163results about How to "Improve case handling efficiency" patented technology

The invention relates to a monitoring alarm system of an internet bar based on the face recognition technology, which comprises a monitoring camera, a video signal processing module, a face recognition host and an alarm management server. The monitoring camera carries out face video image acquisition and transmits the acquired face video images to the video signal processing module for video image processing; the video signal processing module transmits the processed video signals and the face images to the face recognition host; the face recognition host carries out comparative recognition processing on the face images according to face database of a blacklist; and if the matching is successful, alarm messages are transmitted to the alarm management server for alarming by a computer network. By adopting the monitoring alarm system of the internet bar based on the face recognition technology, whether the persons to be found appear can be automatically judged and automatic alarming is carried out, therefore, the system is safe and fast, has stable and reliable working performance and wide application range, greatly improves the degree of monitoring intellectualization of the internet bar and can provide clues for the police to solve cases, thereby being beneficial to improving the efficiency of ministry of public security for solving cases.

The invention relates to a vehicle searching method and system based on user-defined features. The method includes the steps of firstly, extracting features of each vehicle in a vehicle image database shot by a monitoring camera and storing the features; secondly, searching for the vehicle, satisfying the user-defined features, in the vehicle image database shot by the monitoring camera and feeding back the searching result. The system comprises a vehicle image data reading device, a vehicle area positioning device, a vehicle feature extracting device, a vehicle feature storage device, a vehicle searching device and a searching result displaying device. According to the vehicle searching method and system, diversified searching methods can be provided, a user can search for the vehicle according to the user-defined features in the practical situation, the number of images which are manually confirmed by personnel who handling cases is greatly lowered, labor and materials are effectively saved, the case handling efficiency is greatly improved, and very good social benefits and economic benefits can be produced.

The invention discloses a recognition method and device for associated persons. The method comprises the steps of obtaining facial image features of persons to be recognized within the preset region around a target person, and recording the appearing time, position and frequency of the persons to be recognized within the preset region; according to the facial image features, time, position and frequency, generating feature identity identifiers of the persons to be recognized; judging whether the feature identity identifiers are related to the target person or not; when the feature identity identifiers are associated with the target person, judging whether the frequency of the feature identity identifiers is larger than a preset threshold or not; when the frequency in the feature identity identifiers is larger than a set threshold value, an alarm signal is generated for the feature identity identifiers. For the surroundings of the target person, the persons to be recognized around the target person are monitored, and the associated features of the target person and the persons to be recognized can be rapidly recognized, so that partners of the target person are rapidly tracked, and the case handling efficiency of public security organization is improved.

The invention relates to a system and a method for acquiring, recognizing and monitoring portraits in hotels, office buildings and recreation areas. The system mainly comprises a front end monitoring point and monitoring management centers at all levels, wherein the front end monitoring end is arranged in the hotels, the office buildings or the recreation areas and comprises an image acquisition device and a portrait acquisition comparing device for acquiring human face images, performing comparing recognition, and storing the acquired human face images and scene images, the results of the comparing recognition and other monitoring management information in a local database or transmitting the same to a higher level monitoring management center to accept the inquiry and the management by the higher level monitoring management center; the monitoring management is provided with the database, and can receive information of the front end monitoring point or a lower level monitoring management center, transmit monitor objects in an area under administration, receive and process an instruction of the higher level monitoring management center, and perform system management, service scheduling processing and portrait comparing recognition and inquiry of the area under administration. By adopting the system and the method, the intelligent degree of the prior monitoring system, and clues are provided for the public security department to solve a case.

The invention provides an operation method of an intelligent security monitoring system. The method comprises the following steps of cloud video analysis, an information center, an operation method center, chart-hanging battling, network monitoring, statistical analysis, function management and system access. Compared with the prior art, the operation method has the advantages of being convenientin operation, timely in information sharing, and high in practicality, and improving the case handling efficiency.

