1221results about "Other databases retrieval" patented technology

To realize improvement of complicated task execution ability under unpredictable circumstance, understanding and execution of high-level abstract instructions, effective integration of multi-modal feedback, enhancement of ability to adapt itself to change of environment and uncertainty, efficient use of knowledge base, and securing expandability.SOLUTION: The present invention is directed to a robot control system which integrates a large-scale language model, retrieval-enhanced generation technique, a visual system, a force sense module, a voice recognition and synthesizing module, a multi-modal integration module, and a robot control system. A language processing component recognizes high-level instructions, and dynamically selects and adapts relevant examples from a knowledge base by using the retrieval-enhanced generation technique. The visual system generates a three-dimensional expression of an environment. The force sense module measures force of an end effector. The multi-modal integration module integrates information from different modalities to realize environment understanding and adaptive action generation. Thus, it is possible to adapt the system to execution of complicated tasks and change of the environment under an unpredictable environment.SELECTED DRAWING: None

The invention relates to the technical field of data analysis, can be applied to business scenes of medical health, financial science and technology, cultural research and the like, and discloses a multi-modal abstract generation and output method, which comprises the following steps of: acquiring target domain data and cleaning to obtain structured data; extracting entities and association relationships among the entities from the structured data, and constructing a target domain knowledge graph; generating a text abstract containing entity associated information based on the target domain knowledge graph; matching the image data and the audio data corresponding to the text abstract, and integrating the text abstract, the image data and the audio data to generate a multi-modal abstract; and constructing a user portrait according to the user behavior data, and outputting the multi-modal abstract based on the user portrait. According to the method, extraction and analysis of entities and association relationships thereof are optimized through knowledge graph construction; through multi-modal fusion, associated display of texts, images and voices is realized; and through user portrait optimization output, the efficiency and adaptability of knowledge summarization are improved.

There are provided systems and methods for automated chatbots that detect privacy data sharing and leakage by other automated chatbot systems. A service provider and other chatbot services, including an electronic transaction processor, may provide self-service channels for assistance through chatbot and other automated computing processes. However, these chatbots may be regulated by compliance with privacy protection requirements, and therefore use of the chatbots and / or user data when responding to users via chatbots in chat sessions may be noncompliant and / or attacked by malicious users to compromise privacy protected data. In order to facilitate detection of leaks and shares by chatbots, an AI for a privacy protection chatbot may be trained on regulations for chatbot use and / or data security and privacy protection. The chatbot may then interact with other chatbots and question the other chatbots using the trained AI model to detect whether privacy protected data is exposed.

The invention discloses a self-adaptive data knitting performance optimization method based on artificial intelligence. The method comprises the steps of obtaining multi-source heterogeneous data based on a data source list and analyzing the multi-source heterogeneous data to generate a metadata set at least comprising technical metadata, business metadata, operation metadata and management metadata; based on the virtual table interface, performing virtual table abstraction and packaging processing on the metadata set to generate a logic data carrier; determining an operational attribute of the metadata set to generate a data knitting path of the logical data carrier based on the operational attribute; monitoring the data access task queue and the access index feedback in real time, extracting resource load association features from the data access task queue and the access index feedback based on the constructed resource scheduling model, and generating a resource scheduling strategy according to the resource load association features; and optimizing the data knitting path of the logic data carrier based on a resource scheduling strategy to obtain an optimized data knitting path so as to perform data knitting on the multi-source heterogeneous data.

The invention relates to the technical field of automobile fault detection, in particular to an automobile fault detection and diagnosis case library construction method based on rules and a fault tree, which comprises the following steps: performing context enhancement on original fault data by external environment data to obtain environment enhanced fault associated data; performing fault classification on the automobile fault features to obtain fault classification labels; performing rule matching on the fault classification label according to a preset expert rule base to obtain a matching result; performing case correlation analysis according to the fault propagation chain and a preset historical diagnosis case library to obtain case correlation characteristics; constructing a case library according to the structured case model to obtain a diagnosis case library; and sending the diagnosis case library to a cloud platform to execute automobile fault detection and diagnosis. According to the method, the fault classification labels are subjected to rule matching, the known fault modes can be quickly and effectively identified according to expert experience, and corresponding solutions can be provided for known faults.

