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

58 results about "Self evaluation" patented technology

Learning Self-Evaluation to Improve Selective Prediction in LLMs

Aspects of the disclosure are directed to methods, systems, and computer readable media for adaptation with self-evaluation to improve selective prediction in large language models (LLMs), generally referred to as ASPIRE. ASPIRE includes training LLMs on a portion of training data from a question answering task to learn self-evaluation, e.g., learn to distinguish whether a generated answer is correct or not. ASPIRE further includes a selection score that combines a likelihood of that generated answer is correct with a self-evaluation score for selective prediction. ASPIRE demonstrates improved selective prediction performance with less computational cost.
Owner:GOOGLE LLC

Rubric based self learning methods and systems in an artificial intelligence environment

Systems and methods for an artificial intelligence (AI) agent to perform self-learning, self-evaluation based on a rubric and then perform self-correction as needed is described. The methods generate a rubric. The rubric includes the AI agent's performance data and evaluations of the data and related feedback by a separate LLM and a human agent. Once a level of confidence is achieved that the AI agent is performing at a threshold confidence level of the human agent, or that the separate LLM is evaluating the AI agent's performance within a threshold confidence of the human agent's evaluation of the same, the rubric in which the AI agent's performance and evaluation data is inputted is determined to be complete for use in a self-evaluation. The AI agent may then use the rubric to self-evaluate and self-correct its performance without a need for human evaluation.
Owner:EMA UNLIMITED INC

Mental health assessment system and method based on big data

The invention discloses a psychological health assessment system and method based on big data, and relates to the technical field of physical and psychological health assessment, the system comprises a data acquisition module, a data processing module, a psychological mechanism analysis module, an ability quality modeling module, a multi-modal detection module and an assessment result generation module; the technical key points are as follows: in the implementation process of the technical scheme, a data acquisition module synchronously acquires static, dynamic, self-assessment and real-time emotion data of an assessed person in multiple scenes of campus, security and protection and the like; with a campus scene as an example, static information such as homework documents and social platform records of students is collected, dynamic behavior data such as classroom interaction and extracurricular activities are collected through an intelligent camera and voice equipment, and meanwhile, real-time emotion data are obtained by means of a face video stream collection technology to form a multi-dimensional data source; the heterogeneous data are processed into standardized coded data in a unified mode, and the limitation that traditional evaluation depends on a single questionnaire or simple observation is broken through.
Owner:HANGZHOU PIGEON NEST TECH CO LTD

Device for evaluating bladder filling degree before radiotherapy based on perceptual training

The invention discloses a device for evaluating bladder filling degree before radiotherapy based on perceptual training, and the device comprises a sensing module which is used for obtaining bladder data information; the bladder filling degree prediction module is used for predicting the bladder filling degree according to the bladder data information; the perception training module is used for generating a dynamic perception training plan according to the bladder filling degree predicted by the bladder filling degree prediction module, and the dynamic perception training plan is used for controlling the bladder filling degree of the patient to be kept on the preset bladder filling degree. The technical problem that an effective bladder filling degree self-evaluation and training means is lacked in the prior art is solved.
Owner:JIANGXI MATERNAL & CHILD HEALTH HOSPITAL +1

Green credit risk assessment system

The invention discloses a green credit risk assessment system, which comprises a data acquisition module, a risk assessment module and a result output module, and is characterized in that the data acquisition module is used for collecting information of enterprise environment, enterprise finance and enterprise projects, and the risk assessment module is used for analyzing and assessing the collected data information; and the result output module is used for outputting an evaluation result to a financial institution and an enterprise, and the financial enterprise performs loan approval according to the evaluation result and determines loan pricing and post-loan management. The system can provide an effective green credit risk assessment tool for a financial institution, help the financial institution better manage the risk and promote the development of green finance, and meanwhile, the system can also provide a self-assessment tool for an enterprise to help the enterprise know the green credit risk condition of the enterprise, thereby improving the safety of the enterprise. And the environment management level and the sustainable development capability of an enterprise are improved.
Owner:HEFEI UNIV OF TECH