The invention provides a driver information and vehicle information verification method, a driver information and vehicle information verification device and a driver information and vehicle information verification system and relates to the technical field of person and vehicle verification. The method comprises the steps of determining a vehicle region image of a plurality of road traffic monitoring images; respectively carrying out human face identification, vehicle identification on the vehicle region image to obtain the driver face information and the vehicle information; respectively comparing the driver face information and the vehicle information with existing vehicle / driver database information to obtain driver verification information and vehicle verification information; and carrying out driver and vehicle information verification according to the driver verification information and the vehicle verification information, and inputting a driver and vehicle information verification result to a vehicle / driver database. According to the method, the vehicle information and the driver information can be associated through verification for the driver information and the vehicle information so that the vehicle / driver information database is more perfect, more comprehensive information is provided in the process of case investigation and the case handling efficiency of a policeman is improved.

The invention provides a patent agency internal management system. The patent internal management system comprises a data unit, and a background management unit and a user management unit connected with the data unit via networks; the background management unit is used for administrator inputting, editing personnel information, assigning permission of personnel accessing to the data unit, and checking and managing data of the patent agency; the data unit comprises a data storage module and a prompting module; the prompting module is used for prompting auditing personnel and flow personnel to audit and submit files and comprises a short message prompting module and / or a mail prompting module; and the user management unit is used for personnel login and operating modules of the data unit in the assigned permission. According to the panting agency internal management system, the business management capability of the patent agency can be enhanced, the patent agent flow is optimized, the case-handling efficiency is improved, and the patent agency service quality is improved.

The invention discloses a method and device for recognizing vehicle information, and the method comprises the steps: recognizing identification information of a photographed vehicle according to a vehicle travel record image; judging whether the photographed vehicle is a vehicle breaking the law or not according to the identification information of the photographed vehicle; and recording the travel information of the photographed vehicle if the photographed vehicle is the vehicle breaking the law. The method provided by the invention can effectively recognize whether the photographed vehicle is the vehicle breaking the law or not. When the photographed vehicle is the vehicle breaking the law, the method can transmit the useful information, which comprises the license plate number of the photographed vehicle and the time and place of meeting with a user vehicle, to a law enforcement department, thereby enabling the law enforcement department to quickly track the vehicle breaking the law according to the clue provided by the user, and improving the tracking efficiency of the vehicle breaking the law.

The invention provides a warning condition linkage management system for audio and video evidences of a law enforcement instrument, and the system employs a law enforcement recording device to collect the law enforcement data, and employs a central working station to enable the collected law enforcement data and the law enforcement recording device to carry out first correlated processing. The system comprises a server which is used for carrying out the second correlated processing of the read policemen data information in an alarm-receiving system and received first correlated information, and storing the obtained second correlated information. According to request information which is transmitted by a user, carries query conditions and is used for inquiring law enforcement data, the second correlated information corresponding to the request information is searched in a preset database, and is transmitted to a corresponding webpage for display. The system can enable the law enforcement data of all policemen in a law enforcement process to be correlated and stored, so a person with a corresponding preset authority can see the data, thereby enabling the confidentiality to be good. Moreover, a user can correspondingly obtain the law enforcement data in the law enforcement process according to the identity information of the user. The system is high in query speed and efficiency, and facilitates the improvement of case handling efficiency of policemen.

The invention provides a video processing method and system. The method comprises the steps of: extracting each motion target and motion track thereof from a video stream; for each motion target, determining video frames of each motion target during emergence and disappearance according to the motion track respectively; and searching the video frames between the video frame on motion target emergence and the video frame on motion target disappearance in the video stream, labeling the searched video frames and the video fames of the motion target during emergence and disappearance together to be a video sequence corresponding to the motion target. According to the invention, video data can be located more rapidly and accurately and are easier to look up and discriminate, and data search management is more convenient.

The invention relates to an integrated electronic record, signature and fingerprint system. The system comprises: (1) a police information resource database and a social information resource database for forming a sharable information resource database in a police intranet; (2) a comprehensive application platform based on police information; (3) an electronic fingerprint database constructed according to the requirement of standard fingerprint information collection of the ministry of public security and capable of being applied for special subjects; (4) a full text retrieval system; (5) a hybrid architecture using a C / S structure system, or a B / S structure or the combination of the C / S and B / S structure systems; (6) a unit adopting an MD5 algorithm for digital signature so as to ensure not to modify a generated record file, and a unit adopting Blowfish encryption algorithm for preventing leakage of the record data; and (7) a unit with integrated XML (extensible markup language) and WebService. The electronic record can greatly lower the case handling cost, improves the case handling efficiency, and can expand the information sources.

