19 results about "Case Search" patented technology

The invention relates to the technical field of computers, and discloses a legal case strategy analysis method and system, electronic equipment and a storage medium, and the method comprises the steps: analyzing a to-be-analyzed legal case, extracting key information, and constructing a dynamic affair graph based on the key information; matching with a historical case database by adopting a multi-dimensional class case retrieval method on the basis of the dynamic event atlas, and retrieving similar historical cases; based on the judgment result information of the similar historical cases, performing analysis in combination with key information or a dynamic affair map of the to-be-analyzed legal case, and generating judgment result prediction of the to-be-analyzed legal case; and fusing the dynamic affair atlas, similar historical cases and judgment result prediction, calling a large language model adjusted by a law field instruction through a retrieval enhancement generation architecture, and generating a litigation policy analysis report with a preset structure part. According to the method, the automation degree and depth of case information processing are improved, and closed-loop generation from analysis to strategy is realized.

The invention discloses a law enforcement case qualitative analysis method based on a large language model, and belongs to the technical field of law enforcement informatization. The system mainly comprises a data preprocessing module, a law article and case retrieval module, a prompt template generation module, a large language model reasoning module, a consistency checking module and a manual auditing and writing-back module. The method comprises the following steps: S1, data preprocessing; s2, retrieving law provisions and cases; s3, a prompt template is constructed; s4, large language model reasoning; s5, checking the consistency; and S6, performing manual auditing and write-back. In the step S1, sensitive information such as a natural person name, an identity card number, a contact way, a family address and the like in a case text is subjected to anonymization replacement or hash processing. The law enforcement case qualitative analysis method based on the large language model achieves the effects of improving accuracy, consistency and interpretability.

The invention belongs to the technical field of intelligent dispatching of power systems, and particularly relates to a power distribution network historical case retrieval and recommendation method based on multi-modal data fusion and depth similarity matching. The method comprises the following steps: constructing a multi-modal case feature library, and storing historical case data including a topological structure, a load curve and a scheduling text; receiving current power distribution network fault or scheduling demand information; calculating the topological similarity between the current scene and the historical case by adopting a graph neural network; calculating load distribution similarity by applying a dynamic time warping algorithm; calculating the semantic similarity of the scheduling text based on a fine-tuned BERT model of the electric power major; dynamically adjusting each feature weight according to the real-time new energy permeability, and generating a comprehensive similarity score; candidate cases conforming to power grid safe operation conditions are screened through a physical constraint verification layer; and outputting the recommendation case and the applicability analysis report thereof.

The invention discloses a crane main beam non-probability reliability assessment method based on a convex set model, and the method comprises the steps: collecting the working condition and key section multi-source data of a crane, and carrying out the time alignment, missing measurement compensation and time-frequency feature extraction; selecting a parameter vector influencing the safety of the main beam, and constructing a combined convex set uncertain domain consisting of an interval box, an ellipsoid set and polyhedron linear constraints; based on a finite element and radial basis function substitution model, main beam key section response mapping is established, the proportion of equivalent stress and deflection relative to an allowable value is obtained, and an overall limit criterion is formed; executing worst case search in the uncertain domain, and calculating an opposite number of a maximum value of a limit criterion as a non-probability reliability index; and reliability indexes are further calculated and summarized at the section layer and the main beam layer, and the reliable state grading of the main beam is realized according to a preset threshold value. The method does not need to depend on probability distribution hypothesis, and rapid assessment of the safety of the crane girder can be realized under small sample and multi-source uncertain conditions.

The present disclosure relates to a text encoding model training method, a case search method, a device and an electronic device. The text encoding model training method comprises: obtaining a training data set, the training data set comprising case information of a plurality of query cases and case information of positive cases and negative cases; encoding the case information in the training data set using a text encoding model to obtain a case feature set corresponding to the training data set; determining a first correlation score between each query case and a corresponding positive case and a second correlation score between each query case and a corresponding negative case according to the case feature set; determining a contrast learning loss according to the first correlation score and the second correlation score and training the text encoding model based on the contrast learning loss. According to the present disclosure, the text encoding model can learn legal knowledge from the unannotated training data set, thereby improving the performance of the trained text encoding model in the legal field downstream task.

The application discloses a skin disease case retrieval method and device, a medium and a product, and relates to the technical field of medical image understanding and multi-modal knowledge fusion. The method encodes and maps multi-modal data of each skin disease case, obtains labeled features of the multi-modal data, projects the labeled features to a shared latent space, and obtains labeled features of the multi-modal data in the shared latent space; based on the labeled features, a Top-k node selection mechanism based on correlation scores is used to construct a single-modal knowledge graph of each image modality and a cross-modal knowledge graph between any two modalities, and then a modality-level representation and a cross-modal embedded representation are obtained, and a case database is obtained by splicing; the similarity between the feature vector of a skin disease query case and the feature vectors in the case database is determined, the feature vector with the highest similarity in the case database is output, and a retrieval result of the skin disease query case is obtained. The application can improve the accuracy and clinical applicability of cross-modal medical image retrieval.

