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

1654results about How to "Improve trust" patented technology

Power distribution network fault processing equipment

The invention relates to power distribution network fault processing equipment applied to the technical field of power distribution, and aims to improve the fault prediction, diagnosis and processing capabilities of a power system. The equipment comprises a pre-training module, a neural network architecture module, a data acquisition layer, an edge calculation layer, a core processing layer, a context learning module, a reasoning processing module, an output and interaction layer and a continuous learning and improvement layer, and is characterized in that a large-scale pre-trained Transform model is utilized, and professional knowledge of a power system is combined; according to the method, deep understanding and analysis of a complex power grid state are realized, through multi-source data fusion, edge calculation and central cooperative processing, the equipment can monitor the power grid state in real time, accurately predict potential faults and provide intelligent diagnosis and repair suggestions, and model pre-training and optimization are performed by adopting self-supervised learning and federated learning technologies; using reinforcement learning to optimize a fault response strategy; the interpretability of the model is realized, and the decision transparency is improved.
Owner:STATE GRID SHANDONG ELECTRIC POWER CO PINGYI COUNTY POWER SUPPLY CO

Information security risk assessment system based on block chain

The invention relates to the technical field of information risk assessment, in particular to a blockchain-based information security risk assessment system, which comprises the following modules: a data acquisition module for acquiring basic operation data from an information storage system; the heterogeneous data fusion module is used for integrating multi-dimensional data by adopting a data fusion algorithm; the block chain-driven model training and updating module is used for carrying out training and real-time updating on a risk assessment model by utilizing distributed computing resources of a block chain network; the graph theory-based risk propagation analysis module is used for modeling each component of the information storage system and the mutual relation thereof by adopting a graph theory method; a multi-dimensional risk assessment and quantification module; and the intelligent risk response and strategy adjustment module automatically formulates and adjusts a defense strategy according to a multi-dimensional risk assessment result. According to the method, the key data storage position and the potential weakness of the access control point in the information storage system are effectively identified, and a basis is provided for accurate safety protection.
Owner:广州易至信息科技有限公司

Power data security policy large model question-answering system and method based on relation pooling

The invention belongs to the technical field of electric power data security management and intelligent question answering, and particularly relates to an electric power data security policy large model question answering system and method based on relation pooling. The system comprises a power data security policy knowledge base, a language model, a question processing module, an answer generation module and a user output module. Data of the electric power data security policy knowledge base comes from an electric power data security policy file; the language model converts a natural language problem into a structured query for knowledge base retrieval; the question processing module retrieves policy terms related to the natural language question to serve as retrieval results; the answer generation module generates a final answer according to the natural language question and a retrieval result of the knowledge base; by introducing the intelligent question-answering system combining the large language model and the knowledge base, the problems of low efficiency, inaccurate interpretation, incapability of dynamically updating and the like in the existing power data security policy query and management are solved.
Owner:ECONOMIC TECH RES INST OF STATE GRID HENAN ELECTRIC POWER +1

Knowledge retrieval-based vertical type government affair large model service method and system

The invention provides a vertical type government affair large model service method and system based on knowledge retrieval, and relates to the technical field of large models, and the method comprises the steps: carrying out word segmentation and semantic understanding on a natural language query through a natural language processing model, extracting a query intention, and determining a vertical field to which the natural language query belongs according to the query intention; performing deep matching on query semantic representation corresponding to a query intention and the knowledge nodes by adopting an attention mechanism, and obtaining top-K knowledge nodes most relevant to the query semantic representation in a jumping knowledge graph reasoning mode; starting from each most relevant knowledge node, constructing a credibility propagation network in combination with the vertical knowledge graph, and iteratively calculating the credibility of each most relevant knowledge node in the propagation process of the credibility propagation network by setting the initial credibility of the most relevant knowledge nodes; and summarizing the most relevant knowledge nodes of which the credibility scores exceed a preset confidence threshold as target reply content.
Owner:XIAODUO INTELLIGENT TECH (BEIJING) CO LTD

Method for AI model maternal and infant assistant from question answering to accurate recommendation