Iterative text refining method, system and equipment based on fidelity and medium

The invention discloses a fidelity-based iterative text refining method, system and equipment and a medium, belongs to the technical field of natural language processing and artificial intelligence, and aims to solve the technical problem of how to overcome the limitation of unidirectional generation, realize self-evaluation and iterative optimization of a generated text, and improve the reliability of the text. According to the technical scheme, the method comprises the following steps: collecting a group of structured source information sets; a target text sequence is initialized, the length of the target text sequence is determined according to the estimated target text length, and the target text sequence is completely filled with special [MASK] lexical elements; entering an iterative refining cycle, and specifically, performing de-noising processing on a target text sequence by utilizing a pre-trained gradual de-noising language model to generate an intermediate version text; and evaluating fragments in the intermediate version text through a content fidelity evaluation module.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

Self-assessment neurological health care system

A system has a digital health avatar can substitute to a neurologist, nurse practitioner, physical assistant or research coordinator (in the context of a clinical trial) to run efficiently a routine neurological examination and document the report. This avatar supports the neurologist in his / her work, and will not replace the neurologist who still need to use his / her expertise to do the final diagnostic and manage the patient disease.
Owner:GEORGE WASHINGTON UNIVERSITY +1

Laser simulation shooting training system and method

The invention relates to the technical field of laser simulation shooting training, and particularly discloses a laser simulation shooting training system and method, and the system comprises a laser targeting gun which is used for simulating shooting to emit a laser beam; the shooting data acquisition module is used for acquiring shooting data of a shooter in real time; the laser shooting gun is used for simulating shooting to emit laser beams, the laser receiving target collects the positions, falling on the receiving target, of the laser beams, the data analysis module analyzes the collected data, scores corresponding to various evaluation indexes in the shooting process of the shooter are generated, and the comprehensive score of the shooter is generated. According to the laser simulation training method, the aim of accurately feeding back various evaluation indexes in the laser simulation training process of the shooter can be achieved, the shooter can conveniently and clearly find out the defects of the shooter and carry out targeted training, and the generated comprehensive score is convenient for the shooter to carry out self-evaluation on the shooting ability of the shooter.
Owner:ANHUI ZHONGAN ICT TECH CO LTD

Data-adaptive equipment production process defect identification method and system

The invention relates to the technical field of industrial equipment monitoring and defect diagnosis, and particularly discloses a data self-adaptive equipment production process defect identification method and system. By constructing a multi-dimensional delay dynamic reference and based on a joint decision of a delay gradient and a fluctuation entropy, intelligent classification and fast routing of sudden faults, environmental disturbance and composite hidden dangers are realized. According to the system, a three-layer nested diagnosis mechanism of abnormal dimension screening, causal chain tracing and defect mode matching is adopted, a root cause is accurately positioned, and a three-order adaptive response closed loop of instantaneous suppression, parameter compensation and model correction is driven so as to minimize production interruption. Meanwhile, the system periodically calculates the health index of the production line and realizes self-evaluation and collaborative optimization of key parameters, so that a monitoring model can continuously evolve along with the change of the equipment state and the environment, and finally, integration from real-time perception and intelligent diagnosis to adaptive optimization is formed, and the defect identification accuracy, the system stability and the overall operation and maintenance efficiency are remarkably improved.
Owner:ZHEJIANG EVERGREEN INFORMATION TECH CO LTD +2

Information technology personalized learning system based on artificial intelligence

