32results about How to "Decision support" patented technology

A method is for automatically indexing multimedia data archives and categorizing the files held therein and also to a client/server architecture in an image retrieval system for content-based searching for relevant files in a particular format and having a particular file structure. The parsed files stored in a data archive managed by the document management system are subjected to a feature extraction algorithm. The features obtained are then used for producing a binary-coded inverted index which includes elements of at least two attributes and holds context information which is held in these files and is needed for content-based image retrieval. If new files or files with an extended or modified content are stored in the data archive, then it involves a parsing algorithm and also an algorithm for automatically extracting features of these files being executed under event control during every storage process, in order to extend the inverted index by individual attributes or in order to update particular elements of already existing index attributes.

The invention is directed to a method of monitoring or detecting treatment-resistant clones in a patient being treated for a lymphoid or myeloid neoplasm from which patient-specific correlating clonotypes have been identified. In some embodiments, such method includes the steps of obtaining a sample from the patient comprising T-cells and/or B-cells; amplifying molecules of nucleic acid from the T-cells and/or B-cells of the sample, the molecules of nucleic acid comprising recombined DNA sequences from T-cell receptor genes or immunoglobulin genes; sequencing the amplified molecules of nucleic acid to form a clonotype profile; determining from the clonotype profile a level of each correlating clonotype and clonotypes clonally evolved therefrom; and correlating a presence of a treatment-resistant clone of the neoplasm with a change in relative levels of the correlating clonotypes and clonotypes clonally evolved therefrom. In part, the invention permits one to distinguish between cases where treatment is effective but insufficiently intense and cases where a cancer clone arises that is resistant to a current treatment approach.

A medical testing system and method is disclosed in which an Internet device is used to obtain test data from a patient automatically via sensor devices. The test program in the Internet device is downloaded from a web site via the Internet. After the test program has obtained the test data, the test data is uploaded to the web site server. At the server, the data is processed and the processed data is downloaded via the Internet to the patient's Internet device and/or to other Internet devices.

The invention discloses an intelligent management system for a tool based on a radio frequency technology. The intelligent management system comprises a hardware part and a system software part, wherein the hardware part comprises an RFID (Radio Frequency Identification Device) electronic tag, a fixed reader-writer, a handheld reader-writer, an application server, a WEB server and a database server; the RFID electronic tag carries out information exchange with the fixed reader-writer and the handheld reader-writer through radio frequency; information of the fixed reader-writer and information of the handheld reader-writer are transmitted to the application server, the WEB server is connected to the database server through a backbone network, and the application server is connected to the WEB server and the database server through network equipment. According to the intelligent management system, intelligent management of each link of the tool, such as warehouse in and out, maintenance, test and abandonment, can be normalized, the speed and the accuracy for data input of each link of warehouse management are guaranteed, the whole informatization management of the life cycle of the tool is implemented, the use safety of the tool is guaranteed, and the load of a worker is reduced.

The invention discloses a CT image-based nasopharyngeal carcinoma radiotherapy target region automatic sketching method, belongs to the technical field of medical image segmentation, and particularlyrelates to a convolutional neural network automatic segmentation method for a nasopharyngeal carcinoma target region in three-dimensional medical image segmentation. Aiming at the problems of a medical image segmentation method based on deep learning, the invention provides a multi-scale integration model based on combination of a 2.5-dimensional convolutional neural network and an attention mechanism. When a target area is segmented, the method has higher feature learning capability for large-spacing images, more attention is paid to a target segmentation area in the segmentation process so as to obtain a better segmentation effect, the segmentation precision is improved by integrating models under multiple scales, and segmentation result uncertainty evaluation is provided according to amodel integration result so as to better assist doctors in making decisions.