The invention discloses a method for an AI model maternal and infant assistant from question answering to accurate recommendation, belongs to the technical field of artificial intelligence, and comprises the steps of user demand input and analysis, user portrait construction and dynamic updating, commodity recommendation and optimization, feedback optimization and strategy adjustment. According to the method and the system, the change of user demands and interests can be flexibly coped with, the recommendation accuracy and the user satisfaction degree can be improved, accurate understanding and processing of complex demands are ensured, the real-time performance and accuracy of user portraits are ensured, the change of the user demands and interests can be flexibly coped with, and more accurate and personalized recommendation is realized. The recommendation accuracy and the user satisfaction are improved, and the user can understand what a certain commodity is recommended, so that the trust of the user to the recommendation system is enhanced.
Owner:SHANGHAI TONGQU INFORMATION TECH CO LTD

Forest carbon sink remote sensing monitoring method and system

The invention relates to the technical field of forest carbon sequestration, in particular to a forest carbon sequestration remote sensing monitoring method and system, and aims to solve the problems that in the prior art, a carbon sequestration prediction result can be obtained by inputting a target area image into a preset carbon sequestration model, a more comprehensive carbon reserve prediction model cannot be constructed in combination with a vegetation index, and the carbon sequestration prediction result cannot be obtained by using the preset model. The problem that the prediction result is inaccurate due to the fact that the features of specific tasks cannot be effectively handled is solved. According to the invention, ground survey data and vegetation indexes are combined through the prediction model construction module to construct a comprehensive carbon reserve prediction model, and the carbon reserve prediction model is obtained through machine training learning and can effectively cope with the characteristics of a specific task, so that the prediction accuracy and flexibility are improved; and a high-resolution carbon reserve distribution map is generated through an efficient machine learning algorithm, scientific decision and management are supported, and an important tool is provided for carbon reserve research.
Owner:SHAANXI ARROW BIOTECHNOLOGY CO LTD

Breeding product tracing method and system based on block chain

The invention relates to the technical field of supply chain management, in particular to a block chain-based culture product tracing method and system, and the method comprises the following steps: collecting the type, producing area and growth cycle data of culture products, distributing an identifier for each data item, coding the data and the associated identifiers in an upload format, and storing the data and the associated identifiers in a database; and uploading the data to a block chain network through an encryption channel, and generating a coded data record. According to the method, the timestamps and the data records are bound, each record is processed by using the hash function, and the security of each supply chain node is verified, so that not only is the integrity of data processing improved, but also an effective verification means is provided for consumers, and the security of the consumers is improved by decrypting and verifying the encrypted data. The security and privacy protection of data in storage and transmission are ensured, the production and circulation process of products is tracked through a block chain query function, the food security is improved, the supervision compliance is enhanced, and a powerful tool is provided for solving fraud and pollution problems in a supply chain.
Owner:四川德康农牧食品集团股份有限公司 +1

Financial anti-fraud business database construction method and system

The invention relates to the technical field of financial information, in particular to a method and system for constructing a financial anti-fraud business database, and the method comprises the following steps: analyzing transaction time, transaction amount and participant identity information based on transaction business record information, constructing a financial transaction relation graph, and generating financial transaction network information. According to the invention, the financial transaction record is analyzed, the financial transaction network information is constructed, the depth of data processing is increased, the accuracy of data analysis is improved through network construction, and the statistical volatility of the transaction activity is analyzed, so that abnormal fluctuation nodes are accurately identified, and risks and fraudulent behaviors are identified. According to the method, capital and credit state changes of nodes are monitored and simulated in real time, market changes are responded in real time, measures are taken before risks occur, economic losses caused by fraud are reduced, transaction data are classified and subjected to risk assessment, the risk management capacity and market adaptability of financial institutions are improved, and the risk management efficiency is improved. And the credibility of customers and the competitiveness of the market are enhanced.
Owner:SICHUAN FENLING INFORMATION TECHNOLOGY CO LTD

Organic fertilizer quality safety traceability management method based on multi-source data

The invention relates to the technical field of quality traceability management, in particular to an organic fertilizer quality safety traceability management method based on multi-source data. The method comprises the following steps: collecting organic fertilizer source data in real time from links of organic fertilizer production, circulation, storage and use, performing standardization processing, and performing production batch synchronous set processing and traceability association connection file establishment to generate an organic fertilizer multi-source data traceability association connection file; and carrying out production batch tracing extraction processing on the organic fertilizer multi-source data traceability association connection file, carrying out organic fertilizer quality index evaluation analysis and quality index error limitation analysis, carrying out organic fertilizer quality safety abnormity traceability processing and abnormity decision support processing, and generating an organic fertilizer quality safety abnormity problem decision support report. Therefore, the corresponding organic fertilizer quality safety abnormity traceability problem management work is executed. The scientificity and accuracy of organic fertilizer quality safety management can be improved.
Owner:INST OF AGRI RESOURCES & ENVIRONMENT SICHUAN ACAD OF AGRI SCI

