Patents
Literature
18 results about "Case analysis" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Case analysis is one of the most general and applicable methods of analytical thinking, depending only on the division of a problem, decision or situation into a sufficient number of separate cases. Analysing each such case individually may be enough to resolve the initial question. The principle of case analysis is invoked in the celebrated remark of Sherlock Holmes, to the effect that when one has eliminated the impossible, what remains must be true, however unlikely it seems. The logical roots of the Holmes remark speak to the principle of excluded middle. That indicates the importance to case analysis of logical disjunction: stringing together propositions with the logical connective "or". Medical diagnosis can indeed follow the Holmes pattern, with a patient's symptom possibly caused by a number of conditions: the patient suffers from A or B or ... or illness I; see differential diagnosis. Deductive logic is applied to reducing the number of cases; see case-based reasoning. A canonical statement of case analysis in the sentential calculus is this: "If a statement P implies a statement Q, and a statement R also implies Q, and either P or R is true, then Q must be true."
Atmospheric pollution case system, case analysis method and medium
The invention discloses an atmospheric pollution case system, a case analysis method and a medium, and the system comprises a basic information layer which is used for storing the whole-process feature data and treatment measure data of a pollution event; the logic analysis layer is used for carrying out quality control on the data, carrying out source analysis and cause analysis on the whole-process feature data of the pollution event after the quality control, and carrying out effect evaluation on the treatment measures after the quality control; and the comprehensive decision-making layer is used for comparing historical cases according to the retrieval conditions and matching similar historical cases, and finding out treatment measures corresponding to the similar historical cases according to the similar historical cases, or formulating targeted new treatment measures according to the corresponding treatment measures. The invention provides a'basic information-logical analysis-comprehensive decision 'three-layer progressive architecture case library, so that other modules can be conveniently expanded on the architecture of the case library subsequently; and multi-source data are systematically integrated, so that the problem of fragmentation of existing case data is solved.
Owner:NANKAI UNIV
Police file and image association reasoning method of multi-modal large model
PendingCN121480692ABiological modelsKnowledge representationPattern recognitionInformation processing
The invention discloses a multi-mode large model police file and image association reasoning method, and belongs to the technical field of artificial intelligence and police information processing. The method comprises the following steps: preprocessing police affair texts and images; respectively extracting word-level and sentence-level features and local and global visual features by using a text encoder and an image encoder; realizing alignment and joint representation through a cross-modal fusion layer and an attention mechanism; generating a preliminary reasoning result by adopting a task output head; a heterogeneous evidence graph is constructed, and priori knowledge is injected in combination with the knowledge graph; and finally, joint reasoning is carried out through the graph neural network, and a cross-modal reasoning result and a complete evidence chain are output. According to the method, deep correlation analysis of police affair texts and images is realized, and the accuracy and interpretability of case research and judgment are improved.
Owner:JIANGSU LIANFENG GOLDEN SHIELD INTELLIGENT TECH CO
Dispute focus identification method and device, computer equipment and readable storage medium
The embodiment of the invention discloses a dispute focus recognition method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring real case data to perform multi-modal feature extraction to respectively obtain text features, table features and image features; performing feature fusion on the text features, the table features and the image features to obtain cross-modal fusion features; constructing an element knowledge graph based on entities and relationships in the real case data; obtaining a statement text, and synthesizing the statement text, the cross-modal fusion features and the element knowledge graph to construct a multi-dimensional data set; mining potential dispute points in the multi-dimensional data set through a preset rule base; performing similarity calculation based on the statement text corresponding to the potential dispute point to obtain a similarity result; and judging whether the potential dispute point is a real dispute point or not according to a similarity result. According to the method, information splitting caused by single-modal data processing is avoided, case analysis is ensured to be based on a complete evidence chain, and the conclusion is more comprehensive and accurate.
Owner:BEIJING TAIXIN TIANCHENG TECHNOLOGY CO LTD
Auxiliary proof method and system, electronic equipment and storage medium
The embodiment of the invention provides an auxiliary proof-giving method, an auxiliary proof-giving system, electronic equipment, a storage medium and a computer program product. The auxiliary proof-proof method comprises the following steps: acquiring right protection request content corresponding to a to-be-proof right protection event; performing case analysis on the right protection request content to obtain a right protection category positioning result matched with the right protection event; retrieving a preset checking template based on a right protection category positioning result to obtain a proof item list for the right protection event; and executing a verification task corresponding to the proof item list based on a mode of iteratively retrieving a preset knowledge base, and obtaining a proof suggestion report corresponding to the right protection event for guiding the user to provide a proof. According to the method, an iterative autonomous retrieval mechanism is driven by a task, an analysis process of manual gradual evidence collection is simulated through multiple rounds of query, and compared with a manual dominant evidence collection process, the evidence collection efficiency is improved, and the recall rate and the accuracy of key evidence are effectively improved.