A computing system comprising a central processing unit (CPU), and memory coupled to the CPU and having stored therein instructions that, when executed by the computing system, cause the computing system to execute operations to generate a radiation treatment plan. The operations include accessing a minimum prescribed dose to be delivered into and across the target, determining a number of beams and directions of the beams, and determining a beam energy for each of the beams, wherein the number of beams, the directions of the beams, and the beam energy for each of the beams are determined such that the entire target receives the minimum prescribed dose. A quantitative time-dependent model-based charged particle pencil beam scanning optimization is then implemented for FLASH therapy.

The invention discloses a housing leasing platform based on a block chain. The platform comprises a government affair module, a housing resource management module, an appointment check-in module, a contract signing management module, a financial service module, a post-rental life module and a payment and bill module. The platform is combined with a government, a financial institution, a real estate broker company, a property institution and a community service institution, breaks through a government supervision platform, obtains real and real-time updated housing resource and property right information, is in butt joint with a financial institution business system, integrates house renting business flow and capital flow, and reduces financial risks. Finally, the targets of multi-party information sharing, data integration, real-time interaction, business collaboration, comprehensive supervision and the like are achieved. On the basis of the block chain technology, a housing leasing platform which is online in whole process, real, credible, dynamic, real-time, convenient and efficient is built, decision support is provided for government supervision, and healthy development of theleasing market is promoted.

The invention aims to provide a radio link-based disease follow-up system, which brings convenience to recording and counting. The system comprises a server storing patient information, a doctor handheld terminal for querying and inputting the patient information, and a patient query terminal only for query. The doctor handheld terminal comprises a wireless transmission module, an authentication module, a notice module and an information query and input module, wherein the doctor handheld terminal uploads and downloads the information by the wireless transmission module and the server; a user obtains rights of querying and inputting the patient information stored in the server by the authentication module; the notice module is used for displaying notices of the server after the login of the user; and the user performs query and input operations on the patient information stored in the server by the information query and input module. The radio link-based disease follow-up system is applied to all hospitals and centers for disease control.

The invention discloses a sandbox based two-dimensional code detection method. The sandbox based two-dimensional code detection method comprises the following steps of inputting a two-dimensional code to a simulation sandbox for running when a scanning tool is scanning the two-dimensional code; acquiring correlation behavior information of the two-dimensional code, and judging whether the correlation behavior information is possessed with a threat, if yes, giving out a threat level; monitoring the stability of the simulation sandbox in real time, and giving out an abnormal level if abnormality occurs; and comprehensively judging whether the two-dimensional code is malicious or not according to the thread level and the abnormal level, if yes, intercepting the two-dimensional code and generating a behavior report, otherwise allowing a terminal to open the two-dimensional code. The invention also discloses a sandbox based two-dimensional code detection system. With the technical scheme disclosed by the invention, the limitation of static detection can be made up, and a better detection effect can be achieved.

A system and method to support exploring the interior of an object. The system 100, 200 includes a graphical user interface generator (GG) to generate a graphical user interface (GUI). The graphical user interface (GUI) includes an indicator (NC) of a current position of an interventional tool (IT) inside an object (OB). There is also an exploratory indictor (PC) to indicate material composition and/or type that surrounds the tool's tip (TP) at a current position in the object (OB). The exploratory indicator (PC) includes a pointer element for a current reading against a dial element for a range of possible values.

The invention relates to a road traffic signal simulation system applied to a tramcar. The road traffic signal simulation system comprises an industrial computer and a tramcar track signal system OLC,wherein the industrial computer is connected with the tramcar track signal system OLC through a DIO board; a UI interaction module, a traffic flow simulation module and a road traffic signal controlsystem TSC are embedded into the industrial computer; the UI interaction module is connected with the tramcar track signal system OLC and the traffic flow simulation module respectively; the traffic flow simulation module is connected with the road traffic signal control system TSC. Compared with the prior art, the road traffic signal simulation system has the advantages that a real and reliable tramcar signal system simulation environment is provided, and the like.