To provide a mechanism capable of easily searching for information indicating a file storage location without being restricted by circumstances under which the file has been stored on a network.SOLUTION: A user terminal 101, which can be connected via a network 105 to a large language model server 103 in which a large language model searches for URLs being information indicating file storage locations on the basis of similarity of language vectors of natural language, comprises a CPU 201 that transmits, in natural language, a query sentence for inquiring about a file storage location to the large language model, and receives, from the large language model, a response sentence that conveys a URL being information indicating the file storage location searched by the large language model using a language vector of the natural language of the query sentence.SELECTED DRAWING: Figure 1

Methods, apparatus, and processor-readable storage media for detecting device component defects and generating corresponding recommendations using artificial intelligence techniques are provided herein. An example computer-implemented method includes obtaining image data of one or more device components and user input pertaining to at least a portion of the device component(s); predicting at least one defect associated with the device component(s) by processing at least a portion of the image data and the user input using a first set of artificial intelligence techniques; determining, using a second set of artificial intelligence techniques, that the at least one predicted defect is repairable; generating recommendation(s) for repairing the defect(s) by processing, using the second set artificial intelligence techniques, the at least a portion of the image data, the at least a portion of the user input, and information pertaining to the defect(s); and performing automated actions based on the recommendation(s).

A method and system for action preset based application programming interface (API) call is disclosed. In some embodiments, the method includes receiving a natural language instruction from a user, processing the natural language instruction to extract a set of parameters through a large language model, comparing the extracted parameters against a preset database to find a matching action preset, formatting an API request by combining the extracted parameters with default values obtained from the matching action preset, and sending the formatted API request to an external API endpoint to execute the API request.

A system and method for accuracy-enhanced processing of query data within a multi-digital agent architecture may include receiving unrefined query data including textual data; retrieving historical user dialogue data from a computer database associated with the unrefined query data; transforming the unrefined query data to refined query data based on the retrieved historical user dialogue data; generating at least one digital agent classification inference using the refined query data; routing the refined query data to a digital agent based on the at least one digital agent classification inference; generating, by the digital agent, a digital response to the unrefined query data; and returning the digital response to an interactive graphical user interface.

Provided are an information processing apparatus, a method, and a program that present an answer considering the operation of an organization to a user's question. 【Solution means】In an information processing system, an information processing apparatus 2 includes a reception unit 231 that receives a question from a user, an identification unit 232 that identifies the attributes of the user in the organization, a document acquisition unit 233 that acquires a relevant document, which is a document including content related to the question received by the reception unit, from a document management database, a generation unit 234 that generates a request prompt including a determination request for determining whether the relevant document acquired by the document acquisition unit is permitted to be disclosed to the user based on the attributes of the user and the public permission attributes included in the relevant document acquired by the document acquisition unit, a result acquisition unit 235 that acquires an output result output by a predetermined language model by inputting the request prompt generated by the generation unit into the predetermined language model, and a presentation unit 236 that presents information based on the output result acquired by the result acquisition unit to the user.

The invention belongs to the technical field of data and graph conversion, and discloses a data information and graph conversion management system applied to a design drawing, and the system comprises a data collection module which collects design data from a device end, a main system end and a background database, and guarantees the stability and accuracy of data collection through a built-in verification mechanism; after receiving the data of the acquisition module, the data preprocessing module unifies the data in different formats into a system standard format, removes redundant records and corrects logic errors, so that the data structure is unified and the formats are compatible; the unit conversion module receives the preprocessed data, and performs unit conversion on flow and pressure parameters by utilizing a rule base according to a factory standard and an equipment source unit, so that the data units are unified; and after the rule operation module obtains data with unified units, a merging calculation model is called to carry out data classification, traffic sum calculation and traffic load verification.

The invention provides a medical record data extraction script generation method and device, computer equipment and a medium, and relates to the technical field of medical informationization, and the method comprises the steps: extracting information of a plurality of three-party medical record fields in a three-party medical service system from an interface document of a medical record data interface in the three-party medical service system, according to the identification information of each three-party medical record field, determining identification information of a target structured medical record field matched with the three-party medical record field in a target medical service system and target library table information to which the target structured medical record field belongs, and according to a current field mapping relationship between the identification information of the three-party medical record field and the identification information of the target structured medical record field, and the target library table information, generating a target medical record data extraction script for the three-party medical service system. According to the method, automatic generation does not need to be performed by professional medical personnel, the target medical record data extraction efficiency is improved, the labor cost is reduced, and the data extraction accuracy is improved.

To optimize a combination of a plurality of language models to be discussed and their prompts.SOLUTION: The recommended information consultation device 1 for risk assessment includes an answer generation unit 131 that answers a search result obtained by extracting and summarizing specific information based on a plurality of cases, a consultation processing unit 132 that consults the search result answered by the answer generation unit 131 with a predetermined number of language models and a predetermined prompt, and a model optimization unit 133 that evaluates a consultation result by the consultation processing unit 132 and optimizes the number of language models used by the consultation processing unit 132 and a combination of prompts.SELECTED DRAWING: Figure 1

