reasone the first cue word to obtain a preliminary result; comparing the preliminary result with a standard example of the current task context to generate a difference report; and assembling a second cue word, calling the large language model to reasone the second cue word, extracting the implicit knowledge according to the difference report, and solidifying the implicit knowledge contained in the standard paradigm. According to the method, implicit knowledge of experts is mined and extracted, solidification of the implicit knowledge is realized, and accumulation and reuse of enterprise knowledge assets and structured management are realized.

According to the modern industry college industry-university-research project full-life-cycle management and contribution degree metering system provided by the invention, by fusing multi-source heterogeneous data such as codes, documents and communication and extracting multi-dimensional features, the limitation of single metering dimension of a traditional method is overcome; an adaptive weight adjustment algorithm based on a project stage is introduced, so that the importance of contributions of different dimensions such as code development, technical documents and collaborative communication can dynamically change along with a project process, and the timeliness and situation adaptability of evaluation are improved; an influence propagation model based on a complex network theory is utilized to quantify implicit knowledge transmission and leadership contribution in a project collaborative network for the first time, and the problem that indirect contribution is difficult to measure is solved; the comprehensive contribution degree obtained through calculation is directly linked with management decisions such as resource allocation and authority management, and the crossing from static statistics to dynamic intelligent decisions is achieved. According to the invention, the collaborative efficiency, resource utilization efficiency and management intelligence level of industry-university-research projects are effectively improved.

The examples described herein provide a method for capturing and representing tacit knowledge to improve AI-supported decision-making. The method involves capturing raw data from user interactions and extracting representations of tacit knowledge from this raw data. It further involves generating documented tacit knowledge by systematically recording representations of tacit knowledge, including individual actions and decisions taken and made during specific tasks, in a knowledge management system. Finally, the method includes categorizing the documented tacit knowledge to generate structured knowledge representations.The process further includes integrating the structured knowledge representations into an AI system, whereby the AI ​​system uses the implicit knowledge to improve the quality of data inputs and enhance decision-making capabilities. The process also includes providing a personalized knowledge management system that allows individuals to document their decision-making processes.

This technology quantifies and visualizes the intuitive information that was previously the tacit knowledge of the practitioner, enabling objective decision-making support. [Solution] A program for operating a computer 20 comprising a processor 29 and memories 25 and 26, wherein the memories 25 and 26 store a trained model that takes acoustic data acquired in an environment where vascular treatment is being performed as input and outputs risk assessment information regarding vascular treatment procedures. The program causes the processor 29 to perform a first step of receiving acoustic data, a second step of inputting the acoustic data received in the first step into the trained model and acquiring risk assessment information output from this trained model, and a third step of outputting the risk assessment information acquired in the second step in a form that can be perceived by humans.

Provides information on operational processes, including tacit knowledge. [Solution] A program for causing one or more computers to execute the following steps: an action type receiving step for receiving an action type; a tentative process information obtaining step for obtaining tentative process information indicating a tentative action process by inputting a prompt including an instruction to generate an action process corresponding to the action type into a generation model; a tentative process information presenting step for presenting the tentative process information to an actor; a video obtaining step for obtaining an action video of the actor to whom the tentative process information was presented performing the action process; a process information obtaining step for obtaining process information by inputting a prompt including the action video and an instruction to generate process information indicating the action process into a generation model; and a process information output step for outputting the process information.

Collect tacit knowledge from experts. [Solution] The agent system 2 is characterized by comprising a video playback unit 26 that displays a video of the site on a display 41 and presents it to the user 4, a questioning unit 27 that asks the agent using a large-scale language model 200 questions of the user 4 about how to respond to each situation in the manufacturing site 1, and a data collection unit 28 that collects dialogue between the agent and the user 4.

The invention discloses an implicit knowledge explicit multichannel man-machine collaborative natural interaction method, which comprises the following steps of: (1) analyzing collaborative task sensing nodes taking an operator as a center to obtain a sensing information flow model in a man-machine-ring in a collaborative scene, and researching an explicit and implicit knowledge conversion chain in a man-machine collaborative combat process; step (2), constructing an SECI model of knowledge conversion, representing that there is explicit and implicit knowledge in a collaborative combat man-machine loop closed-loop system, and obtaining knowledge conversion node importance weight under a man-machine collaborative task; step (3), according to knowledge conversion node importance weights, carrying out an eye movement physiological evaluation experiment to obtain a behavior cognitive map fusing multiple perception channels, and explicitly expressing tacit knowledge in multichannel interaction behaviors; and step (4), outputting a multi-channel man-machine collaborative natural interaction method according to the behavior cognitive map. The method provides reference for man-machine collaborative interaction design of a multi-channel interaction system by mining behavior interaction implicit knowledge of an operator.

The invention provides a silence knowledge reasoning and analogy decision-making method for an AGI, which solves the problem that the AGI lacks deep structure analogy and mapping of situations and allusions, and the like, and comprises the following steps: S1, training a philosophy semantic understanding model; s2, constructing a structured allusion knowledge base; and S3, executing situation-allusion analogy reasoning. The method has the advantages of being high in interpretability, wide in universality and the like.

Methods and systems for capturing tacit knowledge data from an expert user and methods and systems for using the captured tacit knowledge data to assist a novice user. Steps of a computer-implemented method for capturing tacit knowledge data from an expert user comprise: receiving expert data, analysing the expert data, and storing the sequence of expert actions in a database. The expert data comprises expert real-time data received while the expert user performs a task. The expert real-time data comprises expert sensor data from a first plurality of sensors monitoring the expert user and / or the surroundings of the expert user. Analysing the expert data uses a machine learning system to determine what actions the expert user has performed. The analysing comprises classifying the expert data to determine expert actions that the expert has performed and clustering the expert actions into a sequence of expert actions.