The invention belongs to the field of big-data processing, and provides a determination method and device of a crime name, computer equipment and a storage medium. The determination method of the crime name includes: obtaining to-be-determined crime fact text information; carrying out word segmentation processing and denoising processing on the crime fact text information; carrying out keyword extraction from the crime fact text information after word segmentation processing and denoising processing, wherein keywords are used to represent a crime fact; and bringing extracted keyword information into a conviction classifier to generate a crime name determination result for the to-be-determined crime fact, wherein the conviction classifier is obtained through training of a crime fact learning corpus. According to the method, the crime name can be intelligently determined, a process of conviction is simplified, efficiency of case handling is improved, an auxiliary effect is also providedfor case handling of legal professionals, and a guidance help is provided for related consultation of non-legal personnel.

The invention belongs to the technical field of signal and information processing, and relates to a digital-image evidence obtaining method for detecting camera sources of digital photo images. The method is characterized in that a CFA interpolation coefficient in an imaging process is estimated by utilizing a covariance matrix under the circumstance of only acquiring a digital image; an optimal feature is preferred by adopting an SFFS feature selection algorithm and is taken as the feature of classification detection; and through pre-trained models and parameters, the digital image with an unknown source is detected and the camera-source evidence of the digital image is obtained by using a support vector machine SVM as a classifier. The method has the advantages of accurately identifying the camera source of the digital image and obtaining evidence under the circumstance of only acquiring the digital image. The method is suitable for the field of information security.

The invention belongs to the field of data mining, and relates to an information interactive network-based criminal individual recognition method. The method comprises the following steps of: (1) obtaining a data set which comprises criminal activity contents, and pre-processing the data set; (2) extracting keyword descriptions of criminal topics; (3) determining the number of subjects of a subject model LDA on the basis of perplexity; (4) extracting interactive subjects between individuals in the pre-processed data set on the basis of LDA, wherein the interactive subjects are as follows: an association probability matrix of the interactive subjects and keywords, and an association probability matrix of interactive edges of the interactive subjects; (5) calculating weights of the interactive edges; (6) calculating local criminal suspects of the individuals on the basis of a structure of a weighted information interactive network; and (7) calculating global criminal suspects of the individuals on the basis of a fuzzy K-means cluster and distance density cluster combined method, and recognizing the criminal individuals. The method is independent of prior information, and can be used for analyzing the most possible suspected person according to communication contents so that the case handling efficiency is improved.

The invention discloses a community population security surveillance system and relates to the technical field of security and protection systems. The community population security surveillance system comprises a plurality of district security and protection nodes and a community central monitoring point respectively connected with the district security and protection nodes, wherein, the district security and protection nodes comprise district gate control nodes and cell gate access control systems, the cell gate access control systems and the district gate control nodes form a local area network, and each district gate control node comprises a switchboard receiving information of the access control systems, and a transceiver, an information reader-writer and a camera respectively connected with the switchboard. The system provided in the invention can monitor access situation of floating population in all the districts and discards the conventional management mode that considerable manpower and material resources are employed for extensive patrol, which enables manpower and material resources to be saved and targeted monitoring and arresting to be realized, thereby improving case handling efficiency.

The invention discloses a railway public security intelligent security system which specifically comprises an application layer, a data layer, a service layer and a sensing layer. Wherein the front-section acquisition information is realized through the perception layer, and the perception layer comprises a human face snapshot unit, a video snapshot unit, a human ticket gate, a mobile phone fencebase station, a certificate supplementing all-in-one machine and a dangerous article checking all-in-one machine. The face snapshot unit is responsible for collecting faces; The video snapshot unit isresponsible for collecting video information; The human ticket gate machine is responsible for collecting passenger identity cards and ticket information; The mobile phone fence base station is responsible for collecting mobile phone information of a station-crossing passenger; Wherein the identity information collection all-in-one machine is used for collecting identity information of people whoredo the identity card and comprises an identity card photo, a snapshot face photo and other information on the identity card; The checking and abandoning all-in-one machine is responsible for information collection of personnel carrying dangerous goods, namely identity card information collection.