PendingCN119129777AStimulate interest in learningReduce ineffective study timeData processing applicationsMachine learningPersonalized learningDynamic learning
The invention relates to an artificial intelligence-based information technology personalized learning system, which can customize a personalized learning path for each student by comprehensively collecting and analyzing learning behaviors, history and interest data of the student and utilizing an advanced machine learning algorithm. The core functions of the system comprise intelligent learning resource recommendation, dynamic learning content difficulty adjustment and providing of an ai teacher assistant and an intelligent question answering system so as to realize real-time tutoring and feedback. In addition, the system also provides an autonomous learning tool to support students to make learning plans, track the progress and perform self-evaluation. The invention aims to improve the learning efficiency and motivation of students in information technology subjects, promote the cultivation of deep learning and autonomous learning ability, and optimize the distribution and use of educational resources. The system not only adapts to individual requirements of students, but also can be expanded and applied to other subjects.
Owner:王小华

Intelligent dialogue method and system with self-evaluation and error correction capabilities

The invention discloses an intelligent dialogue method and system with self-evaluation and error correction capabilities, and relates to the technical field of artificial intelligence. Comprising the following steps of: 1.1, detecting a question input by a user, and analyzing a historical dialogue record by utilizing a context filling full-time agent; a semantic completion full-time agent is utilized to analyze the user input problem according to the filled context information, the problem is reasonably completed, and a processed user input problem is generated; 1.2, the processed user input question is transmitted into a large model, and a preliminary answer is generated for the user input question; 1.3, evaluating the generated preliminary answer in four aspects, namely, fact accuracy, logic rationality, semantic consistency and intention integrating degree; and step 1.4, outputting a decision. Step 2.1, defect detection is carried out, answered defect types are diagnosed, and corresponding error correction measures are taken according to different defect types; step 2.2, carrying out iterative optimization; and step 2.3, outputting a final qualified answer to the user side, and displaying the answer to the user for the user to check and use.
Owner:QINGDAO INSPUR HAIRUO ARTIFICIAL INTELLIGENCE CO LTD

Custom-made diet proposal system, custom-made diet proposal method, and program

To provide a custom-made diet proposal system, a method, and a program capable of performing custom-made eating management to improve own health while giving a feedback on the basis of the appearance of intestinal bacterial flora and self-evaluation.SOLUTION: A health management system 1 comprises: an eating information input unit 401 that successively inputs eating information; a health information input unit 402 that successively inputs health information; a bacterial flora information input unit 403 that successively inputs intestinal bacterial flora information; a health condition evaluation unit 407 that successively evaluates individual health conditions on the basis of the input information; an influence determination unit 408 that successively determines the influences given by individual eating histories to the health conditions on the basis of the eating information and a history of the health conditions; a menu determination unit 409 that successively determines menus continuously adopted for a prescribed period for observing the progress of maintenance improvement of the individual health conditions on the basis of a determination result; and a menu information output unit 410 that outputs menu information to a corresponding individual.SELECTED DRAWING: Figure 4
Owner:MIRAI MUGEN RECIPE CO LTD

Personalized learning monitoring system based on user behavior data

The invention relates to the technical field of personalized education, and discloses a personalized learning monitoring system based on user behavior data, and the system comprises a data collection module which is used for collecting the learning behavior data and physiological data of a target user, and integrating the interaction log data in a learning platform; the learning target formulating module is used for formulating a personalized learning target system containing short-term and long-term learning; the self-evaluation and feedback module is used for guiding the target user to perform self-evaluation regularly and assisting the target user in knowing the current learning progress; the emotion monitoring module identifies the current emotion fluctuation of the target user; and the dynamic task adjustment module is used for dynamically adjusting the difficulty, the content and the rhythm of the learning task based on the personalized learning target system, the current learning progress and the current emotion fluctuation, and generating a real-time adaptive learning task flow. The state change is automatically identified, the matching task is pushed, and the cognitive burden and the management cost are greatly reduced.
Owner:GUANGZHOU INTEREST ISLAND INFORMATION TECH CO LTD