Owner:HANGZHOU ALIBABA INT INTERNET IND CO LTD
Method and device for evaluating intelligent agent, equipment and medium
The embodiment of the invention provides a method and device for evaluating an intelligent agent, equipment and a medium, and the method comprises the steps: obtaining to-be-evaluated data which at least comprises data for at least one bad case; based on the number of the at least one bad case, obtaining at least one first agent corresponding to the at least one bad case; and correspondingly processing the at least one bad case by using the at least one first agent so as to generate at least one bad case analysis result corresponding to the at least one bad case. According to the method, the multi-agent collaboration architecture for evaluating the performance of the agents is established. For each bad case of the to-be-evaluated agent, the corresponding agent can be adaptively acquired to carry out bad case-by-bad case analysis. According to the mode, the effects of high evaluation speed and comprehensive evaluation results can be achieved, and the context explosion phenomenon can be prevented.
Owner:BEIJING ZITIAO NETWORK TECH CO LTD
A Machine Learning-Based Method and System for Outputting Case Studies in Traditional Chinese Medicine Acupuncture
This invention discloses a method and system for analyzing and outputting TCM acupuncture cases based on machine learning, belonging to the field of medical image processing technology. The method acquires facial image sequences from two pathological cycles of the subject, extracts spatiotemporal feature maps, and obtains local receptive field feature matrix pairs through sliding windowing. It calculates the cross-cycle joint entropy gradient and its matrix, and generates a two-dimensional deformation vector using optical flow. Using the coordinates of the first cycle as a reference, the deformation vector is set to zero when the joint entropy gradient does not exceed the rigidity threshold; otherwise, the joint entropy gradient matrix is used as a weight matrix through a sigmoid activation function, and a Hadamard product is performed with the deformation vector to obtain a denoised deformation vector. The denoised vectors are superimposed to obtain corrected pixel coordinates, which are mapped to the target localization coordinate matrix, and the acupuncture case analysis results are output. This scheme achieves precise spatial decoupling of local tissue evolution, eliminates the contamination of rigid regions by global deformation, and significantly improves the robustness and accuracy of cross-cycle acupuncture target localization.
Owner:THE FIRST AFFILIATED HOSPITAL OF ZHEJIANG CHINESE MEDICAL UNIVERSITY
Training methods for forensic case data analysis models and case data analysis methods
The present disclosure provides a forensic case data analysis model training method and a case data analysis method, wherein the training method comprises: obtaining a plurality of sets of sample forensic information based on a plurality of sample forensic case data; training the preset large language model based on each set of sample forensic information and the model fine-tuning strategy corresponding to each type of sub-sample forensic information included in the sample forensic information, to obtain the forensic case data analysis model; wherein the forensic case data analysis model is used to infer and analyze the corresponding target inference analysis result based on the input target forensic case data. The forensic case data analysis model obtained by the above training method can obtain corresponding case analysis results for different input conditions, improving the case analysis efficiency.
Owner:ACADEMY OF FORENSIC SCIENCE
A judicial case retrieval method based on general-specialty fusion model
The application discloses a kind of based on general and special fusion model's judicial case retrieval method, it is related to data retrieval technical field, model scheduling module is based on case complexity and the preset complexity threshold value selects the preset domain professional model and general inference model to carry out semantic analysis, obtains professional feature vector;Input analysis module is preprocessed to original case text and completes feature vectorization, combines professional feature vector to generate paragraph level vector representation and corresponding keyword vector group;Case analysis module calculates cosine similarity by large-scale vector database, outputs preliminary similar case set, then based on model scheduling module carries out verification, outputs refined candidate case set;Result output module is structured and presents the final retrieval result of candidate case set using list structure.The application is more accurate case retrieval realized by combining general model and domain professional model.
