1998results about "Other databases retrieval" patented technology

Systems and methods are provided for implementing automatic prompt optimization using textual gradients. In various embodiments, a feedback prompt, input into a large language model (“LLM”), is used to generate textual gradients that criticize a current prompt. The feedback prompt includes the current prompt and predictions that are incorrect compared with corresponding labels associated with minibatch data processed by the LLM using the current prompt. The textual gradients and current prompt are used in an editing prompt to the LLM to obtain a set of optimized prompts, which may be expanded using a paraphrasing prompt that is input into the LLM to generate a set of paraphrased prompts. A selection algorithm is used to select one or more optimized prompts from the set of optimized prompts and / or the set of paraphrased prompts, and the process is repeated with the selected one or more optimized prompts replacing the current prompt.

A browsing support system is provided that enables medical-related information to be entered accurately. [Solution] The information processing terminal 10 included in the browsing support system 1 has an input unit 12 that creates questions for contents to be registered in the electronic medical record displayed on the display unit 11. The medical record management system 3 has a medical record management unit 31 that outputs creation information for creating the electronic medical record, which is input by the information processing terminal 10, to a RAG system 4, receives answers from the RAG system 4, and supports the creation of the electronic medical record. The RAG system 4 has a vector DB 52 that stores knowledge that has been vectorized and embedded in a vector space, and a knowledge search unit 44 that searches the vector DB 52 for knowledge based on the vectorized creation information and outputs answers formed from the searched knowledge to the medical record management unit 31.

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

To facilitate, when a generative AI being used is changed to another generative AI on the way, causing another generative AI after the change to take over an experience of conversations with the generative AI being used.SOLUTION: A generative AI management system according to the present invention is connected to servers of a plurality of generative AIs to provide user terminals with a function for utilizing the plurality of generative AIs and comprises: a recording control unit which records the plurality of generative AIs; an input information acquisition unit which acquires information to be given to one generative AI out of the plurality of generative AIs, as input information; an answer information acquisition unit which acquires an answer of the one generative AI corresponding to the input information, as answer information from a server; a conversation data storage unit in which the input information and the answer information corresponding to the input information are stored in association with each other as conversation data; and a training unit which, when the one generative AI is changed to another generative AI, trains this generative AI by using the conversation data which is stored in the conversation data storage unit and is obtained by conversation with the one generative AI.SELECTED DRAWING: Figure 4

To enable appropriate response to a user input.SOLUTION: An action control system disclosed herein is configured to: input an instruction to inquire about a travel plan to a sentence generation model as a first prompt to generate a travel plan proposal; input an instruction to make a proxy reservation to the sentence generation model as a second prompt to generate a reservation plan proposal, input an instruction to inquire about items to bring on the travel to the sentence generation model as a third prompt to generate travel possession proposal; input an instruction to inquire about questions during travel to the sentence generation model as a fourth prompt to generate proposed answers; and acquire the generated travel plan proposal, reservation plan proposal, travel possession proposal, and proposed answers as a result of specific processing.SELECTED DRAWING: Figure 2A

Machine learning model optimization explainability application is provides explanations (e.g., natural language explanations) for the operations and decisions associated with an optimization model (e.g., optimization algorithm) used to solve an optimization problem. More specifically, the software application for machine learning model optimization explainability enables explainability for a query that determine how the solution was generated. The system can provide a query response (e.g., natural language explanation), and perform a variety of different actions to address any issues surfaced in the query response.

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.

To generate a prompt that includes valid sentences as reference information for an input question sentence within a determined character limit.SOLUTION: A sentence generation device comprises: an additional sentence generation unit 11 that generates additional sentences related to a question sentence based on a question sentence input by a user, with a total number of characters including the number of characters in the question sentence not exceeding the character limit that can be input to an answer generation unit 20 of a large-scale language model (LLM) 1; and a prompt generation unit 12 that generates a prompt by adding the additional sentences generated by the additional sentence generation unit 11 to the input question sentence as reference information. The sentence generation device generates the additional sentences so that the number of characters does not exceed the character limit that can be input to the LLM 1 as a prompt, thereby making it possible to generate a prompt that adds valid sentences to the input question sentence as reference information within the determined character limit.SELECTED DRAWING: Figure 2

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.

