61 results about "Investigation methods" patented technology

The invention relates to the technical field of background investigation, and particularly discloses a talent background investigation method based on multi-source data evaluation, which comprises the steps of constructing a dynamic talent knowledge graph, performing semantic alignment processing on multi-source cross-modal data, evaluating data quality based on a multi-dimensional confidence model, and constructing a confidence closed-loop correction mechanism. Performing intelligent correction on the low-confidence data, and reversely updating the credibility weight of the data source according to a correction result; an event-driven incremental update architecture is adopted, and dynamic events of multi-source data are captured in real time through a distributed event awareness engine. According to the method, the dynamic knowledge graph is used as a unified carrier, and the multi-source data is upgraded from fragmented storage to a semantic association network, so that the talent background survey data is converted from static piling to a dynamically evolved knowledge network, and the accuracy and timeliness of evaluation are remarkably improved.

The invention relates to the technical field of human resources, and discloses a multi-dimensional automatic background investigation method and system based on Ai assistance. The system comprises a multi-source data acquisition module, an intelligent analysis engine module, a real-time interview processing module, a quality verification control module, a dynamic decision support module, a privacy security protection module and a visual report generation module. According to the method, public data of candidates are acquired through a multi-thread crawler technology, and the authenticity of educational background is verified; analyzing the paper certificate by adopting an optical character recognition technology; constructing a space-time relation knowledge graph to detect work experience abnormality; interview content is transcribed in real time, and emotional tendency is analyzed; dynamically adjusting the evaluation dimension weight; and generating a visual risk assessment report. According to the method, the enterprise employment risk is reduced, the comprehensiveness and depth of background investigation are improved, the accuracy and applicability of a background investigation conclusion are improved, a safe and reliable background investigation environment is constructed, and the enterprise human resource allocation effect is optimized.

The application discloses a kind of urban road physical structure hidden danger investigation method, device and electronic equipment, method includes: obtaining the road physical structure data in target road network;According to the road physical structure data, determine the risk evaluation index data corresponding to target type road, the risk evaluation index data is determined according to the road attribute of corresponding type road;According to the risk evaluation rule and the risk evaluation index data of the preset, the risk of target type road is evaluated;According to the risk evaluation result of target type road, determine the hidden danger investigation scheme of target type road.The method of the application can make the road hidden danger investigation more efficient, effectively solve the problem that the dependence degree of existing road hidden danger investigation scheme on the working experience of investigators is high and the investigation is not thorough, greatly save the labor cost.

The invention discloses a multi-modal social network public opinion hidden danger troubleshooting method and system, and the method comprises the steps: collecting the multi-modal data of a social platform in real time through a distributed edge node, and the multi-modal data comprise text, image and audio data; dividing a plurality of social network communities based on user interaction relationships, wherein the user interaction relationships include but are not limited to topic circles, friend relationships, comment interaction and forwarding likes; community propagation dynamic features, group topological features and content features are extracted from the multiple social network communities one by one based on the multi-modal data; screening out a plurality of suspected hidden danger communities from the plurality of social network communities based on the community propagation dynamic characteristics, the group topological characteristics, the content characteristics and a preset screening strategy; and after carrying out hidden danger detection and hidden danger classification on the plurality of suspected hidden danger communities based on the multi-modal data, outputting a plurality of hidden danger classifications corresponding to the plurality of suspected hidden danger communities. According to the method and the system, the comprehensiveness and the accuracy of public opinion hidden danger recognition are remarkably improved.

The invention provides an intelligent auxiliary flow scheduling method for a whole flow scheduling process, and relates to the technical field of big data, and the method comprises the steps: S1, deploying an artificial intelligence computing power cluster at a center end; s2, registering a traffic scheduling task through a held mobile terminal by a traffic scheduling person during traffic scheduling, interacting with the central terminal in the traffic scheduling task execution process to call an artificial intelligence computing power cluster to perform remote identity verification and auxiliary traffic scheduling question and answer on a traffic scheduling object, and after the traffic scheduling task is finished, according to a generated traffic scheduling question and answer record, performing traffic scheduling on the traffic scheduling object according to the traffic scheduling question and answer record; and completing structured analysis and generating an epidemiological investigation report. The method has the beneficial effects that by deploying the artificial intelligence computing power cluster at the center end, unified management and application of the flow scheduling artificial intelligence models and reasonable scheduling of resources are realized, so that each flow scheduling artificial intelligence model can be integrated into the whole flow scheduling process, and the flow scheduling efficiency and accuracy are effectively improved.