To provide an information processing system and so on which can reduce a work load upon machine learning.SOLUTION: The present invention is directed to an information processing system having at least one processor according to an embodiment thereof. In the information processing system, the processor acquires, in its history acquiring step, acquires a response history indicating an inquiry from a user and a response to the inquiry from a person in charge. In a learning instruction step, the processor gives an artificial intelligence module instructions to carry out machine learning using at least learning data using the inquiry indicated by the acquired response history as an input and the response indicated by the response history as an output.SELECTED DRAWING: Figure 1

The invention relates to airspace state updating, in particular to a GeoSOT airspace graph data dynamic updating method and a GeoSOT airspace graph data dynamic updating system, multi-source heterogeneous data is accessed in real time, and data differences are eliminated by mapping the data to a GeoSOT-3D grid to unify a space-time reference; dynamic attributes are given to each GeoSOT-3D grid, local updating and version management are supported, and real-time representation and historical tracing of the airspace state are achieved; low-delay updating of a grid state is realized through event triggering and edge calculation, and spatial domain resource allocation is optimized in combination with AI prediction; according to the technical scheme provided by the invention, the defects that real-time representation and historical tracing of the airspace state are difficult to realize and the updating delay of the airspace state is relatively high in the prior art can be effectively overcome.

The invention discloses a multi-source big data analysis cloud platform and a data analysis method thereof, and relates to the technical field of big data analysis. The method comprises the steps of receiving multi-source data to form a multi-source big database, obtaining a to-be-analyzed application field, extracting theme elements, capturing corresponding application field data from the multi-source big database and classifying the application field data, constructing an application field classification database, determining a multi-source data fusion coefficient influencing the application field according to the theme elements, and analyzing the multi-source data fusion coefficient. And performing multi-source data classification feature extraction and feature fusion on the application field classification database to generate multi-source data fusion features, and inputting the multi-source data fusion features into a pre-trained application field data analysis model to obtain an analysis result. According to the method, mass data of different formats and structures from different service systems can be gathered, multi-source data of the required application field can be quickly captured from multi-source big data, the multi-source data is integrated and analyzed, potential relations which are difficult to perceive by a traditional analysis method are found, and the analysis accuracy and reliability are improved.

To provide a method of supporting a chatbot for conversation with a user, so as to improve the accuracy of responses.SOLUTION: A program to be executed on a computer causes the computer to execute the steps of: acquiring a user question; acquiring a vector value which is generated by transforming the user question into a vector using a vector-conversion machine learning model; acquiring data corresponding to an approximate value of the vector value detected by inputting the vector value to at least one database of a plurality of preset databases; causing a language model to generate an answer based on the data corresponding to the approximate value; and transmitting data for displaying the answer on a user terminal.SELECTED DRAWING: Figure 6

Provided in the embodiments of the present disclosure are a training data acquisition method, system and apparatus, a storage medium and a program. The training data acquisition method comprises: acquiring an initial data set having data of the same type, and using a plurality of candidate processing modes to process the data in the initial data set so as to obtain a plurality of data sets; on the basis of the plurality of data sets, training a small model to obtain a trained small model; and, on the basis of the trained small model, evaluating the plurality of candidate processing modes to determine a target processing mode, the target processing mode being configured to process pre-trained data so as to obtain training data of a large model, and the size of the small model being smaller than that of the large model. The present disclosure uses the different candidate processing modes to obtain the data sets for small model training, and evaluates the performance of the small model to select an optimal data processing mode for determining the training data for the large model, thereby obtaining training data which is easy for the large model to learn and remains intact, and allowing the large model to achieve optimal performance with fewer training steps.

To provide an information processing system, an information processing method and a program, which efficiently estimate a use purpose for a system that interactively replies for input of a user.SOLUTION: A chat bot 100 that interactively replies for input of a user includes: a reply generation unit 121 that receives user input from a user input reception unit 110 to generate a reply of the chat bot for this input; a reply output unit 122 that returns the reply generated by the reply generation unit 121 to the user and outputs the reply to a category estimation device 130; a category estimation unit 131 that estimates a category of the use purpose for the chat bot of the user in a series of exchange comprising the user input and the reply of the chat bot (hereinafter, conversation); and an estimation result output unit 132 that outputs the category estimated by the category estimation unit 131 to a log DB 140.SELECTED DRAWING: Figure 1

To improve the accuracy of a response created in response to a user's inquiry.SOLUTION: An information processor comprises: acquisition means for acquiring emotional information of a user based on at least one of a captured image and the voice of the user; prompt generation means for generating a prompt based on the emotional information and one or more keywords extracted from the voice; and output means for outputting an answer obtained by using the prompt generated by the prompt generation means.SELECTED DRAWING: Figure 2