SOLUTION: An answer feedback method to be applied to a large-scale language model includes the steps of: receiving a question inputted by a user; generating a candidate answer set for a question, selecting an answer from the candidate answer set as a target answer and displaying the target answer to the user by a pre-training large-scale language model; and generating a feedback page in accordance with the reception of a feedback request transmitted to the target answered by the user, and displaying the feedback page to the user. A content of the feedback page includes the candidate answer set. Also, the method includes a step of specifying an answer indicated by an update request in the candidate answer set as a new target answer, and displaying the new target answer to the user in accordance with the reception of an update request transmitted to the feedback page by the user.EFFECT: An explicit correct answer given from a user can be simply acquired, and the accuracy of an answer feedback result can be improved.SELECTED DRAWING: Figure 2

In some implementations, a computing device may include one or more processors, a memory for storing instructions that when executed by the one or more processors perform operations may include: accessing a drill plan for a drilling operation; receiving a plurality of drilling parameters for the drilling operation; generating a report including: a graphical depiction of the drilling operation based on the plurality of drilling parameters for the drilling operation, the graphic depiction including an animated or video illustration of the drilling operation within a past predetermined time period; a plurality of metrics associated with the drilling operation as provided by the drill plan; and a summary of a planned activity for a drilling operation for a future predetermined time period. Also, the device may include saving the report on a sever connected to a network. Further, the device may include providing the report to at least one user. Similar systems and methods may be used to automatically generate and distribute or provide access to video reports of completion and / or production activities during a first time interval and planned completion and / or production activities during a future, second time interval.

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.

To enhance the quality of response data to question data, when acquiring the response data utilizing a large-scale language model.SOLUTION: A management server 1 is an information processing device which can acquire response data to question data input to a language model server 3 from the language model server 3. The management server 1 includes: a prior knowledge narrowing unit 62 for extracting a first character string "rabbit" associated with LLM determination 305 "unknown", from each term included in the question data, in prior knowledge DB 300 for holding the LLM determination 305, a term 303, and a description 304 thereof in association with each other; and a provision information generation unit 63 and a response information management unit 64 for inputting a prompt 730 including the first character string "rabbit" and the description 304 associated with the first character string "rabbit" in the question data to the language model server 3, and acquiring the response data to the question data from the language model server 3.SELECTED DRAWING: Figure 3

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.

A program, method, information processing device, and system for creating an optimal FAQ are provided. [Solution] The method includes a document acquisition step of acquiring specified document information, a first generation step of generating a first prompt for creating a question related to content described in a first part that is part of the specified document information, a first acquisition step of acquiring the specified question that is output by inputting the first prompt into a generation AI, a part extraction step of extracting a second part from the specified document information acquired in the document acquisition step that is related to the specified question acquired in the first acquisition step, a second generation step of generating a second prompt that includes the second part and is for creating an answer to the specified question, a second acquisition step of acquiring a specified answer that is output by inputting the second prompt into the generation AI, and an FAQ storage step of associating and storing the specified question and the specified answer.

A data processing device 1 comprises: a control signal acquisition unit 13 that acquires a control signal of a vehicle; and a prompt generation unit 14 that generates a prompt for a language model for outputting language information. The prompt generation unit 14 generates a prompt including vehicle text obtained by converting the control signal into text, and the prompt includes text indicating the format or range of an answer sentence obtained according to the language model.

To provide a method and a system for recommending a question for linkage with a content of an information provider as an answer to a question of a user.SOLUTION: The method for recommending a question according to an embodiment includes the steps of: generating an LLM result based on an LLM (Large Language Models: LLM) to a prompt of a user; and providing the generated question as a response to the prompt of the user along with the generated LLM result.SELECTED DRAWING: Figure 4

An information processing system and program are provided that can assist in creating prompts to be input into a generative AI system. [Solution] An information processing system 10 that is available from a plurality of user terminals 12 having a display means 13 and is equipped with a control means 20 and a storage means 21, the control means 20 being equipped with a user terminal communication unit 30 that generates display content, a prompt acquisition unit 31 that acquires an input prompt, and a prompt evaluation unit 32 that evaluates the prompt, the prompt evaluation unit 32 storing the evaluated prompt in the storage means 21 as a shared prompt if the evaluated prompt is highly rated, and the user terminal communication unit 30 is an information processing system 10 that generates display content including an input area 40 for the prompt, a display area 44 for AI output information, and a display area 45 for the shared prompt stored in the storage means 21.

The present invention provides a highly convenient automatic response data improving device, method, and program that can effectively present to a user information that is the basis for determining learning data suitable for input. [Solution] In order to improve the answer accuracy of an automatic answering device 2, the device analyzes and presents information that serves as a clue to learning data that is recommended to be input, and is composed of a user evaluation means 11, an answer evaluation means 12, an evaluation data analysis means 13, a topic estimation means 14, an answer evaluation display means 15, a simulation means 16, and a topic correction means 17. The user evaluation means 11 accepts user evaluations. The answer evaluation means 12 generates answer evaluation data that evaluates the quality of automatic answers. The topic estimation means 14 performs natural language processing and classifies into categories using topic modeling. The evaluation data analysis means 13 analyzes the quality of automatic answers for each category.