The invention discloses a hidden danger checking method and system based on a multi-modal large model, and belongs to the technical field of artificial intelligence and industrial safety, and the method comprises the steps: building a hidden danger checking professional knowledge collecting, integrating, carrying out structured processing, and cleaning various data related to hidden danger checking; performing refined labeling on the text and picture data, wherein the refined labeling comprises troubleshooting standard labeling, historical troubleshooting record labeling, picture risk point labeling and data alignment; performing fine adjustment on the basic model by utilizing the marked multi-modal data set; on-site inspectors can shoot pictures of hidden danger points through the mobile phone APP and upload the pictures, and the server identifies the pictures and then returns results to the mobile phone APP; and performing intelligent question and answer query on the content in the hidden danger checking knowledge base by using the multi-modal large model. According to the invention, hidden danger investigation can be carried out efficiently, accurately and comprehensively, and intelligent identification, analysis and processing suggestion generation of hidden dangers are realized, so that the quality and efficiency of hidden danger investigation work are improved.

The invention relates to the field of artificial intelligence, discloses a full-duty investigation method and system based on a large model hierarchical agent architecture, and aims to solve the problems of efficiency bottleneck, knowledge blind areas, data stream solidification and the like in existing full-duty investigation. The method comprises the steps that a central task planning agent receives an instruction and decomposes and dynamically reconstructs a task; the agent modules in each field refine tasks and cooperatively analyze multi-source data; the central evidence management agent constructs a global evidence chain; the central report generation agent generates a report. The system comprises a central task planning module, a plurality of fields, a central evidence management module and a central report generation agent module. According to the technical scheme, intelligence, efficiency and depth of full-duty investigation can be remarkably improved, existing problems are solved, and through dynamic task reconstruction, knowledge fusion, evidence verification and full-link traceability, conclusion objectivity and reliability are improved, and systematic risks are reduced.

The present invention provides a building investigation object generation method, a building investigation method, a building investigation facility, and a system. The building investigation object generation method includes generating, for at least one investigation waiting system in a building, a plurality of investigation objects corresponding to the at least one investigation waiting system by a duplicate elimination scheme. The plurality of generated investigation objects are different from each other, and the duplicate elimination scheme is implemented at least on the basis of a correspondence relation between the investigation waiting system and the investigation object. It is thereby made possible to improve the accuracy and versatility of identifying the object to be investigated, improve the investigation efficiency, and save the investigation cost.

This invention discloses a method and device for assisting epidemiological investigation based on machine vision and deep learning. The method includes acquiring the target to be tracked, single-lens target tracking, mask detection and classification and storage of at-risk individuals, cross-lens target re-identification, and target trajectory mapping. It innovatively applies pedestrian re-identification technology to epidemiological investigation and tracing, automatically generating trajectories and close contacts, significantly reducing manual labor while improving the accuracy and timeliness of the investigation. Furthermore, this system has no hardware requirements and can be directly integrated into existing monitoring systems, allowing for remote maintenance and easy upgrades. Overall, this software outperforms existing epidemiological investigation methods and has advantages such as strong versatility, wide applicability, and ease of use.

The invention discloses a double-path verifiable threshold signature-based block chain right confirmation and responsibility investigation method, which comprises the following steps of: S1, receiving right confirmation data, processing the data to obtain normalized data, and calculating a data abstract of the normalized data; submitting the data abstract and the associated information thereof to a block chain for evidence storage to form a right confirmation request record; s2, in response to the right confirmation request record, selecting a committee member set from candidate nodes based on a preset strategy, and cooperatively generating a global public key and a private key share corresponding to each committee member by the committee member set through a distributed key generation protocol; and S3, each committee member generates a partial signature for the data abstract by using the private key share of the committee member, and generates a verifiable proof for proving the correctness of the calculation process of the partial signature of the committee member at the same time. According to the invention, independent verification and accurate responsibility tracing of individual signature behaviors of committee members can be realized.

In order to prevent a CRC from having an excessive work burden and also to reduce the likelihood of burden on a subject, and to improve efficiency of survival investigation, this survival confirmation investigation system for confirming the survival of a subject in a clinical trial generates a clinical trial project conforming to a clinical trial protocol, sets a predetermined distribution schedule for each subject on the basis of the clinical trial project, distributes a confirmation message for the subject relating to survival confirmation of the subject and a multiple-choice question on the basis of the distribution schedule, acquires an answer to the question, and manages the answer for each subject.