Embodiments of the present invention provide an integrated solution to radiotherapy treatment planning that enables accurate recording and accumulation of physical parameters as input (e.g., dose, dose rate, irradiation time per voxel, etc.). User-defined functions are evaluated to correlate the input parameters with 4D biological outcomes. The resulting biological parameters can be visualized as a biological outcome map to evaluate decisions, support decisions, and optimize decisions regarding the parameters of the radiotherapy treatment plan, for example, for supporting clinical trials and related clinical research.

The invention discloses an FFM-based situation information classification recommendation system and method under a multi-task condition. The method comprises the following steps: establishing a Pew-based task processing model, analyzing current task state information, calculating task completion probabilities under different situation information recommendation strategies by utilizing an FFM model according to different attention degrees of different tasks on different situation information and considering state attributes of operators, and obtaining recommendation probability values of the situation information recommendation strategies; therefore, the situation information recommendation strategy with the highest recommendation probability value is selected as an information group for an operator to complete a task, the information group is intelligently displayed on an interaction interface, and the intelligence, interactivity and user satisfaction of a man-machine interaction system are improved.

An in-situ monitoring tool is provided that is compromised of a non-reactive medium, a reactive medium, or a combination thereof, contained in a water-permeable mesh. The tool is placed in an aquifer for a predetermined amount of time to allow the medium(s) to act as a substrate that collects minerals from the aquifer for analysis.

The invention discloses a logic deduction method based on index direction, and the method comprises the following steps: employing a graphic configuration tool, carrying out index definition and direction connecting in a deduction graphical region, and building the binding relation between an index and data; obtaining a binding data source through a data loading engine; carrying out the call of a filter through a condition configuration tool to screen the data bound with the index, and carrying out the preposed binding of a current index and a correlated index; carrying out the analysis and reading of the data of the index and the data of the correlated index through the call of a condition analysis engine, generating an index result, and displaying the index result to a client. The method finally achieves the visual and effective logic deduction among the indexes, completes an analysis target, assists the information analysis and decision making, and digs out the value of data.

The invention discloses an information generation method and device. The method comprises the steps: obtaining the behavior information of a user and the information of a target when determining to recommend the target to the user, and obtaining the behavior information of the user and the information of the target in each preset scene according to at least one of the current environment information, behavior information and target information of the user and the attribute information of each scene; determining a plurality of scenes as specified scenes, and generating and displaying recommendation information for recommending the target to the user through a generation template corresponding to the specified scene for each specified scene according to at least one of the environment information, the behavior information and the target information. As the recommendation information browsed by the user has the characteristics of user preferences and targets, compared with existing recommendation information, the recommendation information generated in the specification is more attractive to the user, and the user can be effectively assisted in making decisions.

The invention relates to new media content delivery, in particular to a new media content delivery method and equipment based on asset risk control. The method comprises the following steps: obtaining financial data, new media public opinion data and transaction data of an enterprise; the financial data and the transaction data are preprocessed, new media data are classified according to sources and event subjects, and an enterprise new media traffic matrix is constructed; the DBSCAN clustering algorithm is used to determine the influence of each element in the new media traffic matrix on the enterprise risk level and the enterprise revenue, so that the new media content, the enterprise financial data and the market value data can be integrated, and the possible risk and revenue level when the current enterprise faces the new media content can be more effectively determined; and constructing a planning problem based on enterprise content delivery requirements according to the influence weight matrix, solving to obtain an optimal feasible scheme, and implementing new media content delivery through a delivery module to achieve an asset risk control effect.

The invention discloses a weight quantification method for an electric vehicle charging decision, and belongs to the field of electric vehicles. The weight quantification method for the electric vehicle charging decision comprises the steps that 1, a city is abstracted into a road network layer and a power grid layer, and nodes, edges and weights in a road network and a power grid are defined; 2,defining a road network topology method and a power grid topology method; defining a road network weight and a power grid weight; and step 3, quantizing and feeding back the weight to the user. Compared with the prior art, the method can effectively assist the user in deciding and planning automobile charging, effectively guide charging load transfer, optimize the overall running state of a city,reduce the average weight of a network and effectively relieve charging congestion.