The invention relates to a grid method for drawing a city map and an application thereof, which introduces a method for drawing the city map by the grid method. The method is characterized by increasing the information amount and functions of a grid map by tens of times through the function match of a series of assisted diagrams and also supplying a new space for the digital and intelligent management of a city. The map is drawn on the basis of a longitude and a latitude of the earth, but because the city area is even smaller than the surface area of the earth and an error generated by simulating and replacing the longitude and the latitude of the earth by a grid line is infinitesimal, the method is feasible. The method sets the area that 1km multiplies 1km is equal to 1km to be a grid basic unit, 100 basic units of 10*10 form a grid cell, the city map is drawn on the grid cell, a street, a community and a building of the city map are all relative with the basic units (grids), and each basic unit has regular and non-repeating name signs, thereby bringing convenience for searching and positioning each place name. In order to improve positioning accuracy, smaller grids, such as a subunit, an ultra-fine unit, and the like can be used as a calibration, and the accuracy can be improved within 10m, 100m, and the like. When the grid cell area of a big city is not enough, the grid cell expansion of grade 1, grade 2, and the like can be used, and orient expansion can be also adopted according to a city shape.

The invention relates to a handheld mobile terminal real-time online vehicle information fast query method and system which are achieved through two integration modes. A handheld background grid-connected mode comprises the steps of capturing license plate picture information, performing license plate picture local processing, uploading pictures to a vehicle information query system, inquiring license plate information relevant with text information and sending query results to a handheld terminal; the system in the handheld background grid-connected mode is composed of the handheld terminal, a background management computer (server) and a vehicle information query system (database), and the handheld terminal performs communication with the background management computer (server) and the vehicle information query system (database) through a wireless network. A handheld vehicle identity card mode comprises the steps of capturing license plate picture information, extracting vehicle identity card information, performing site comparison and confirmation of the vehicle identity card information and captured license plate number information, and displaying query results on the handheld terminal; the system in the handheld vehicle identity card mode is composed of the handheld terminal and a vehicle electronic indentity label, and the handheld terminal performs communication and data exchange with the vehicle electronic indentity label in a wireless transmission mode.

The invention provides a method for realizing quick alarming and quick alarming confirmation. The method comprises the following steps: user login is completed; authenticity of a user identity is verified; report information is uploaded by a user through a terminal, is saved at the server-side by the server-side, and is processed; and pictures of personnel, vehicles and articles are recognized and compared, and if the comparison is successful, the server-side sends out the automatic alarming prompt. According to the method, after the account number of the user is registered, login can be performed at any time and a picture or a video is uploaded, so that details of a case can be reported conveniently, and the identity of a criminal suspect is checked conveniently; hints are provided for people's police to handle the case; practical capabilities of collecting the hints are greatly promoted; the method facilitates the improvement of case handling efficiency of the people's police; and meanwhile, the efficient identity is registered and verified during alarming, so that the situations of false alarms are greatly reduced, and the factual basis is provided for the reporting and registering of the case and an incident.

The invention discloses a device for extracting mobile phone position information and marking the mobile phone position information on a map. An interface and a display module are arranged on the surface of the device. A partition mirror image module, an APP extraction module, a storage module, an analysis module and a map marking module are arranged in the device. The interface is connected with the partition mirror image module and the APP extraction module. The partition mirror image module is connected with the APP extraction module and then connected with the storage module. The analysis module is connected with the storage module and the map marking module. The map marking module is connected with the display module. The invention further discloses a method based on the device. The method comprises the steps that (1) the device is connected with a mobile phone and a connection channel is created; (2) data are scanned and extracted; (3) a position and a track are marked. A storage space of the mobile phone is completely scanned so that all the position information and time information can be extracted; according to the extracted position information and the extracted time information, the map is marked, the movement track of a criminal suspect can be rapidly known, and the case handling efficiency is greatly improved.