Owner:CHINA UNIVERSITY OF POLITICAL SCIENCE AND LAW
Criminal case early warning method and system based on multi-modal fusion and dynamic adaptation
PendingCN122112940Aimprove accuracyHigh quality data foundationKnowledge representationInference methodsSemantic vectorEarly warning system
The present application relates to the technical field of criminal case data analysis and early warning, in particular to a multi-technology coordinated criminal case intelligent early warning system and method fusing pre-training large model customization adaptation, dynamic weighted clustering and semantic vector retrieval, belonging to the cross technical field of judicial big data and artificial intelligence, through the coordinated technical path of "large model label extraction-weighted clustering-vector deduplication", a full-process intelligent system of "data input-intelligent analysis-accurate early warning-feedback iteration" applicable to judicial case analysis and processing scenes is constructed, not only effectively solving the core problems of low efficiency and early warning redundancy under the traditional manual analysis mode, but also completely solving the many common problems existing in the current technical system of criminal case analysis and early warning.
Owner:CHONGQING TELECOM SYST INTEGRATION CO LTD
Qualitative and quantitative intelligent auxiliary trial method and system
This invention discloses an intelligent auxiliary method and system for qualitative and quantitative disciplinary proceedings. The method includes: acquiring detailed case information; analyzing the detailed information using a large-scale model to predict the type of violation; extracting key parameters needed to determine the qualitative and quantitative disciplinary action based on the violation type; supplementing necessary information through human-computer interaction; and combining the key parameters with regulations to generate the final case analysis, qualitative, and quantitative disciplinary results. By implementing this method, the powerful tagging, summarizing, and deep reading comprehension capabilities of the large-scale model can be utilized to effectively parse and integrate complex legal provisions and case scenarios, significantly simplifying development and improving the accuracy and efficiency of the qualitative and quantitative disciplinary process.
Owner:HANGZHOU BENJING LABORATORY CO LTD
Public appeal case intelligent processing method and system
PendingCN121502388AData processing applicationsNeural learning methodsStatistical analysisValidation methods
The invention relates to a public appeal case intelligent processing method and system, and the method achieves the analysis of a case through employing a government affair entity matching-oriented extraction model and combining with the comparison learning for optimization, and achieves the analysis of the case through a small computing power resource overhead. By introducing a small parameter quantization LLM model and adopting a verification method based on a thinking chain and evidence retrieval, the case analysis accuracy is improved while the model illusion risk is reduced; more accurate subject information is obtained by establishing a supervision object database and adopting a matching strategy of vectorization, weighted cosine similarity and cross comparison; and through a subsequent classification model and a clustering algorithm (such as DBScan and counting), macroscopic statistical analysis, hotspot map generation and high-risk object early warning of the case are realized. The problems that in the prior art, resource expenditure is large, precision is poor, subjects are complex, fuzzy and difficult to match, and a macroscopic analysis function is lacked are solved, and efficient and accurate automatic analysis, matching and statistical analysis of public appeal cases are achieved.
Owner:SHAOXING SMART CITY GRP CO LTD
A case analysis method and device, a storage medium and an electronic device
ActiveCN117131185BNatural language data processingSpecial data processing applicationsData ingestionFeature extraction
The specification discloses a case analysis method and device, a storage medium and an electronic equipment, wherein the method comprises: obtaining target case data corresponding to a target case type, inputting the target case data into a pre-trained feature extraction model, extracting features of the target case data by using the feature extraction model to obtain target features of the target case data, obtaining first historical data corresponding to the target features in a data center associated with the target case type, extracting features from the first historical data based on the target features to obtain first feature data, obtaining evaluation data based on the first feature data and the target case data, generating a first evaluation report based on the evaluation data, and using the embodiments of the specification, the features extracted based on the target case data are used to obtain historical data, and an evaluation report corresponding to the target case type is generated, thereby reducing the time required for analyzing cases and writing reports, improving the processing efficiency of case analysis, and ensuring the efficiency and accuracy of case analysis.
Owner:ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
A power facility case management and application system and method
ActiveCN115689827BEnsure comprehensivenessimprove teaching qualityData processing applicationsOther databases queryingFault managementCase analysis
The disclosure provides a power facility case management and application system and method, comprising: a case uploading unit configured to provide a case uploading interface for each power facility substation, a management personnel of a management center, and a hidden danger, defect and fault management subsystem, and store uploaded case information, wherein the case comprises three types of cases of hidden danger, defect and fault; a case analysis unit configured to, for imported cases, select and associate countermeasures and standards related to the cases from a pre-constructed countermeasure library and a standard library based on the system, equipment and components to which the cases belong; meanwhile, divide the cases into typical cases and ordinary cases based on case characteristics; and a case display unit configured to graphically display the distribution of cases in each system, equipment or component and typical cases.