To provide a fund use investigation device that can efficiently and reliably trace the flow of funds related to a green project to prevent greenwashing with appropriate accuracy.SOLUTION: A fund use investigation device 100 comprises: a storage 101 that holds the history of circulation of digital currencies issued in relation to a green project; and an arithmetic unit 104 that executes processing of extracting, from the circulation history, information on processing of converting the digital currencies into cash in persons involved in the green project to calculate the ratio of conversion of the digital currencies into cash in each of the persons involved, and processing of outputting information on the persons involved with the ratio of conversion into cash exceeding a reference as information on the risk that the digital currencies are used out of the purpose of use.SELECTED DRAWING: Figure 2

The invention relates to the field of territorial investigation technology and artificial intelligence application technology, in particular to a territorial intelligent investigation method and system based on multi-source remote sensing fusion and AI collaboration, and the method comprises the steps: obtaining multi-source remote sensing data and auxiliary data, carrying out the preprocessing, extracting meta-information, carrying out the time phase-semantic double-constraint fusion, and obtaining a fusion image; according to the fused image and the auxiliary information, land type identification and land utilization change detection are carried out through a constructed semantic enhancement type adaptive AI model, suspicious pattern spots are marked, and optimization training is carried out on the semantic enhancement type adaptive AI model through real-time incremental learning; according to the suspicious pattern spots, pattern spot tasks are generated, AR live-action linkage type interior work and field work real-time collaborative operation is carried out, and knowledge graph driven investigation result standardization management is carried out. According to the scheme, the precision, efficiency and data utilization rate of land intelligent investigation are improved.

The invention provides a multifunctional field geological survey portable cart, and relates to the technical field of field geological survey, the multifunctional field geological survey portable cart comprises a survey storage box, the rear end face of the survey storage box is provided with a rear support frame, the upper end face of the survey storage box is provided with a tablet personal computer, and the survey storage box is internally provided with an auxiliary survey assembly. An auxiliary damping assembly is arranged between the rear supporting frame and the investigation storage box, through the design of the auxiliary damping assembly, a working platform and a moving platform in the equipment are separated, so that the influence of vibration generated in the field dragging and moving process on the equipment is reduced, through the arrangement of the auxiliary damping assembly, multiple investigation means are combined, and the investigation efficiency is improved. According to the field geological survey device, the data are integrated into a working platform, so that the device is convenient to carry and store, real-time data acquisition, fusion and analysis are realized, the efficiency and the intelligent level of field geological survey are greatly improved, and the practicability is high.

To efficiently determine the usage status of a telephone number to be investigated. [Solution] A telephone number investigation device (10) is connected to a plurality of IMS terminals (50) connected to a terminating mobile IMS network (30) via an originating fixed IMS network (20), adds SDP parameters to an INVITE request for the IMS terminal (50) being investigated, sends the INVITE request to the originating fixed IMS network (20), receives a response message via the originating fixed IMS network (20), and determines the usage status of the telephone number of the IMS terminal (50) being investigated based on the elapsed time until the response message (response) is received.

The invention discloses a soil field investigation method and device adaptive to a network environment. The method comprises the following steps: A, acquiring survey task information on line according to identity information of survey equipment, wherein the survey task information comprises identification information of a soil survey task and a form model of survey data; b, constructing an off-line data model according to the survey task information, performing soil survey, then forming off-line survey data according to the off-line data model, and temporarily storing the off-line survey data; c, acquiring the current network connection state and signal strength of the investigation equipment through network service, and if the requirements are met, uploading the identity information of the investigation equipment, the identification information of the soil investigation task and the offline investigation data to a server; and D, the server analyzes and verifies the identity information of the investigation equipment, the identification information of the soil investigation task and the offline investigation data, and stores the information in a cloud database if the verification is passed. Through the cloud and the investigation device, the data storage efficiency is improved.

The invention relates to an industrial hidden danger troubleshooting method and system based on visual identification, relates to the technical field of industrial safety production management, and aims to construct hierarchical feature extraction-dynamic association fusion-whole process closed-loop management and deploy a multi-level industrial hidden danger visual identification model. The basic and multi-scale feature extraction layer cooperatively obtains global, microscopic and multi-scale features; the spatial correlation fusion layer integrates the multi-source features through dynamic weighting to form industrial hidden danger characterization features; and the fault decision-making layer outputs a target fault type, carries out linkage rectification and generates a troubleshooting report. The system solves the limitation of an existing system, gives consideration to macro and micro features, improves the adaptability to hidden dangers of different sizes, achieves the full-process digital closed loop from detection to treatment, and meets the core demands of industrial hidden danger investigation.