Upper limb flattening protractor

The invention relates to the technical field of medical instruments, in particular to an upper limb flattening protractor which comprises a straight ruler for finger wall climbing training and a semicircular arc ruler for upper limb flattening training. The arc rulers and the rulers are staggered; the circular arc ruler and the straight ruler are marked with scales, and the center point of the circular arc ruler is rotatably matched with a pointer. According to the invention, the specific range of activity is displayed through the indication effect of the beacon, and the intuitive mode helps a patient to understand the body limit of the patient and gradually enlarge the range of activity of joints. By using clear scales and an easy-to-understand operation method, even non-professionals can independently complete basic self-evaluation and training.
Owner:ENSHI TUJIA & MIAO AUTONOMOUS PREFECTURE CENT HOSPITAL

System

To provide a system.SOLUTION: A system includes generative AI, means of connecting with employees' self-evaluations or calendars, means of organizing various evaluation points such as projects participated in, man-hours worked, and employees' selling points, and means of supporting the evaluation of the degree of achievement and overall performance against initially set goals.SELECTED DRAWING: Figure 1
Owner:SOFTBANK GROUP CORP

Cyclic channel self evaluation

A system and method are disclosed to test signal paths within sensor signal channels by providing an additional signal channel having testing means. The additional signal channel has a test signal generator, a test signal evaluator, and a signal path that is provided in parallel to existing signal paths within the sensor. Signal paths between each sensing element and each output are manipulated by input and output path couplers so that sense signals always reach the correct outputs but the intermediary signal path(s) may be changed according to a self-test protocol. In particular, the signal path(s) may be selected for cyclical testing. The signal path under test is subjected to test signals from the test signal generator which are then evaluated by the test signal evaluator for correctness, and faults signaled. The test signals may be selected to test each signal processing function in the signal path.
Owner:ALLEGRO MICROSYSTEMS LLC

System

An object of a system according to an embodiment is to provide a hint and a way of thinking for a user to derive an answer by himself / herself.SOLUTION: A system according to an embodiment includes a hint provider, a concept presenter, and a self-evaluation promoter. The hint providing unit provides a hint. The concept presenting unit presents a concept. The self-evaluation promotion unit promotes the self-evaluation.SELECTED DRAWING: Figure 1
Owner:SOFTBANK GROUP CORP

Model training data generation method and electronic equipment

The embodiment of the invention discloses a model training data generation method and electronic equipment. The method comprises the steps that multiple pieces of original input content are acquired; generating response content corresponding to the original input content by a first AI generation model; performing self-evaluation on the response content by the first AI generation model; if the evaluation score does not meet the condition, calling the first AI generation model to rewrite the original input content, and according to the rewritten input content, re-executing the generation and self-evaluation of the response content until the evaluation score of the response content corresponding to the rewritten input content meets the condition or the cycle index reaches a threshold value; and determining the input contents belonging to the positive samples and the negative samples according to the input contents of multiple versions obtained in the input content rewriting process and the evaluation scores of the corresponding response contents so as to serve as model training data of the second AI generation model. Through the embodiment of the invention, resources and cost required for constructing the training data can be saved.
Owner:HANGZHOU ALIBABA INT INTERNET IND CO LTD

An electronic contract approval management system

The present invention discloses an electronic contract approval management system, which specifically relates to the technical field of electronic contract management, including a process monitoring module, an editing tracking module, a risk sign detection module, a data analysis module, a joint identification module and a response decision module; dynamic behavior data such as approval path, processing time and transfer failure are obtained through process monitoring, and the editing tracking module collects multi-person editing behavior trajectory data; the risk sign detection module analyzes data combination patterns and outputs risk trigger signals; the data analysis module constructs a multidimensional data set, calculates the process anomaly index and content conflict index, and the joint identification module performs fuzzy reasoning based on the two indices to divide risk levels; the response decision module executes a graded intervention strategy according to the risk level; the present invention can identify process anomalies and guide repairs, accurately warn of multi-person editing conflicts, ensure content consistency, and has the ability to self-evaluate and optimize strategy response effects, thereby improving the intelligent level of contract approval.
Owner:SHAANXI DONGRUN TECH CO LTD