The invention provides a license plate deblurring method for video detection. The method comprises the following steps: S1, collecting a plurality of sets of license plate data combinations includingblurred license plate images and corresponding clear license plate images, and dividing the combinations into training data sets, verification data sets and test data sets; S2, collecting a pluralityof license plate data combinations including blurred license plate images and corresponding clear license plate images. S2, designing a generation countermeasure network model of de-motion blur, the generation network includes two convolution blocks of step size, seven inversion residual blocks of Mobilenet V2 and two transposed convolution blocks; 3, training that generated antagonism network, and put the data set obtained in the step S1 into the generated antagonism network model for training; S4, on the basis of the deblurring generation countermeasure network model trained in the step S3,the license plate image blurred by the motion is input, and the output data is the generated clear license plate image. The invention can realize the license plate clarity, so as to quickly determinethe identity of the suspect, effectively help the criminal investigator to solve the case as soon as possible, and the generation network composed of Inverted Residual Block of Mobilenet V2 can betterextract the high-dimensional features.

The invention discloses a method and system for determining a suspected vehicle involved in a case. The method comprises: vehicle passing data are obtained and a vehicle passing record table and a vehicle passing index table are generated based on the vehicle passing data; the vehicle passing data are analyzed to generate a record table of vehicles with fake license plates; a suspected vehicle involved in a case is determined based on the vehicle passing record table, the vehicle passing index table, and the record table of vehicles with fake license plates, wherein determination conditions for determination includes a time-space condition and at least one of the following conditions: a sun shield state, a stealing high-risk area, a suspected vehicle with a fake license plate, frequent vehicle passing, and initial city entrance; and according to the determination result, the vehicle passing data in a suspected vehicle set are ranked based on score values in a suspected score set in a descending order, so that an involved suspected vehicle sequence table is generated. According to the method and system disclosed by the invention, the integrated analysis is carried out based on multiple features of involved vehicles, so that lots of useless data are filtered and removed; and most possible vehicles top the list, so that crime solving feasibility is improved.

The invention discloses a digital court trial system of a people's court, comprising: at least one main exchange, and an on-site court trial system and a remote court trial system connected to the main exchange. The system makes synchronous audio and video recordings of the trial process, completely records the relevant personnel in the trial, video and audio recordings, electronic transcripts and other information, and manages the trial materials in an orderly manner, greatly improving the work efficiency of the judges, reducing labor intensity, and fully benefiting both parties. Embodying the principle of "justice and fairness", the upgrade cost of the system is not high, and it meets the actual needs of modern court trials, and the implementation effect is good.

The invention provides a grid method for drawing a city map and application of the grid method. The grid method for drawing the city map is characterized in that Yuan grids are designed through the grid technology, decimalism is determined, grid measurement units such as a grid cell, a basic unit and a subunit are created, wherein each basic unit represents the actual area of 1km*1km=1km<2>, and each basic unit is 100 times larger than a last-level basic unit; according to the technical feature of the earth meridians and parallels, the conclusion that the actual meridians and parallels of the city map are similar to grid lines of the Yuan grids is drawn according to the calculus theory, the city grid map is drawn based on the conclusion, and each information name on the map must obtain a unique regular grid code name; then auxiliary charts are developed, and therefore a larger amount of map information can be transferred to the auxiliary charts from map pictures. In this way, the contradiction between continuous increase of the information amount of a printing map and a limited area of the picture of the printing map can be solved, and due to the fact that the grid map and the digital technology are docked, it is predicted that the grid method for drawing the city map can provide support for municipal engineering, national defense and military and urban modern management.

The invention provides a drug detection device and detection method. The device comprises a shell, a collection module, a drug detection card and a drug detection module, wherein the collection module and the drug detection card are arranged on the outer part of the shell; the drug detection module is arranged in the shell; the collection module, the drug detection card and the drug detection module are connected in sequence; the drug detection module comprises a developing interpretation submodule and an intelligent control submodule, wherein the developing interpretation submodule is used for reading an optical signal detected on the drug detection card; the intelligent control submodule is connected with the developing interpretation submodule for processing the optical signal detected by the developing interpretation submodule to obtain a detection result. According to the device, the developing interpretation submodule is used for replacing human eye identification, a color distinguishing degree for a drug detection card developing result is improved, drug taking detection sensitivity is enhanced, a drug detection threshold value is lowered, and the case handling efficiency of law enforcement officers is improved.