Medical image lesion detection system

The invention relates to the technical field, in particular to a medical image lesion detection system which comprises a data processing module, a quality control module, a resolution reconstruction module, a data enhancement module, a dynamic learning module, a real-time feedback module, a model interpretation enhancement module and a comprehensive diagnosis module. According to the medical image lesion detection system and method, the image resolution is improved through the quality optimization image, lesion features in the medical image are simulated in combination with the conditional generative adversarial network, the efficiency and accuracy of the medical image lesion detection system are remarkably improved, and the improvement of the image resolution ensures high quality and authenticity of the image; accurate basic data are provided for lesion detection, the application of the conditional generative adversarial network expands a data set, the recognition ability of the model to rare lesions is enhanced, the dynamic learning module allows the model to be self-optimized according to the feedback of a doctor, the adaptability and the diagnosis accuracy are improved, and the diagnosis accuracy is improved. And due to the intervention of the real-time feedback module, an operator can obtain quality feedback in the diagnosis process in real time.
Owner:SHENZHEN LONGGANG DISTRICT THIRD PEOPLES HOSPITAL

Knowledge reinforcement learning method and system based on multiple agents

The invention relates to the technical field of AI computing, in particular to a knowledge reinforcement learning method and system based on multiple agents. Modifying parameters of the large language model by using a supervised fine-tuning training method for the pre-trained large language model; constructing a knowledge base of a large language model, and vectorizing, storing and retrieving texts in various file formats; a multi-agent workflow optimization information processing and decision-making process is developed, a real-time problem is decomposed, a logic chain for solving the problem is constructed, and internet texts are obtained, filtered and summarized. Compared with the prior art, the method has the advantages that the knowledge quantity of the pre-trained large language model in the specific field is increased, the knowledge base is high in flexibility, the obtained text is high in real-time performance, certain interpretability is achieved and the like, and then the ability of the large language model to solve problems in the specific field is improved.
Owner:TONGJI UNIV

Patient nursing strategy optimization system for nursing of liver, gall and pancreas department

The invention discloses a patient nursing strategy optimization system for nursing in the department of hepatobiliary and pancreatic, and relates to the technical field of nursing strategy optimization. The nursing strategy optimization platform is in communication connection with a patient information management module, a knowledge base module, a nursing evaluation module, a nursing strategy plan making module, a nursing implementation module, a communication and cooperation module and a nursing effect evaluation module. According to the patient nursing strategy optimization system for nursing in the department of hepatobiliary and pancreatic, data in multiple aspects of physiology, psychology, society and the like of a patient are comprehensively collected and analyzed through the integrated nursing evaluation module, and key indexes such as vital signs, pain degree, nutritional status, sleep quality and the like are monitored and evaluated in real time; in addition, a personalized nursing plan provided by the system is combined with specific requirements and illness state changes of the patient, so that the nursing service better fits the actual condition of the patient.
Owner:JILIN UNIV FIRST HOSPITAL

Fine-grained large model illusion processing method and system based on zero resource framework

The invention belongs to the technical field of natural language processing. According to the zero resource framework-based fine-grained large model illusion processing method and system, multi-dimensional anomaly detection is carried out on a preprocessed text through a large language model, and a multi-dimensional anomaly detection result is obtained; performing anomaly correction priority ranking according to a multi-dimensional anomaly detection result; dynamically adjusting a context window range according to a syntactic analysis result and the generated syntactic dependency tree; performing priority correction on high-risk vocabularies and sentences according to an abnormal correction priority ranking result in combination with the adjusted context window range; and evaluating the corrected content, and obtaining a corrected final text when a termination condition is met. According to the method, the excessive confidence, subtle semantics and grammar deviation illusion detection of the detection content is realized, and the illusion detection processing capability of a large language model, especially the detection processing capability of a fine-grained illusion problem, is improved.
Owner:SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN +3