System

An object of a system according to an embodiment is to analyze a user's emotion or psychological state and propose personalized counseling or self-care activity.SOLUTION: A system includes a self-evaluation unit, an analysis unit, a proposal unit, and a tracking unit. The self-evaluation unit receives a self-evaluation of the user. The analysis unit analyzes the self-evaluation data received by the self-evaluation unit. The suggestion unit suggests a counseling session or a self-care activity based on the data analyzed by the analysis unit. The tracker tracks the user's progress and adjusts the plan as needed.SELECTED DRAWING: Figure 1
Owner:SOFTBANK GROUP CORP

Method and system for personal growth and accountability through cycle recognition and self-assessment

The invention provides a method and system for personal growth and accountability, addressing limitations of traditional therapy approaches. It teaches individuals to recognize cyclical patterns of victimhood, identify triggers, and analyze personal narratives. The method includes an Adult Circle Process for defining boundaries and acknowledging responsibility, and introduces “The Line,” a self-assessment tool for evaluating behaviors on a respect-disrespect scale. A Power Circle component encourages positive growth through recognizing positive triggers and developing empowering narratives. The invention can be implemented via digital platforms, workbooks, or guided sessions, offering concrete tools and measurable outcomes for users to foster accountability and shift focus from problem-solving to strength-building.
Owner:DIXON AMY

Psychological intervention platform focusing on improvement of emotional ability

The invention discloses a psychological intervention platform focusing on improving emotional ability. The psychological intervention platform is used for helping a user to identify, understand and process emotional problems. The platform guides a user to perform self-assessment and treatment through multiple modules, including baseline assessment, named emotion, recognized emotion, body feeling, interpersonal application, and summary feedback. The plurality of modules cooperate to help the user to improve the ability to recognize and process emotions in different aspects. Through the platform, the users can better understand their emotions and how these emotions affect their psychological states, body health and interpersonal relationships, the intervention compliance of the users with the condition disorder is improved, and the efficiency and effect of psychological intervention are optimized.
Owner:PEKING UNION MEDICAL COLLEGE HOSPITAL

A method, apparatus, device, and medium for depression relapse risk intervention

The application discloses a depression relapse risk intervention method, device, equipment and medium, and belongs to the medical technical field. The method comprises the following steps: integrating a gene risk score, a neural imaging brain region feature and clinical history data through a multi-modal fusion neural network to generate an individualized baseline risk score; dynamically correcting the baseline score based on self-evaluation data to enhance the real-time performance of risk assessment; analyzing the time sequence characteristics of physiological and behavioral data by using an LSTM time sequence model to output a short-term relapse early warning label; and combining real-time voice / text data emotion knowledge graph analysis and dynamic risk grading to trigger a hierarchical intervention strategy. The application solves the problems of single evaluation dimension and response lag of traditional methods through a multi-dimensional data fusion and dynamic calibration mechanism, realizes closed-loop management from risk warning to precise intervention on the premise of avoiding direct clinical diagnosis, and improves the comprehensiveness and timeliness of depression relapse prevention and control.
Owner:BEIJING CHINESE MEDICINE HOSPITAL AFFILIATED CAPITAL MEDICAL UNIV

Learning motivation detection method and device, electronic equipment and storage medium

The invention relates to the technical field of intelligent education, in particular to a learning incentive detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a log file of a learner, and carrying out the separation detection of the log file, and obtaining the participation information of the learner; if it is judged that the learner is out of learning according to the participation degree information, dialogue information is generated based on a preset item questionnaire, and the learner is inquired based on the dialogue information to obtain an incentive file of the learner; and generating a personalized intervention scheme for the learner based on the participation degree information and the motivation archive. Therefore, the motivation state of the learner can be recognized more accurately and timely in combination with automatic monitoring and active self-evaluation of the behavior of the learner, the learning process is quickly intervened and optimized, and the teaching efficiency is improved.
Owner:BEIJING SANSAN SMART EDUCATION TECHNOLOGY CO LTD