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.

To provide a data processing apparatus, a data processing method, and a program capable of giving advice for relieving user's feeling.SOLUTION: A data processing apparatus includes: a state recognition unit which recognizes a user's state; a feeling recognition unit which recognizes user's feeling on the basis of the user's state when the user's state satisfies a trigger condition determined in advance; a processing unit which acquires advice to the user using output of a data generation model by inputting a prompt including a result of recognizing the user's feeling and an instruction text to obtain advice for relieving the user's feeling, to the data generation model that generates a sentence according to the input data; and an output unit which outputs the acquired advice.SELECTED DRAWING: Figure 4

To provide a data processing device, a communication terminal, a data processing method, and a program that can contribute to reducing the burden on an answerer and a questioner when the answerer answers questions from the questioner and the questioner collects answers from the answerer, and to collecting highly reliable answers.SOLUTION: A data processing device includes an execution unit that interactively asks questions to an answerer and makes answers to the questions from the answerer, a generation unit that generates summary data that summarizes the answers by using a summary data generation model, and an output unit that outputs at least one of the summary data and data based on the summary data.SELECTED DRAWING: Figure 6

To provide an information processing system and a program capable of improving prompts when AI output information from a generation AI system is not as desired. [Solution] The information processing system comprises a control means 20 and a memory means 21, and the control means 20 comprises a user terminal communication unit 30, a prompt generation unit 31, a prompt sending unit 33, and an AI output information acquisition unit 34, wherein the prompt generation unit 31 sends AI output information acquired in response to the initial prompt to the user terminal 12, and then generates an improvement request prompt that requests an improvement prompt that improves the initial prompt based on the AI ​​output improvement information input at the user terminal 12, the prompt sending unit 33 sends the improvement request prompt to the generation AI system, and the user terminal communication unit 30 sends the improvement prompt included in the AI ​​output information acquired in response to the improvement request prompt to the user terminal 12.

To provide highly reliable responses on the basis of discussion results by multiple pieces of generative AI.SOLUTION: A system according to an embodiment comprises a reception unit, multiple generation units, an evaluation unit, and a provision unit. The reception unit inputs a question. The multiple generation units individually generate responses to the question input by the reception unit. The evaluation unit compares and evaluates the responses generated by the multiple generation units. The provision unit provides the response selected by the evaluation unit.SELECTED DRAWING: Figure 1

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.

To enable an input character string to a system for outputting a response in the form of a character string to input of a character string to be the character string in which information subject to concealment is concealed.SOLUTION: The concealment apparatus is provided with concealment means for generating a second character string in which a partial character string detected as a concealment object in a first character string is replaced by another partial character string, and concealment prompt issuing means for inputting the second character string to a device for outputting a response to the second character string.SELECTED DRAWING: Figure 2

Provided is an information processing system and the like that can generate a sentence tailored to a job seeker. 【Solution means】According to one aspect of the present invention, there is provided an information processing system including at least one processor configured to execute the following steps by reading a program. In a reception step, first job seeker information including information regarding the attributes of a job seeker is received. In a question information extraction step, question information corresponding to the first job seeker information is extracted from reference information. The question information includes questions for the job seeker and information regarding answer examples corresponding to the questions. The reference information includes a plurality of question information candidates that are candidates for question information generated in advance based on the accumulated job content. In an acquisition step, an answer from the job seeker to the question information is acquired. In a job content generation step, a sentence regarding the job content of the job seeker is generated based on second job seeker information. The second job seeker information includes the first job seeker information and the answer acquired in the acquisition step. An information processing system is provided.

To make an electronic device take an appropriate action in response to an action of a user.SOLUTION: An action control system disclosed herein comprises an input unit for receiving user input including information on date of birth and an area of residence of a particular infant, a processing unit for performing specific processing using a sentence generation model for generating a sentence according to an input sentence, and an output unit configured to control an action of an electronic device to output a result of the specific processing, where the specific processing comprises suggesting meal recipes for the infant. The processing unit determines whether a predetermined trigger condition is met or not and, when affirmative, suggests meal recipes for the infant using an output of the sentence generation model that uses information obtained from the user input as the input sentence.SELECTED DRAWING: Figure 2