Owner:ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER COMPANY
Hazardous chemical substance storage explosion accident cause analysis and risk diagnosis method
The invention belongs to the technical field of accident analysis, and particularly discloses a hazardous chemical substance storage explosion accident cause analysis and risk diagnosis method, which comprises the following steps: analyzing an accident report text by combining an improved HFACS model and related regulatory standards, and constructing a cause factor set; calculating the grey relational degree of each cause factor and the explosion accident through a grey relational degree method, and substituting the grey relational degree into an Apriori algorithm to mine cause factor association rules; establishing a Bayesian network model based on a strong association rule to obtain key cause factors and cause paths; predictive analysis is carried out by focusing key cause factors, a high-risk scene and the key cause factors which have the most obvious influence on an accident are identified, and targeted prevention measures are put forward; through reasoning and analyzing specific accidents, potential cause factors are identified, and targeted prevention measures are provided. According to the method, the accuracy and comprehensiveness of dangerous chemical substance storage accident case analysis are improved, and a theoretical basis is provided for realizing accurate risk grading prevention and control and optimizing resource allocation.
Owner:CHINA UNIV OF MINING & TECH (BEIJING)
Structured extraction and identification method and system for multi-modal key information of legal consultation
ActiveCN121959492AImprove the level of intelligenceImprove case handling efficiencyCharacter and pattern recognitionBiological modelsStructure extractionSpatial mapping
The invention discloses a legal consultation multi-mode key information structured extraction and identification method and system, and relates to the field of legal services. The method comprises the steps of obtaining a legal consultation request submitted by a user; analyzing the multi-modal evidence file, and establishing a triple mapping relationship among text contents, visual elements and spatial positions; constructing a legal evidence ontology dictionary, performing cross-modal semantic understanding on visual-text joint information with a spatial mapping relationship, and extracting a structured evidence tuple comprising legal entities, entity attributes and relationships among entities; and carrying out logic merging on the structured evidence tuple according to the case element template to generate a standardized case fact structural body. The method has the advantages that unstructured evidence files such as contracts, borrows and discriminants are automatically converted into structured case fact structural bodies which can be directly used for case analysis, document generation and legal reasoning.
Owner:BEIJING INSTITUTE OF TECHNOLOGY (ZHUHAI)
Atlas inference analysis system for cell antigen treatment defects
The invention discloses an atlas inference analysis system for cell antigen treatment defects, relates to the technical field of knowledge atlas inference, and is used for solving the problem of slow explaining and positioning of defect presentation. According to the method, a detection likelihood set is constructed by fusing HLA typing, somatic cell variation, transcriptional expression, immunopeptidomics and surface HLA detection, direct presentation and cross presentation sub-graphs are assembled by adopting a mode gating and loading complex integrity rule, a reachable path and observation consistency matrix is generated, structural contradictions and detection limitations are distinguished, and a detection result is obtained. According to constraint propagation, node cutting and link shrinkage are performed to form an individualized map, defect nodes and defect paths are searched and output based on a minimum interpretation path and a cause and effect graph cost, and a verification and intervention list and clinical decision support output are generated, so that unnecessary detection and intervention attempts are reduced, and the detection efficiency is improved. And the timeliness and consistency of case analysis and strategy making are improved.
Owner:南昌大学第一附属医院
Photovoltaic case analysis quota inference method based on case reasoning
The invention discloses a photovoltaic case analysis quota inference method based on case reasoning, and the method comprises the following steps: S1, carrying out the classified storage of each historical project according to the information of each historical project and the feature dimension, and constructing a case library; s2, establishing an overall difficulty coefficient, a construction feature dimension and an environment feature dimension of any historical project and an association rule model of key parameters and quota indexes in a construction process; s3, inputting a plurality of related parameters of any new project into the case index system, and dynamically adjusting the matching weight coefficient of each related parameter according to the importance degree of each related parameter; and S4, the case index system retrieves cases in the case library according to the input related parameters and the corresponding weight coefficients, and outputs an optimal quota index scheme of the current new project. According to the method, the historical engineering data is converted into the structured case library, so that accurate prediction and efficient management of the construction quota can be improved.
Owner:HUAFENG TECH (NANJING) CO LTD
System
An object of the system according to the embodiment is to model a thought pattern of a judge and propose an optimal strategy.SOLUTION: A system includes a precedent collection part, a precedent analysis part, a thinking pattern modeling part, and a strategy proposal part. A case collection part collects past case data of a judge. A case analysis part analyzes the case data collected by the case collection part. The thought pattern modeling unit models a thought pattern of a judge based on the data analyzed by the judge case analysis unit. The strategy proposing section proposes an optimum strategy based on the thinking pattern modeled by the thinking pattern modeling section.SELECTED DRAWING: Figure 1
Owner:SOFTBANK GROUP CORP