47 results about "Human decision" patented technology

An enterprise based workflow server based system to detect and classify images as potentially of pornographic nature. The system is based on two independent stages. The first stage is an automatic stage which eliminates most images that are positively non pornographic, including an image analysis engine with a plurality of sub engines, each dedicated to different attributes of an image. The second stage describes an additional embodiment of a manual review stage. An alternative embodiment describes a similar server solution to detect images suspected as copyrighted material. The images can be individually classified, or analyzed as a cluster or a collection of images such as an album or motion-picture segment, sampled into key still frames. The system optimizes time saving by elimination of images, and assures accuracy by generating a workflow reviewing solution which can involve a human decision-making stage.

A method to provide an insight to a decision maker to assist them in deciding how to perform a task includes: determining a time constraint in which the task needs to be performed; adjusting an accuracy of a computer program designed to calculate the insight to ensure that the insight is generated within the time constraint; scheduling execution of the computer program; and providing an insight output by the executed computer program to the decision maker.

Methods and apparatus for assessing operational process quality and risk of an entity or a group of entities. The present invention enables a user to effectively compare one or more events, representing what actually happened, with a reference, which represents ideal performance in terms of operational process quality and risk, and express the corresponding results in quantitative terms. The present invention is capable of presenting results in a form and with sufficient rapidity that a human decision-maker is able to timely observe conditions which represent unacceptable quality or excessive risk and respond appropriately.

A security system with a processor that receives information from multiple sources. The system is illustrated by a network of inspection machines at multiple locations in an airport, such as at check-in desks. These machines provide data to the processor for threat detection processing. The processor provides a central control and data integration point. Centralized control may be used to readily adapt threat detection programs and data integration may allow more accurate or more thorough threat determinations to be made. Moreover, centralized processing of computation intensive operations, such as image reconstruction, may provide for more efficient processor utilization throughout the system, providing a lower total processing cost. Additionally, centralized processing allows for human decision makers to be readily integrated into the system.

The invention discloses a cellular nerve network with genetic algorithm (GACNN)-based multisource image fusion method, belonging to the field of multisource mage fusion. According to the GACNN-based multisource image fusion method, the multisource image in the same scene can output fusion images with better effect by taking a CNN system as a framework and combining genetic algorithm self-adaptive computing network template parameters, thus facilitating the follow-up processing of image information, and providing more useful and more efficient information for the aspects of feature extraction, image recognition, human decision and the like; the accuracy of the fusion image can be effectively improved while the fusion result can be fast obtained, thus facilitating the observation of human eyes and machine detection, and being convenient for analysis and practical application.

A method for computer emulation of human decision making defines a plurality of concepts related to a domain and a plurality of situations related to the domain, where each situation is a combination of at least two of the concepts. Each concept and situation is represented in the computer as an oscillator output, and each situation and concept oscillator output is distinguishable from all other oscillator outputs. Information is input to the computer representative of detected concepts, and the computer compares the detected concepts with the stored situations to determine if a situation has occurred.

The present invention relates to information systems theories and expert systems theories. The present invention provides a process, apparatus and method for decision making, based on emulation of the human decision-making process using expert-generated primary bias values, wherein a primary bias value associates a particular alternative possibility of a possibility set with a particular query, and reflects the expert s conception of the relative degree of predictive value of the query for the particular alternative relative to other alternatives in the possibility set. In particular embodiments, the present invention provides a process, apparatus and method for providing a medical diagnosis or medical self-assessment.

The invention relates to a grouping method of leaf components of a tobacco leaf raw material. The method comprises the following steps: sampling a tobacco leaf raw material; preparing the sample of the tobacco leaf raw material; detecting aroma components in the tobacco leaf raw material, which is to detect marked intermediate product and marked end product transformed by carotenoid aroma precursor; cluster grouping; and leaf grouping. According to the method, the defects in the prior art, such as priority is given to human decision making experience, a reliable sense and chemical evaluation guiding basis is deficient, and more adverse influence of artificial subjective factors exist and the like, can be overcome. The sense characteristics of the leaf formulation module realizes effective complementation after pertinent treatment in each step, and sense deficiency accumulation is avoided, so that effective regulation and integration of the internal quality of the leaf formulation module is realized, the quality level of the processing process is further played, and the cigarette product quality is stabilized and improved.