To improve the quality of an answer to a prompt from a user.SOLUTION: An information processing apparatus according to an embodiment of the present invention includes a reception unit configured to receive a prompt from a user terminal, a document search unit configured to search for a document based on the prompt, an answer generation unit configured to cause a large scale language model to generate an answer to the prompt based on the prompt and the document, a transmission unit configured to transmit the answer to the user terminal, an evaluation unit configured to evaluate the answer based on an action of a user who operates the user terminal, and an answer management unit configured to store the answer and a result of the evaluation in association with each other.SELECTED DRAWING: Figure 2

A method includes: detecting one or more proxy objects in a space around an autologous object using image data captured by a camera of the autologous object; storing a hierarchical node graph, the hierarchical node graph comprising a destination layer and a plurality of interaction layers of interaction nodes following the destination layer, the destination layer comprising one or more destination nodes; adding an interaction node to an interaction layer of interaction nodes in the plurality of interaction layers; determining a trajectory score for each of the plurality of trajectories based on one or more node scores of one or more nodes corresponding to the trajectory within the hierarchical node graph; and selecting a trajectory of the plurality of trajectories for the autologous object based on the trajectory score for the trajectory.

A dialogue processing apparatus includes one or more computers each including a memory and a processor configured to receive a question Qi as a word string representing a current question in an interactive machine reading comprehension task, a question history {Q1, . . . , Qi−1} as a set of word strings representing previous questions, and an answer history {A1, . . . , Ai−1} as a set of word strings representing previous answers to the previous questions, and use a pre-learned first model parameter, to generate an encoded context vector reflecting an attribute or an importance degree of each of the previous questions and the previous answers; and receive a document P to be used to generate an answer Ai to the question Qi and the encoded context vector, and use a pre-learned second model parameter, to perform matching between the document and the previous questions and previous answers, to generate the answer.

To provide more suitable artificial intelligence response output technique which contributes to the Sustainable Development Goals (SDGs): "9 Build resilient industries, promote innovation, and strengthen industrial capacity" and "11 Make cities and human settlements inclusive, safe, resilient, and sustainable".SOLUTION: A response output device comprises an input part and a control part that generates a response request on the basis of user input from the input part, transmits the response request to a large-scale language model, and outputs a response from the large-scale language model in response to the response request. The control part performs a search process based on search conditions specified by a user, extracts candidate content files to be registered in the response request, and registers the content file selected by the user from the extracted candidates in the response request.SELECTED DRAWING: Figure 8

To provide an information processing device capable of suppressing an inappropriate response, an information processing method, and an information processing program.SOLUTION: An information processing device comprises a generation unit, an acceptance unit, and a determination unit. The generation unit generates non-response target information indicative of a non-response target. The acceptance unit accepts information indicative of a user's request. The determination unit determines whether or not the request indicated by the information accepted by the acceptance unit is a request on the non-response target on the basis of the plurality of pieces of non-response target information generated by the generation unit.SELECTED DRAWING: Figure 3

To output an appropriate answer when a generative AI accepts a question regarding an ability of a system or itself under a situation that the generative AI is integrated in the system to be used.SOLUTION: An information processing device 16 acquires interaction data input from a user. The information processing device 16 refers to a system configuration database 162 in which configuration data representing a configuration of an information processing system 10 is stored and outputs answer data according to the configuration data when the interaction data represents a question regarding an ability of the information processing system 10 or a generative AI.SELECTED DRAWING: Figure 2

To provide a quantification device, a quantification method and a quantification program capable of quantitatively evaluating uncertainty of a response in a system using retrieval extension generation and a generation language model.SOLUTION: A quantification device 1 includes a first index calculation unit 11 for calculating a first index that shows uncertainty of an output generated to an input to a generation language model and does not consider retrieval quality in retrieval extension creation, a second index calculation unit 12 for calculating a second index showing the retrieval quality in the retrieval extension generation, an index adjustment unit 13 for normalizing the second index and adjusting it as an influence degree to an output of the retrieval quality, and an output unit 14 for multiplying the first index by an adjusted value and outputting it as a value obtained by quantifying the uncertainty of the output in the generation language model using the retrieval extension generation.SELECTED DRAWING: Figure 1

A response device according to the present invention comprises: an input unit that is configured to receive input of first text which indicates a question related to a certain task; a search unit that is configured to acquire, from among information pertaining to the task, similarity information which is similar to the first text; a prediction unit that is configured to acquire related information which is stored in association with the similarity information, generate second text which requests the generation of a response to the first text with reference to the similarity information and the related information, and input the second text into a machine learning model which is trained to generate text according to input text; and an output unit that is configured to output text which has been generated by the machine learning model. Thus, it is possible to provide professional answers to questions in an easily understandable format.

An information processing device according to the present invention includes an answer generation unit for generating an answer to a query input by a user, by using a plurality of trained models generated by machine learning, and a contribution degree calculation means for calculating a contribution degree of each trained model to the answer generated by the answer generation unit. According to this information processing device, an answer to a query can be optimized.