Character recognition and automatic auditing method and system

The invention discloses a character recognition and automatic auditing method and system, and the method comprises the steps: obtaining all to-be-audited document data including semi-structured and non-structured document data, guaranteeing the comprehensiveness of an auditing process, accurately recognizing the document content through an OCR technology, converting the document content into operable structured data, and carrying out the automatic auditing of the to-be-audited document data. Key information in a document is selected through two modes of rule extraction and model extraction, the efficiency and accuracy of information processing are improved, the information is compared with pre-established target structured text data, compliance check is automatically completed, the compliance of an auditing result is ensured, a confidence coefficient threshold value is updated in real time according to the complexity of the document, and the accuracy of information processing is improved. The method is suitable for document data with different complexities, the automatic auditing process remarkably improves the auditing efficiency, when a large amount of document data is processed, a large amount of time and manpower resources can be saved, the auditing result and the corresponding confidence rate can be output, a user can see the specific result of document analysis, and the auditing reliability and the credibility of the user are improved.
Owner:BEIJING ZHIZHENYUN INTELLIGENT TECH CO LTD

Block chain intelligent decision-making system based on decision mechanism

The invention relates to the technical field of block chains, and discloses a block chain intelligent decision-making system based on a decision mechanism, and the system comprises a distributed intelligent contract execution module which is used for executing an intelligent contract in parallel in a distributed network; the decentralized data storage and verification module is used for providing a safe data storage and verification mechanism; the intelligent contract automatic auditing module is connected with the decentralized data storage and verification module and is used for monitoring and auditing the execution process of the intelligent contract in real time; the decision optimization module based on AI is used for optimizing the adaptive ability and adaptability of a decision algorithm by analyzing big data and extracting key information; and a block chain identity verification and security access control module. The intelligent contracts are executed on multiple nodes in parallel, the processing capacity and expandability of the system are remarkably improved, optimal utilization of resources and efficient operation of the system are ensured through intelligent load prediction and scheduling, performance optimization and load balancing, and single-point faults are avoided.
Owner:CHINA SCI & TECH WESTERN RES INST OF COMPUTING TECH

Machine learning-based shear capacity analysis method for reinforced concrete beam with stirrups

The invention discloses a shear capacity analysis method for a reinforced concrete beam with stirrups based on machine learning, and the method comprises the steps: constructing a training set and a test set based on a shear capacity database of the beam with stirrups; establishing an interpretable prediction model by utilizing machine learning, setting hyper-parameters for the interpretable prediction model, and performing training; obtaining a shear bearing capacity prediction value of the samples in the test set by using the trained prediction model; and quantifying the contribution of each key anti-shearing characteristic to the anti-shearing bearing capacity predicted value, and analyzing and judging the reasonability of the anti-shearing bearing capacity predicted value output by the prediction model according to the anti-shearing theory. According to the method, the problems of high prediction difficulty, high discreteness, lack of reliable physical models, large calculation amount of high-precision numerical simulation and the like in machine learning are solved for the first time; the prediction model can accurately reflect the complex nonlinear relation between the shear bearing capacity and the influence factors, and meanwhile, the model reasonability is verified and improved in combination with a prediction result and priori knowledge, so that the man-machine interaction trust in practical application is improved.
Owner:INNOVATION CENTER OF YANGTZE RIVER DELTA ZHEJIANG UNIVERSITY

Road disease intelligent identification method and system based on image identification technology

The invention discloses a road disease intelligent identification method and system based on an image identification technology, and the method comprises the steps: capturing a road image, carrying out the preprocessing of the road image, extracting edge features, texture features and linear features from the preprocessed road image, carrying out the classification training of the extracted edge features, texture features and linear features, and obtaining a road disease identification result. The method comprises the following steps: identifying different types of road diseases in a road image, positioning a road disease area, generating three-dimensional point cloud data from the road image at different visual angles of the positioned road disease area, reconstructing a road surface image from the three-dimensional point cloud data, and evaluating the road disease severity of the reconstructed road surface image. And predicting the severity of the road disease, obtaining a road surface image prediction disease identification result, generating the road surface image prediction disease identification result into a detection report, and storing the detection report. A large amount of road image data can be automatically processed by using an image recognition technology, and a disease area can be quickly recognized.
Owner:COMM DESIGN INST CO LTD OF JIANGXI PROV

System and method for improving driving credibility based on multi-modal intelligent interaction