The present application relates to a trial transcript data processing method and apparatus, a computer device and a storage medium. The method comprises: after creating a virtual trial room, receivinga trial attendance request sent by a terminal, and performing identity verification on the participant according to the identity information in the trial attendance request; after the verification ispassed, acquiring audio and video data uploaded by multiple terminals, and extracting voice feature information of the audio and video data; performing voiceprint recognition on the voice feature information by using a voiceprint recognition model to obtain a plurality of voice segments and corresponding voiceprint identifiers; and converting the voice segments into corresponding text transcriptinformation according to the voiceprint identifiers, performing semantic analysis on the text transcript information by using a semantic analysis model, and when there is an ambiguous text, correctingthe ambiguous text according to the analysis result, generating trial transcript information according to the corrected text transcript information, and transmitting the trial transcript informationto multiple terminals for displaying. By using the method provided by the present invention, the recognition accuracy of trial audio data can be effectively improved.

The invention discloses a big data-based accompanying vehicle analysis method and system. The method comprises the following steps: receiving and recognizing a passing vehicle picture by a picture recognition server, generating video structural data and sending the video structural data to a message server; storing the video structural data into a message queue by the message server; reading record information of the video structural data from the message queue by a consumer unit of the message server, and sending the video structural data to a column-oriented open source database; storing the video structural data into a first list and a second list of the open source database by the open source database; querying all the checkpoints, through which a target vehicle passes in a starting-ending time range through the second list according to a license plate number and a starting-ending time; combining all the checkpoints, through which the target vehicle passes and the starting-ending time, and querying all the vehicles which pass through the same checkpoints with the target vehicle through the first list; carrying out analysis to obtain accompanying vehicles of the target vehicle.

The invention discloses a case retrieval method and system, and the method comprises the steps: extracting case element information and an expression text in a case database, carrying out the clustering of a judicial dispute focus description text, and forming a dispute focus and an element label library; based on the dispute focus and the element label library, performing data corresponding labeling on the case file materials in the case database to form a case file dispute focus library; constructing and training a case language retrieval model according to the dispute focus and element label library and the case file dispute focus library; for case materials to be retrieved, determining conflict points in the case file materials through a topic conflict detection method based on case dispute focuses, and extracting dispute focuses matched with the case materials according to the conflict points; and providing a data retrieval service for a case material to be retrieved according tothe extracted dispute focus by utilizing the case language retrieval model. According to the invention, similar cases can be retrieved and pushed from the case dispute focus angle.

The invention discloses a method and a system for analyzing the first-time city entering behavior of a vehicle. The method comprises the steps of acquiring vehicle passing data, and generating a vehicle passing record table and a vehicle city-entering index table according to the vehicle passing data; segmenting the generation time range of a case into a plurality of time periods by adopting a time segmentation function, and transmitting the time periods to an original recording thread pool; calling the original recording thread pool to inquire a vehicle passing record list; according to the plurality of time periods, inquiring the vehicle passing record table in the starting and ending time corresponding to each time period; summarizing all inquiry results to obtain a suspected vehicle data set; segmenting the suspected vehicle data set into a plurality of data segments and transmitting the data segments into a backtracking check thread pool by adopting a record segmentation function;calling the backtracking check thread pool to inquire the vehicle city-entering index table through multiple threads; if the suspected vehicle information is not recorded in the vehicle city-enteringindex table, determining that a vehicle corresponding to the suspected vehicle information is driving into a city for the first time within the generation time range of the case; and merging all processing results to obtain a first-time city entering data set. According to the method and the system, vehicles, driving into the city for the first time, can be efficiently inquired.

This invention discloses a linkage displaying method of multiple monitor screens. The method comprises the steps of: acquiring current geographical location information and displaying the current geographical location information in a first display module; according to the current geographical location information, acquiring video monitoring information and displaying the video monitoring information in a second display module; and according to the current geographical location information, acquiring video playback information and displaying the video playback information in a third display module. This invention further discloses a linkage displaying system of multiple monitor screens. Compared with the prior art, the linkage displaying method and device realize the linkage display of multiple client interfaces based on the mixed framework of B / S (Browser / Server) and C / S (Client / Server); and thus, a user is unnecessary to frequently switch among several common clients when operating, and the use efficiency is effectively improved.