45results about How to "Enable real-time evaluation" patented technology

Disclosed are a recommendation method and server. In the method, recommendation lists sent by various recommendation systems are combined by using a preset combining policy, to obtain multiple recommendation models, or a system feeds back a recommendation result to a user, the combined recommendation list is updated according to a selection probability fed back by the user, to implement real-time estimation, a selection result periodically fed back by the user is received, and the combined recommendation list is updated, to reflect both a current interest and a historical interest of the user.

The invention provides a method and a device for online evaluation of a converter valve state based on grey clustering. The method comprises: acquiring online monitoring data of a converter valve in apreset time period; establishing a state evaluation indicator matrix of the converter valve according to online monitoring data, and calculating a score value of each evaluation parameter class in the state evaluation indicator matrix according to the online monitoring data; respectively constructing a whitening weight function corresponding to each preset gray class according to at least three preset grey classes; according to a preset weight value of each evaluation parameter class and the whitening weight function of the score value of each evaluation parameter class, using a grey clustering algorithm to respectively calculate a clustering weight value of each preset grey class; and evaluating an operating state of the converter valve according to the each clustering weight value. By implementing the method, real-time evaluation of the operating state of the converter valve is realized without manual operation, accuracy of an evaluation result is improved, and potential risk prediction of the converter valve is realized, and provides good data basis for planned maintenance of the converter valve.

The invention discloses a fire-fighting monitor fire extinguishment effect automatic monitoring and reburning prevention system and a method. The system comprises an information collection unit, a communication control unit, an information processing unit and a fire extinguishment execution unit. The information collection unit monitors a fire extinguishment area and transmits monitored information to the information processing unit through the communication control unit. The information processing unit processes image information, the fire-fighting monitor fire extinguishment effect is evaluated according to preset parameters, and instructions corresponding to the evaluation results are transmitted to the information collection unit and a fire extinguishment control unit correspondingly. If the judgment result indicates that a fire is not completely extinguished or can reburn, the image information is further analyzed, the position where the fire is not completely extinguished or can reburn is determined, the information and the position information are transmitted to the fire extinguishment control unit, and the fire extinguishment control unit controls fire-fighting monitor locating and carries out fire extinguishment. According to the fire-fighting monitor fire extinguishment effect automatic monitoring and reburning prevention system and the method, the fire-fighting monitor fire extinguishment effect can be monitored in real time, the fire extinguishment effect can be evaluated, and reburning is prevented from happening to the fire area.

The technical proposal of the invention discloses an importance evaluation method of industrial equipment data, which comprises the following steps: S1, collecting a sample data set of industrial equipment, recording the basic situation of the sample data set, and scoring the importance of the quality evaluation index of the data set to form a sample scoring data scoring table; S2, establishing avirtual scoring model based on sample data; 3, scoring the data set to be evaluated accord to the virtual scoring model; S4: based on the scoring results and combined with the data quality evaluationmodel, the data quality evaluation score of the data set to be evaluated being obtained. The technical proposal of the invention realizes the real-time evaluation of the importance of the industrial equipment data, avoids the situation that the entity experts need to be invited, and reduces the manpower cost, and the evaluation result is accurate and reliable.

The invention relates to an invoice data generation method and system based on a block chain technology and computer equipment. The method includes: when the invoice creation quota is greater than thecurrent remaining quota, sending an invoicing limit evaluation request to a node in an invoicing system block chain; enabling an invoicing limit evaluation node in the invoicing system to process operation data and historical invoicing data of an invoice issuer based on a clustering algorithm and an interval relationship between the operation data and an invoicing limit to obtain the invoicing quota update value, broadcasting the invoicing quota update value to each node in the invoicing system block chain, receiving the invoicing quota update value by the invoice creation node, and completing invoice creation according to invoice creation logic in the smart contract when the invoicing quota update value is smaller than or equal to the invoice creation quota. According to the process, theinvoicing amount of the invoice issuer can be evaluated in real time, invoicing is completed, a unified invoicing amount estimation scheme is provided for various platforms with different requirements to complete invoicing, and the invoice creation efficiency is improved.

The invention discloses a real-time evaluation method for economy of a large condensing steam turbine of a thermal power plant. The method is based on plant-level monitoring information systems configured for most thermal power plants. The method comprises the following steps: analyzing historical data of measurement points related to the economy of a steam turbine in an SIS database; by taking the state of a certain period with excellent performance in the historical operation period of the steam turbine as a reference, realizing the relative value of the current steam turbine economy compared with the reference state through data preprocessing and multi-round training by utilizing a deep belief network algorithm, so that the real-time evaluation of the steam turbine economy state is realized. The method depends on an SIS system, and is convenient to use and high in practicability, can help thermal power plant operators and equipment owners to master the performance state of the steamturbine in real time, can provide reference for overhaul time arrangement of the large condensing steam turbine, and explores a new direction for knowledge mining of mass data of the thermal power plant and state overhaul of related equipment.