The invention belongs to the technical field of automatic driving, and particularly relates to a system and method for improving driving credibility based on multi-modal intelligent interaction, and the method comprises the steps: collecting behavior data, physiological signals and eye movement feature data of a driver under driving in various man-machine interaction combination mode scenes, and carrying out the preprocessing and feature extraction; inputting the initial data set into a pre-training model for fine tuning training to obtain a large model for credibility prediction and intelligent interaction recommendation; updating the large model in real time based on a feedback mechanism of a memory bank, and generating a credibility prediction result and a recommendation interaction mode; and judging whether the result meets the requirement of improving the credibility or not, and outputting an optimal man-machine interaction mode to the man-machine interaction module. The problems that in the prior art, a man-machine interaction system is low in intelligent level, and it is difficult to flexibly adjust the interaction mode according to the driver trust degree change are solved.
Owner:HANGZHOU DIANZI UNIV

Offshore wind power operation risk analysis system based on deep learning

The invention relates to the technical field of offshore wind power operation risk analysis, and discloses an offshore wind power operation risk analysis system based on deep learning, and the system comprises a data collection and preprocessing module which is used for collecting wind power equipment operation state data and environment data of multiple types of sensors, and carrying out the cleaning and preprocessing of the data; the multi-modal data fusion and feature extraction module is used for extracting and fusing multi-modal features from different data sources; and the real-time risk prediction and intelligent decision module is used for analyzing the operation state of the wind power equipment in real time based on a deep learning model, and performing prediction and alarm when a fault trend is detected. By introducing a self-attention mechanism and a Transform architecture, deep fusion analysis is performed on multi-modal data from wind power equipment, and information of different data sources can be weighted and integrated in a unified feature space, so that the system can adaptively focus on important features, and the analysis precision and fault detection capability of the multi-modal data are remarkably improved.
Owner:BEIJING ZHIXIN HENGRUI TECH CO LTD

Financial information recommendation method and system based on multi-channel distribution

The invention belongs to the technical field of information recommendation, and discloses a financial information recommendation method and system based on multi-channel distribution, and the method comprises the steps: collecting behavior data of multiple channels of a user, carrying out the cross-platform data integration, and forming a complete user behavior data set; constructing a multi-dimensional user portrait, establishing a financial information database, and marking a keyword tag for each piece of financial information; according to the keyword matching degree of the user portrait and the information content, using content recommendation and financial information conforming to user preferences, and based on historical behavior data of the user and behavior habits of similar users, using collaborative filtering to recommend financial information in which the user is interested to obtain a financial information recommendation list; according to the use habits of the user at different terminals, cross-platform information distribution is performed on the financial information recommendation list through multiple channels, so that the accurate recommendation capability of financial information is improved, and the user experience is improved.
Owner:江西省通信产业服务有限公司

Medical AI question and answer method based on retrieval enhancement

The invention provides a medical AI question and answer method based on retrieval enhancement, which comprises the following steps: acquiring a medical professional knowledge base, and constructing an entity recognition model and a medical knowledge graph; the method comprises the following steps: splitting a medical professional knowledge base, and creating a vector index and a full-text retrieval reverse index; intention classification is carried out, and initial processing is completed; performing multi-path mixed retrieval on the medical professional knowledge base to obtain a user question related text block; a filtering rule is preset, and the user question related text blocks are filtered; answering the user question according to a preset second prompt word, and answering the user question according to a preset third prompt word when the user question exceeds the range of the medical professional knowledge base or the multi-path mixed retrieval has no result. According to the method, related context information can be accurately searched, reliable reference information is provided for a generative large model to answer professional questions, the interactive experience of a medical question answering system is improved, and the accuracy and specialty of answer generation of the system are remarkably improved.
Owner:SICHUAN MEIKANG PHARM SOFTWARE RES & DEV

Intelligent dialogue method and system

The invention provides an intelligent dialogue method and system, and belongs to the technical field of intelligence, the intelligent dialogue method and system comprise an intelligent dialogue system method, the intelligent dialogue system method comprises an intelligent dialogue module, and the intelligent dialogue system is used for processing natural language interaction between a player and an AI assistant (space-time secrete). Comprising functional modules of semantic comprehension, sentiment analysis, context memory and the like; due to the addition of the emotion interaction unit, the system can identify the emotion of the player, such as happiness, disappointment or anger, and dynamically adjust a reply strategy through an emotion mapping strategy, such as giving comfort or encouragement at proper time, so that the reality sense and interestingness of interaction are greatly increased, the player feels understood and concerned, and the user experience is improved. Therefore, the viscosity and the satisfaction degree of the game are improved.
Owner:王光辉