The invention discloses a power equipment operation hidden danger troubleshooting method, which comprises the following steps: S1, multi-source data acquisition and integration: acquiring multi-dimensional data covering the full life cycle of equipment, and forming a structured database by adopting a data cleaning technology; s2, big data intelligent analysis: based on the data pool, adopting machine learning and statistical analysis technologies to identify hidden dangers and predict fault risks in advance; s3, troubleshooting execution based on big data: according to early warning information output by big data analysis and priorities thereof, directly guiding daily inspection, professional detection and special troubleshooting of the equipment; s4, performing big data enabling closed-loop management: performing progress tracking, effect verification and experience precipitation on troubleshooting execution projects by adopting a big data analysis technology, and realizing intelligently upgraded operation hidden danger troubleshooting closed-loop management; the method has the advantages of being good in troubleshooting effect, accurate in troubleshooting result, high in troubleshooting efficiency and capable of guaranteeing the long-term use effect, and long-term safe and stable operation of the power equipment can be effectively guaranteed.

The application discloses a tobacco retail market network case investigation method and related equipment, and the method ensures the timeliness and quality of multi-source data through hierarchical heterogeneous collection and credibility analysis; time sequence fusion and abnormality identification are carried out in a unified space-time framework, and real-time processing of dynamic inflow data can be realized; a dynamic network portrait is constructed and continuously updated based on the abnormality identification result, evolution analysis of a gang structure and a core node is realized, and the limitation of static knowledge reasoning can be broken through; finally, actual investigation results are used as negative feedback labels to optimize the model, a closed-loop system with self-iterative adjustment capability is formed, and the adaptability and accuracy of case investigation are significantly improved, so that the method can be widely applied to the technical field of data processing.

The invention discloses a meteorological science popularization work evaluation index system construction method. The method comprises the following steps: construction of an expert investigation method and an initial index library: adopting the expert investigation method to construct the initial index library; two-dimensional validity screening: introducing a consensus degree-concentration degree two-dimensional validity screening model, and establishing a two-dimensional screening matrix by calculating an average score M and a variable coefficient CV of each index; aHP-entropy weight method combined weighting: obtaining a subjective weight through an AHP analytic hierarchy process, obtaining an objective weight in combination with an entropy weight method, and then carrying out linear weighting combined weighting; nondimensionalization: performing annual data collection on the quantitative indexes, calculating quartile and range, and performing 10-score questionnaire and linear conversion on the qualitative indexes into 1-5 scores; a Pearson's correlation coefficient matrix is calculated through index correlation analysis, if the two indexes are highly correlated and reflect the same problem, one of the indexes is merged or deleted, and if different problems are reflected, the two indexes are reserved; and performing dynamic adjustment and case verification.

The invention provides a vulnerability information checking method, device, equipment and system. The method comprises the following steps: receiving a vulnerability checking request, wherein the vulnerability checking request is generated based on vulnerability intelligence information of an open source component acquired by a production side; according to information of a to-be-checked vulnerability in the vulnerability checking request, creating a checking task on a research and development side; and calling a software material security tool integrated on a research and development side to enable the software material security tool to retrieve a created software component dependency information base according to the troubleshooting task, and determining a code block influenced by the vulnerability to be troubleshot. Wherein an SBOM of a research and development state software project of a research and development side is stored in the software component dependency information base, and the SBOM is generated by calling the software material safety tool. Through the method, quick checking and positioning of vulnerability information are realized, and artificial missing report is avoided.

The invention relates to a social security case-oriented suspect investigation method and system, a processing device and a storage medium, and is characterized in that the method comprises the following steps: on the basis of a pre-established social security case suspect element feature index system and a matching degree calculation rule of the characteristics of a suspect and a harmer of a social security case, according to case information, calculating a matching degree of the suspect and the harmer of the social security case; determining the suspicion degree of each suspect; sorting the suspicion degree of each suspect, and further determining a suspicious target; the matching degree calculation rule of the characteristics of the suspect and the harmer of the social security case is established based on a pre-established social security case suspect element characteristic index system by adopting a fuzzy multi-criterion decision-making method, and the method can be widely applied to the scientific field of criminal investigation and criminal analysis.

The embodiment of the invention provides an appearance information generation method of a building investigation object, and a building investigation method and equipment. The appearance information generation method of the building investigation object comprises the following steps: obtaining investigation object information of at least one investigation object to be investigated in a building and influence factor information influencing the appearance of the investigation object; and determining appearance information of the at least one investigation object according to the investigation object information and the influence factor information. Therefore, the efficiency and the accuracy of generating the appearance information of the reconnaissance object can be improved, so that the building reconnaissance efficiency is improved, and the reconnaissance cost is saved.