An apparatus and method for distinguishing the correct type of fuel to be disposed in a vehicle (4) is provided. The apparatus includes an RFID tag (40) disposed on one of a vehicle (4) or a fuel providing means (2), and a radio receiving means (42) disposed on the other of the vehicle (4) or fuel providing means (2). A signal, indicative of a type of fuel, is emitted by the RFID tag (40) and compared with a predetermined radio signal stored in a storage means (41), and a warning is generated on the basis of a determination of correspondence between the detected radio signal and predetermined radio signal. The present invention therefore provides a safe and reliable system that removes or reduces human decision from a refuelling process, and ensures the correct fuel is provided to the vehicle (4).

A method and apparatus detect and localize electric faults in electrical power grids and circuit. High impedance faults are detected by analyzing data from remote sensor units deployed over the network using the algorithms of speech and speaker analysis software. This is accomplished by converting the voltage and/or current waveform readouts from the sensors into a digital form which is then transmitted to a computer located either near the sensors or at an operations center. The digitized data is converted by a dedicated software or software/hardware interface to a format accepted by a reliable and stable software solution, such as speech or speaker recognition software. The speech or speaker recognition software must be “trained” to recognize various signal patterns that either indicate or not the occurrence of a fault. The readout of the speech or speaker recognition software, if indicating a fault, is transmitted to a central processor and displayed to provide information on the most likely type of fault. Automatic or human decision is then implemented based on the generated information.

Computer systems and methods for training and/or testing a self-driving vehicle. The systems and methods, via in-car cameras and sensors, capture video of conditions surrounding the vehicle, driving data related to control of the vehicle, and driver behavior data representing actions by a human controlling the vehicle. The systems and methods analyze the captured video data and driving data to derive decisions a computer would make to control the vehicle. The systems and methods analyze the captured driver behavior data to determine decisions made by the human to control the vehicle. The systems and methods evaluate the derived computer decisions in comparison to the determined human decisions to detect data indicating discrepancies between the derived computer decisions and the determined human decisions for controlling the vehicle. The systems and methods provide the detected data as input to a model for training and/or testing a self-driving vehicle.

The invention discloses an automatic power generation control-based water pumping and energy storage unit automatic startup-shutdown control method. The control method comprises the following steps of(1) performing expansion of automatic power generation control system models, and adding a water pumping and energy storage unit basic control model; (2) setting the water pumping and energy storageunit basic control model; (3) calculating an automatic startup-shutdown control instruction, wherein the control instruction is a startup capacity value; and (4) performing safety verification on thestartup capacity value, and issuing the startup capacity value after verification is passed. By issuing remote signaling on the main station side, working condition conversion, comprising startup andshutdown, of the water pumping and energy storage unit can be realized, troublesome phone communication by a dispatcher can be avoided, and work pressure can be relieved; in addition, the backup and frequency control levels of the power grid and the day-ahead power generation plan arrangement and dispatcher human decision making can be taken into comprehensive consideration according to the operation condition of the power grid; and therefore, the number of startup and pump starting times and opportunity of a water pumping and energy storage power plant can be changed automatically, and the peak shaving and frequency modulating characteristics of the water pumping and energy storage power plant can be given into full play, thereby ensuring frequency operation safety of the power grid.

The invention relates to an evaluation and regulation method for the internal quality of a tobacco leaf formulation module. The method comprises the following steps: critical regulation for the internal quality of the leaf formulation module; sampling; sample production; sample preparation; sample rolling; smoking evaluation by sense; regulation effect evaluation for the internal quality of the leaf formulation module; chemical analysis to pertinent component addition effect and finished product cigarette internal quality; and further regulation and integration for the internal quality of the leaf formulation module. According to the method, the defects in the prior art, such as priority is given to human decision making experience, reliable sense and chemical evaluation guiding basis is deficient, and more adverse influence of artificial subjective factors exist and the like, can be overcome.