Information processing method and electronic equipment

The invention relates to an information processing method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring input information; the input information is input into the trained large model, output information corresponding to the input information is obtained, the output information comprises internal knowledge output and reasoning output, and the trained large model is obtained based on multiple meta-skill training; wherein the meta-skills include a first meta-skill for extracting internal knowledge, a second meta-skill for generating reasoning, and a third meta-skill for self-evaluation. In this way, according to the method, the trained large model can extract internal knowledge to serve as the support of reasoning, and the output result is continuously optimized based on self-evaluation, so that'illusion 'in the iterative self-learning process can be reduced, and the accuracy, logicality and reliability of output can be improved.
Owner:BEIJING YOUZHUJU NETWORK TECH CO LTD

Adaptive audio and audiovisual recursive self-feedback for speech therapy

Systems and methods are provided for generating, managing, adapting, and delivering speech therapy to a user via a mobile device in an at-home or out-of-clinic setting. Users may be persons experiencing aphasia or other speech conditions. For example, prompts may be communicated to a user, and their spoken responses recorded and analyzed. Based on analysis of the responses, these systems and methods may determine a mode of response including but not limited to playback of the user's spoken response to allow the user to recursively self-assess and / or self-correct. User performance and improvement trends may be assessed, and utilized to adapt future therapy sessions.
Owner:UNIV OF SOUTH FLORIDA

A small sample segmentation method and device based on fine-tuning and self-evaluation

The application belongs to the technical field of deep learning and computer vision, and discloses a small sample segmentation method and device based on fine tuning and self-evaluation. The method firstly initializes system parameters, then predicts pseudo labels for query images to obtain query prototypes, updates the query pseudo labels after combining with support prototypes, fine tunes the system parameters by using the pseudo labels, then repeats the process to realize multiple fine tuning of the system, finally determines the best fine tuning round by using the designed self-evaluation method, and obtains the final segmentation result. The application alleviates the problem that the existing system uses categories or support images in biased training, and improves the segmentation accuracy. The designed self-evaluation method can evaluate the optimal fine tuning round, and prevent the error accumulation in the fine tuning process from causing the problem of low accuracy. Compared with the existing method, the fine tuning process only needs about 1% of the time cost and computing power cost, and can more quickly and efficiently adapt to new categories and obtain high-quality segmentation results.
Owner:NORTHEASTERN UNIV CHINA

Method of certifying a CBD product

In accordance with one embodiment, a method can be implemented that includes enlisting via a computer network a plurality of participants to report one or more effects of their respective usage of a substance; confirming that a prospective participant is located in a state where use of the substance is legal; receiving from each of the one or more participants via the computer network one or more self-assessment reports of any physical, emotional, or mental responses or any combination thereof to the substance; and processing the one or more self-assessment reports with a computer processor to determine if the substance has an effect on a particular symptom or condition.
Owner:ENIGAMI SYST

System

A system is provided.SOLUTION: The system includes a means for collecting data such as an operation history of a learner, a test result, and self-evaluation, a means for analyzing the collected data and identifying a thinking pattern and a cognitive style of the learner, a means for automatically generating individualized educational contents based on the analysis result, a means for delivering the automatically generated educational contents to the learner, and a means for dynamically adjusting an educational program according to the progress of the learner.SELECTED DRAWING: Figure 1
Owner:SOFTBANK GROUP CORP

Organization member evaluation device, organization member evaluation method, and program

We provide a device that provides an integrated system that includes quantitative multiple-choice evaluation by category, combined self- and peer-evaluation, visualization of score trends, and action list presentation. [Solution] The organization comprises a display control means for displaying on a display unit, for each member of a plurality of categories, a screen for each member including one or more questions for each category and multiple choice answers to the questions; an input accepting means for inputting multiple choice answers by each member to each question; and an evaluation means for evaluating each member based on one or more questions for each of the plurality of categories and one or more answers corresponding to each of the one or more questions, wherein the categories include at least categories related to each member's skills, categories related to each member's condition, and categories related to engagement, and the display control means displays on the display unit a screen for each member including the results of the evaluation.
Owner:SKY STONE CO LTD