The invention relates to the technical field of computers, and discloses a class case retrieval method and a class case retrieval model training method and device.The method comprises the steps that a preset text and a first question text input by a user are obtained; determining an overall semantic feature and a word semantic feature corresponding to the preset text; determining a core semantic feature corresponding to the preset text based on the overall semantic feature, and determining tag information corresponding to the preset text based on the word semantic feature; determining the similarity between the first question text and the preset text based on the overall semantic feature, the core semantic feature and the tag information corresponding to the preset text; and when the similarity between the preset text and the first question text is greater than a preset similarity threshold, determining the preset text as a target preset text similar to the first question text. According to the method, the target preset text similar to the first question text input by the user can be determined according to the first question text, and the accuracy of text similarity matching is improved.

In a recovery level estimation device, an image acquisition means acquires images capturing eyes of a target patient for whom a recovery level is estimated. An eye movement feature extraction means extracts an eye movement feature which is a feature of an eye movement of the target patient, based on the images. A past case storage means stores, as past cases, a plurality of cases in which each of patients and information concerning the eye movement feature and the recovery level of the patient are associated with each other. A similar case search means configured to search for each similar case including a similar eye movement feature to the eye movement feature of the target patient among the past cases. A recovery level estimation means estimates the recovery level of the target patient based on information concerning the recovery level of each similar case.

The application provides a case retrieval method and device based on a large language model and vector retrieval, and belongs to the field of data retrieval. The method specifically comprises receiving a case retrieval query instruction; when the large language model is called to determine that the background processing branch of the case retrieval query instruction is regular case retrieval, the case facts and case causes are disassembled according to different case dimensions, case retrieval elements are generated, and retrieval weights are assigned; the preliminary recall cases corresponding to each case dimension are obtained according to the similarity values; the preliminary recall cases are screened once based on the similarity values and the retrieval weights to determine candidate cases; the candidate cases are subjected to a correlation Boolean value determination with the case facts and case causes to obtain target cases; and a case study analysis report is generated based on the case facts and case causes and the target cases by using the large language model. Through the processing scheme of the application, it is ensured that the case search will not miss any important dimension such as facts or controversial points, and the accuracy and comprehensiveness of case retrieval are greatly improved.

The invention discloses a multi-dimensional intention embedding interpretable judgment recommendation system based on a DIKWP model. The system is composed of a judgment inference engine, an intention embedding module, an interpretation generation module and an interactive display interface. The engine performs hierarchical reasoning according to data-information-knowledge-intelligence-intention, and generates referee suggestions in combination with fact elements, legal provisions and class case retrieval; the intention module acts value weights of fairness, efficiency, policies and the like on a target layer to regulate and control the cutting amount; and the interpretation module synchronously outputs a semantic reasoning path which comprises a fact basis, a legal basis, a class case reference and an intention description, and provides hierarchical presentation according to user types. The system improves judicial AI transparency and reviewable performance, and is suitable for court case handling assistance, judgment document interpretation, class case research and other scenes.

The invention provides a heterogeneous judicial data-oriented collaborative platform data fusion system and method, and the system comprises a source data layer which is configured to store dispersed and heterogeneous business data of political and legal departments such as judicial, inspection and court, and covers judicial business data such as counterfeit, correction, wholesale, complaint and judgment; the data virtualization layer is configured to be connected with various databases in the source data layer, provide a unified data access interface, integrate inconsistent expressions through a heterogeneous data analysis and integration module, and provide a unified data access interface; a unified judicial entity-relation view taking various persons, cases, laws and regulations, court hearing sessions and the like as entities is constructed through a unified judicial entity-relation view creation module; and the data fusion collaborative application layer is configured to provide judicial intelligent application services such as intelligent judgment, class case retrieval, decision support and the like based on the unified judicial entity-relationship view. Through the data virtualization technology and the deep neural network technology, logic integration and physical isolation of judicial data are achieved, on the premise that data are not migrated and an existing system is not changed, data islands are broken, real-time and seamless fusion and collaboration of cross-department data are achieved, and the collaboration efficiency and the intelligent level of judicial services are effectively improved.

The application provides a kind of legal system case retrieval method and system, by determining the fuzziness of each legal constitutive element of the case to be retrieved according to statute, and retrieving case base based on the statute to be retrieved, obtain intermediate query result, so as to the semantic vector of the first fact text segment corresponding to each legal constitutive element in basic case, the semantic vector of the second fact text segment corresponding to each legal constitutive element in any case in intermediate query result, and the fuzziness of each legal constitutive element, determine the similarity of each legal constitutive element corresponding to the case and the case to be retrieved, and the total similarity of the case and the case to be retrieved, and then filter the case from intermediate query result, which total similarity with the case to be retrieved is greater than the first threshold value and the similarity of the highest legal constitutive element corresponding to the fuzziness is less than the second threshold value, as query result, return to user, realize the case retrieval focusing on difference.