The invention relates to the technical field of gas pipe network safety management, in particular to a standard knowledge-driven automatic gas hidden danger troubleshooting method. The method comprises the following steps: carrying out knowledge atomization processing on a fuel gas safety standard text, decomposing the fuel gas safety standard text into knowledge atoms which cannot be divided and mapping the knowledge atoms to a pre-established ontology category; the knowledge atoms are converted into machine-readable condition-action rules through rule templating; identifying scene objects from the multi-source data, extracting elements of the scene objects, and classifying the elements into a unified ontology system; a space-time cube coordinate system fusing time, space and semantic dimensions is constructed, and multi-dimensional alignment matching of scene elements and standard knowledge atoms is achieved; and automatically triggering a hidden danger checking task based on a matching result, generating a task list after multi-source cross validation, and assigning and executing the task list. According to the method, the computability and the dynamic recombination of the standard knowledge are realized, the automation degree and the judgment accuracy of hidden danger checking are improved, and the technical problem that multi-source data fusion and rule execution depend on manpower is effectively solved.

The application discloses a kind of based on knowledge graph's mine safety hidden danger intelligent investigation method and system, specifically related to knowledge graph and mine safety information technology field, for solving the problem that the existing hidden danger investigation method based on static knowledge graph cannot follow underground space topology dynamic change and lead to inaccurate reasoning.By obtaining the mine multi-source dynamic data containing sensor data and mining plan, analyzing and identifying the cooperative state change event representing space topology evolution, and comparing the dynamic event subgraph based on this with the static knowledge subgraph extracted from the preset knowledge graph to identify the conflict relationship, then combining the mining plan to verify and correct the conflict relationship to generate the space topology update relationship, finally updating the mine safety knowledge graph in real time according to the update relationship, and based on the updated graph, the safety hidden danger reasoning of real-time monitoring data is carried out, so as to realize the synchronization of knowledge graph and dynamic production environment and the accurate investigation of hidden danger.

Systems and methods for blockchain value transfers including receiving at the server a plurality of transaction requests, each transaction request including sending and receiving user account addresses on first and second blockchain networks, a transaction value in in-network tokens, and an API request, performing a balance check procedure on each transaction request including determining if the transaction value is greater than a permitted transaction amount of the sending user account address, and either refusing the transaction or adding the transaction to an aggregate transaction record. The permitted transaction is updated for the sending and receiving addresses to reflect the transaction and a transaction including calculating a net transaction amount is initiated.

The invention relates to the field of large language models, and discloses a character deep investigation method and system based on identity feature driving, equipment and a medium, and the method comprises the steps: carrying out the deep binding and dynamic matching of the nationality, occupation and other identity features of an investigation target with a specific investigation strategy; according to the method, the automatic matching of the investigation strategy can be performed based on the identity characteristics of the investigation target and the input investigation dimension, the defects of wide data source selection and single analysis dimension caused by the adoption of a single universal template in the prior art are overcome, the investigation scheme can be dynamically decided for figures with different identity types, the high-value information source can be more accurately achieved, and the research efficiency is improved. The correlation and accuracy of information acquisition are effectively improved, refinement and adaptive task arrangement based on identity features are realized, and the quality of an investigation report is greatly improved.

The invention relates to the field of contract review, in particular to a contract risk investigation method, system and device based on multi-agent collaboration and a medium, and the method comprises the steps: receiving and processing a contract file, converting the contract file into an analyzable format, and extracting contract text content; according to the features of the contract text content, automatically judging the contract risk type, and distributing the extracted text content to the intelligent agent of the corresponding risk type; wherein the intelligent agents comprise a semantic risk review intelligent agent, an element risk review intelligent agent and a table risk review intelligent agent; each agent carries out risk investigation on the distributed text content to generate a risk examination result; summarizing risk review results of the intelligent agents and displaying the risk review results to the user; and recording feedback of the user to the review result, and performing iterative optimization on each agent based on the feedback. And each agent carries out risk investigation on the distributed text content to generate a risk investigation result, so that comprehensive and accurate risk investigation on the contract text is realized.

Systems and methods of blockchain value transfer utilizing a smart contract system including processing transaction requests, performing a balance check procedure on each transaction request based on an aggregation of credits and debits, determining by the smart contract system a net transaction amount for each account address comprised by an aggregate transaction record, and executing the net transaction amount for each account address by transacting tokens to and from the account addresses and receiving account addresses included in the transaction requests upon reaching an execution condition.