Text semantic conflict detection method and system for constructing context association based on large model

The invention relates to a text semantic conflict detection method for constructing context association based on a large model. The method comprises the following steps: S1, segmenting an original text by using a segmentation function; s2, performing triple information extraction on each segmented text by using a large model to generate a data set of an entity corresponding relationship; s3, extracting data groups of all entity pairs and relationships, and performing confidence evaluation; s4, aggregating all triads, constructing a affair graph, and pointing out a contradictory relationship with relatively low confidence in the affair graph; and S5, for the found contradictory relationship, performing semantic conflict repair in the text in combination with the large model. According to the method, the accuracy of information generation of the large language model is remarkably improved in a context association mode.
Owner:SHANDONG ENERGY GRP CO LTD +1

Flower selling management system and method based on block chain technology

The invention discloses a fresh flower selling management system and method based on a block chain technology, and relates to the technical field of fresh flower management. A data acquisition module acquires real-time data of a fresh flower planting link and a logistics transportation link, transmits the real-time data to a block chain storage module, and binds an identifier of a fresh flower; the block chain storage module is used for storing the fresh flower information and storing the data of the full life cycle of the fresh flowers in a distributed account book; the user access module is used for checking a display legend of the fresh flower and related information of the fresh flower at a user side, and the intelligent contract module is used for generating order information and carrying out payment settlement and automatic account division; the inspection module is used for inspecting flower quality and flower information; and the abnormity monitoring and feedback module is used for timely recording and sending notifications when abnormity is found in the planting, transportation or sales process, and quickly positioning problem nodes. According to the method, the transparency of the whole flow of fresh flower planting and transportation is improved, the data security and credibility are ensured, and rapid traceability is realized.
Owner:HUAWA NETWORK TECH CO LTD

Milk traceability method based on NFC

ActiveCN119494668AEnsure data transparencyImprove traceability efficiencyCo-operative working arrangementsCommerceOperating systemMilk production
The invention discloses a milk traceability method based on NFC, relates to the technical field of milk traceability, and comprises the following steps: combining an NFC tag with a block chain, performing encryption transmission on data of each link, storing through a distributed account book technology of the block chain, ensuring that the data is transparent and cannot be tampered, and based on the NFC tag, obtaining a milk traceability result; the monitoring data of each stage of milk production, processing and transportation is updated to the block chain, the traceability efficiency is significantly improved, manual participation is reduced, a deep learning model is introduced, prediction and identification of potential quality problems of milk are realized, enterprises are helped to take corrective measures in advance, loss is reduced, a risk early warning mechanism is provided for a supervision mechanism, and the risk of the supervision mechanism is reduced. The overall safety of the supply chain is improved, the consumer can check the complete traceability information of the product by using the NFC scanning device through the NFC label and the block chain technology, the sense of trust of the consumer to the product is greatly improved, and the credibility of the brand can be enhanced.
Owner:BEIJING PURE HI-TECH AGRICULTURE & ANIMAL HUSBANDRY TECHNOLOGY CO LTD

Breast cancer HER2 immunohistochemical image automatic scoring method

The invention discloses a breast cancer HER2 immunohistochemical image automatic scoring method. The method comprises the following steps: firstly, reasoning an image block set by using a cell nucleus instance segmentation model and a tumor tissue semantic segmentation model to output a cell nucleus segmentation map and a tumor region segmentation map; extracting a tumor region contour in the tumor region segmentation map and calculating convex hull ratio and curvature features; performing classification through a Gaussian mixture model and a naive Bayes classifier to obtain an infiltrating cancer region and an in-situ cancer region; performing cell membrane segmentation on the cell nucleus segmentation map to obtain a cell membrane region, and classifying cell staining degrees to obtain tumor cells of different staining levels in the invasive cancer region; and finally, counting and proportion statistics are carried out, and HER2 scoring of the breast cancer immunohistochemical image is completed according to clinical guidelines. According to the method, personal errors are reduced, the consistency and reliability of results are ensured, the diagnosis time is greatly shortened, and instant support is provided for clinical decisions.
Owner:SOUTH CHINA UNIV OF TECH