The application relates to a system for realizing intelligent configuration file checking based on large model and rule fusion, which comprises a configuration loading module for analyzing the structure and key value pairs of a configuration file; a symbol detection module for identifying implicit character errors in the configuration file; a rule checking module for performing single file constraint rule checking and cross-file logic constraint rule checking; a historical case searching module for matching and searching the current configuration to obtain relevant historical fault case information; a large model analysis module for calling a large language model interface to perform semantic reasoning and analysis; and a report output module for generating a structured checking report and outputting the same. The system, method, device, processor and computer readable storage medium thereof for realizing intelligent configuration file checking based on large model and rule fusion can be widely applied to enterprise automation operation and maintenance, securities trading systems and cloud native cluster configuration management scenes, effectively reduces human configuration risks and improves intelligent verification capability of configuration changes.

An object of the system according to the embodiment is to provide information about failure cases and allow doctors and patients to find an appropriate countermeasure.SOLUTION: A system according to an embodiment includes a medical history upload unit, a database construction unit, a similar case search unit, and an information providing unit. The medical history uploading unit uploads the medical history. The database construction unit analyzes the medical history uploaded by the medical history upload unit to construct a database. The similar case search unit searches for a similar case from the database constructed by the database construction unit. The information providing unit provides a treatment method, an explanation method, and a prognosis process based on the similar case searched for by the similar case search unit.SELECTED DRAWING: Figure 1

The application relates to the technical field of case resource matching, and relates to a case resource analysis and matching method and system based on user information, which comprises the following steps: confirming a historical case data set based on an information collection instruction, obtaining an identification case data set by using the historical case data set, constructing an initial search database based on the identification case data set, optimizing the initial search database to obtain a case search database, obtaining a user identity code of a user, obtaining a user information node based on an information analysis instruction and the user identity code, searching in the case search database by using the user information node to obtain an initial search data set, confirming a target search data sequence based on the initial search data set, and sending the target search data sequence to an initiating end of a case matching instruction by using a result feedback unit to realize analysis and matching of case resources. The application can realize analysis and matching of case resources in combination with user information.

1. Name of the product in this design: Graphical User Interface for Emergency Duty Management Information System of Electronic Equipment. 2. Intended use of this design: for use in electronic devices. 3. The key design features of this product are its graphical user interface. 4. The image or photograph that best illustrates the design's key points: the front view. 5. This product is designed with a graphical user interface (GUI), and the rear view, left view, right view, top view, bottom view, and 3D view are omitted. 6. Purpose of the graphical user interface: Used for the operation and management of emergency duty management information systems on electronic devices. 7. Description of the changing states of the graphical user interface: The main view is the interface after logging in. Clicking "Alert" switches to the interface change state diagram 1. Clicking "Seedling Event" in "Seedling Event Management" on the left side of the interface change state diagram 1 enters the interface change state diagram 2. Clicking "View Details" enters the interface change state diagram 3. Scroll the mouse to slide the timeline. Clicking "Case Search Task" will get the interface change state diagram 4.

The present disclosure relates to a text encoder training method, a case retrieval method, a device and an electronic device. The text encoder training method comprises: obtaining a plurality of case groups, each case group comprising case information of at least two cases and corresponding similarity information; encoding the case information of each case using a text encoder to obtain case features of each case; determining intra-class feature similarity in each case group and inter-class feature similarity between each case and a different case according to the case features of each case; determining a contrast learning loss according to the intra-class feature similarity, the inter-class feature similarity and the similarity information corresponding to the cases, and training the text encoder based on the contrast learning loss. According to the embodiment of the present disclosure, fine-grained legal knowledge can be introduced to train the text encoder, so that the trained text encoder outputs high-quality case features, thereby improving the accuracy of case retrieval, and the retrieved same cases have interpretability.

The invention relates to the technical field of data retrieval of cerebral diseases and the like, and particularly discloses a retrieval method and system for neurology cases, and the method comprises the steps: obtaining a current patient characteristic case, screening out core disease characteristics and secondary disease characteristics in combination with a neurology standard case library, and generating a main typical case group by adopting a hierarchical clustering algorithm; on the basis of two dimensions of abnormal disease features and normal examination features, a matching degree score of a patient case and the main typical case group is calculated, and a retrieval strategy is dynamically judged; constructing a secondary typical case group in a high-matching scene and carrying out cross analysis to generate a target case retrieval set, mining a potential disease direction in a low-matching scene, constructing an atypical case group, carrying out weight assignment and matching screening, and then complementarily fusing the atypical case group with a primary typical case group to generate a target case retrieval set; the problems that the neurology department case data is complicated and the retrieval accuracy and efficiency are low are solved, and the coverage of typical and atypical case retrieval scenes is realized.

The invention relates to the technical field of medical treatment, in particular to an outpatient triage intelligent hospital guide system which comprises a data acquisition module, a model establishment module, a case search module, an intelligent hospital guide module, a real-time distribution module, an emergency processing module, an intelligent suggestion module and an online medicine taking module. The dialect data and the language data of all countries in the world are integrated through the model building module, and the dialect database, the Chinese and foreign language database and the Chinese and foreign language switching model are built, so that the system can better serve patients with different language backgrounds, communication obstacles caused by language impassability are reduced, and the communication efficiency is improved. Therefore, the time consumption of the patient in the hospital guide process is reduced.