The invention discloses an SVM-RF-based decision rule extraction and reduction method, and belongs to the technical field of computer and information science. The method comprises the following stepsof training an SVM by using data to obtain a classifier and a support vector; generating new data characteristics by adopting a regeneration tree method, obtaining a new data label by using an SVM (support vector machine), and integrating the new data to obtain a most information amount of data set; training a random forest model by using the data set with the maximum information amount to obtaina plurality of decision-making trees; fusing the terminal node similarity and the decision tree performance similarity of the decision tree into new similarity by introducing a trade-off factor, and reducing the redundant decision tree based on the similarity; and finally obtaining a rule set by using a decision tree traversal method. The decision rule extraction and reduction method provided by the invention not only gives consideration to higher accuracy of the SVM-RF model, but also can avoid that the extracted decisions are too many and are not easy to understand by people, thereby helpingthe SVM-RF model to popularize in practical application and playing a role in assisting human decision making.

The invention discloses a method and device used for identification selection. The method used for identification selection includes the steps that identifications of at least two devices are obtained; the identifications of the devices are circularly traversed in a preset mode; when an end instruction is received, circular traversal is stopped immediately; the identification where the last time of traversal of circular traversal stops is determined; the identification where the last time of traversal stops is output. A sender of the end instruction cannot predict or interfere with a selected identification, and the selected identification is random and cannot be predicted. Meanwhile, subjective feeling and fun of human participation and human decision can be provided.

The invention discloses a behavior model generation method and system. The method comprises a step of providing a behavior model edition interface, wherein the edition interface comprises edition entries, and the edition entries comprise an atomic state edition entry, a state diagram drawing entry, a state transfer relation edition entry and a state nest relation edition entry. A behavior model generated through the method is used for simulating the human decision behaviors in simulation systems, completing behavior model edition through carrying out state synthesis and condition transfer on basic atomic states, and rehearsing the state transfer process in real time. The method is visual, simple and convenient to carry out model edition by non-technical personnel, for example, the military personnel that do not understand programing only need to combine atomic conditions during the edition of tactic behavior models. The method is popular, easy to understand and convenient to use, and the edition model can be conveniently provided to various simulation systems for calling.

The invention relates to a system for determining and adjusting human decision-making state psychology and behaviors, which comprises the following components: a questioning and answering module, a computation module, an assemble editing module, a classification module and a result module, wherein the computation module is directly associated with the questioning and answering module and the assemble editing module respectively; the assemble editing module is also associated with the classification module; and the result module is associated with a second module, a third module and a fourth module respectively to form an associated whole together. The system enables a user to obtain suggestions or cautions suitable for the psychological behaviors through a humanized design and a humanized using process, so the user obtains a psychological adjusting and obtains a good corresponding technical effect.

The invention relates to an oil well maximum yield mode control method based on the stroke ratio and a dynamic control diagram. A ground indicator diagram of an oil well is analyzed, the effective stroke of the oil well is calculated, the change condition of the stroke ratio is analyzed, under the premise that the pump efficiency is as high as possible, a pumping unit is maintained to run at the low frequency, that is, based on the principles of the high pump efficiency and low energy consumption, an intelligent optimization frequency conversion scheme of the oil well is designed, and a frequency conversion control strategy is corrected combined with evaluation results of the dynamic control diagram of the oil well, so that the oil well maintains a reasonable maximum yield model to produce. Under traditional frequency conversion control modes, frequency conversion control of a rod pumping well is still dominated by human decision-making, real-time adjustment of a pumping well is difficult to realize, according to a rod pumping well intelligent frequency conversion control method based on the indicator diagram stroke ratio and the oil well dynamic control diagram, the oil well is optimized and controlled in real time, the oil well is subjected to frequency conversion optimization control while the reservoir potentiality is exerted to the maximum limit, oil extraction energy consumption is lowered, the system efficiency is improved, and the purposes of cost lowering and efficiency improving of production of an oil field are achieved.