Financial security transaction risk assessment system

InactiveCN119067779AImprove risk assessmentIn-depth understanding of market conditionsFinanceWeb data indexingFinancial securityPrivacy protection
The invention discloses a financial security transaction risk assessment system, which comprises a data acquisition module, a risk assessment module and a visual display module, and can provide comprehensive risk assessment including market risk, credit risk, operation risk and mobility risk, the risk assessment module adopts an advanced risk assessment model and a machine learning technology, and the risk assessment module adopts a visual display module. The accuracy and comprehensiveness of risk prediction are improved. And the visual display module helps the user to quickly understand the risk condition through a visual graphical interface. The system also has an early warning mechanism and investment portfolio optimization suggestions to assist users in effectively managing risks. In addition, the system pays attention to data security and privacy protection, and the security of sensitive data is ensured by adopting access control, data encryption and other measures. The system is suitable for individual investors, institution investors and risk management experts, and aims to improve the risk management capability of financial transactions.
Owner:NANJING HONGAIYI SOFTWARE TECHNOLOGY CO LTD

Tracing method and system based on drug consumable traceability code

The invention relates to the technical field of medicine information management, in particular to a traceability method and system based on a medicine consumable traceability code. The method comprises the following steps: acquiring medicine purchasing information data; generating a unique code for the number of medicine purchasing information so as to generate a medicine warehousing traceability code; performing drug information association on the drug purchase information data according to the drug warehousing traceability code to generate a drug warehousing associated traceability code; storing the medicine warehousing associated traceability code in an information base to generate a medicine warehousing traceability code information base; performing scanning access mode division on the medicine warehousing traceability code, and generating a medicine dispensing scanning request mode and a medicine returning scanning request mode; and performing drug splitting tracing on the drug warehousing tracing code in a drug dispensing scanning request mode to generate drug splitting tracing data. According to the invention, through full-process closed-loop management, data association enhancement, intelligent scheduling optimization and drug return tracing improvement, the efficiency and precision of the drug consumable traceability code tracing method are improved.
Owner:JIANGSU QIHANG SOFTWARE LTD CO

Intelligent bid evaluation method and system based on large model, and related product

The invention discloses an intelligent bid evaluation method and system based on a large model, and a related product, relates to the technical field of purchase bid evaluation systems, and solves the problems that an existing intelligent bid evaluation system is difficult to understand a complex logical relationship and semantic connotation and cannot provide a comprehensive and accurate scoring result. According to the technical scheme, the method comprises the steps that S1, bidding and tendering files are obtained; s2, performing disassembly processing based on the bidding and tendering file to obtain a plurality of bidding and tendering data pairs; s3, performing instruction construction on the bidding and tendering data pair based on a historical bidding and tendering database to obtain a prompt instruction of the bidding and tendering data pair; s4, processing the prompt instruction of the bidding and tendering data pair based on the large model after training and fine tuning to obtain the score of the bidding and tendering data pair, and accumulating the scores to obtain the score of the bidding file; through the method based on the large model, the scoring effect is effectively improved in the intelligent bid evaluation work, the efficiency is improved, manpower and material resources are saved, and meanwhile interference caused by human factors is avoided.
Owner:SICHUAN ENRISING INFORMATION TECH CO LTD

Energy industry intelligent algorithm optimization method based on federal learning

The invention discloses an energy industry intelligent algorithm optimization method based on federal learning. The method comprises the following steps: S1, collecting and preprocessing local energy data; s2, acquiring and preprocessing expert example data; s3, constructing a comprehensive data set by applying a multi-modal data fusion technology; s4, each participant performs local model training on the comprehensive data set by using a federal adaptive optimization algorithm to generate local model update; s5, the central server aggregates local model updating to generate a global model; s6, applying a soft actor-commentator algorithm in the global model, and combining an inverse reinforcement learning technology to optimize an energy distribution strategy; s7, creating a virtual simulation environment by using a digital twinning technology, and testing and optimizing the performance of the global model; and S8, providing a user-friendly interface and a natural language processing interface, and realizing personalized energy management suggestions. According to the method, federated learning, a soft actor-commentator algorithm and an inverse reinforcement learning technology are combined, and an energy distribution strategy is optimized.
Owner:SHENHUA HOLLYSYS INFORMATION TECH CO LTD