The invention provides an enterprise credit risk identification method and device which can be used in the financial field or other fields. The identification method comprises the following steps: acquiring a target bank customer having a transaction with a bank enterprise customer and transaction data between the target bank customer and the bank enterprise customer; determining an association relationship between the bank enterprise customer and the target bank customer according to a pre-established knowledge graph, the knowledge graph comprising all bank customers and an association relationship between the bank customers; and carrying out credit risk identification on the transaction data of the target bank customer based on the association relationship. According to the method, the labor investment can be reduced, the risk conduction can be effectively reduced, the response time is shortened by timely alarming, and the detection efficiency is improved.

An actual navigation performance evaluation and improvement method based on numerical integration comprises the following specific steps: 1, constructing a navigation system position error distribution model; 2, performing integral calculation of binary normal distribution on the circular area by adopting an efficient approximation method; and 3, solving the radius of the circular domain under the specified probability by using a binary iteration method, thereby obtaining the evaluation of the ANP value of the aircraft. The invention aims to provide the actual navigation performance evaluation and improvement method based on numerical integration, a navigation system position error distribution model is constructed, an efficient binary normal distribution integral solving method is adopted for integral calculation under the deviation condition, an integral circular domain radius value under the specified probability is obtained according to a binary iteration method, and the integral circular domain radius value under the specified probability is obtained. And evaluation of actual navigation performance is realized.

The invention provides a ship power supply system electric energy quality on-line monitoring and evaluation device which is used for on-line monitoring and evaluation of a ship electric propulsion AC/DC power supply system. The device comprises surge current, current unbalance degree, pulse load, jump load, harmonic analysis, voltage deviation, voltage drop, transient voltage deviation, peak voltage, ripple voltage, relative value of voltage change, line voltage unbalance degree, frequency deviation, transient frequency deviation, transient frequency recovery time and frequency periodic change. The device has the functions of man-machine interaction, historical data query, waveform analysis recording and data communication, can adaptively correct the evaluation weight of the electric energy quality index, gives an electric energy quality comprehensive evaluation result in real time, has the minimum monitoring duration of 0.8 us for the electric energy quality characteristic parametersof the electric propulsion AC/DC power supply system, has the sampling precision reaching 2.498 mV, and the process from sampling to data analysis of 69 electrical measurement channels is completed within 50ms.

The invention discloses an electric power system transient stability evaluation method, which comprises the steps: building a to-be-tested electric power system by using electric power system time domain simulation software PSD-BPA; extracting a characteristic quantity capable of representing the state of an electric power system based on large amount of sample data, and performing normalization processing on characteristic data; completing the construction of a multi-radial basis function extreme learning machine integration model, wherein the output result of the integration model is the output after the prediction results of all sub-models are integrated; and after a fault occurs, inputting the acquired characteristic quantity of the electric power system at the steady-state moment andthe fault occurrence moment of the electric power system and after the fault removing into the trained multi-radial basis function extreme learning machine integration model, and predicting the transient stability of the electric power system. According to the method, the stability rules learned by different sub-models are utilized, so that important engineering application value is achieved for online transient stability evaluation of the electric power system on the premise that high evaluation accuracy is kept.

The invention discloses an intelligent terminal of a distribution transformer and a working method thereof, and belongs to the technical field of power equipment state detection. Theintelligent terminal comprises a multisensor signal integration module, a data processing and calculating module, an energy-taking power supply module and a communication module, the multisensor signal integration module and the energy-taking power supply module are respectively connected with a temperature sensor, a vibration sensor and a partial discharge sensor which are arranged in the distribution transformer, and the energy-taking power supply module is of a current induction type and is arranged in the distribution transformer; and the multisensor signal integration module is connected with the data processing and calculating module, and the data processing and calculating module is in communication interconnection with the upper computer through the communication module. According to the invention, timely processing of data can be ensured, data redundancy is avoided, real-time evaluation of the operation state of the transformer, fault early warning and life evaluation can be realized, the reliability and safety of the distribution transformer are improved, and the reliability and safety of the whole power supply network are further improved.

The invention provides an accounting collaborative performance rating assessment system, which comprises a detection device, an acquisition device, a processing device, an assessment device, a displaydevice and a processor, and is characterized in that the detection device is configured to detect accounting data and perform verification or entry based on verification of the accounting data; the acquisition device is configured to detect and monitor the operation and progress of an operator and access cache data of the accounting database; the processing device is configured to grade the dataamong the operators; the evaluation device is configured to acquire data of the processing device and respond to data verification; and the display device is configured to evaluate the evaluation result of the evaluation unit and update the evaluation data result in real time. According to the invention, the evaluation device is adopted to evaluate each operation, cooperative work can be carried out, real-time interaction between an operator and an evaluation rule is promoted, real-time evaluation is realized, and promotion suggestions are given in time.

The invention provides a quality evaluation method and evaluation system for new energy grid-connected data. According to the quality evaluation method, a reference data sequence matched with a presetlength data sequence before to-be-evaluated data is searched from reference sample sequences based on a vector matching method and a linear correlation method; and the quality mark of the next data of each reference data sequence is taken as a candidate quality mark of the to-be-evaluated data, and the candidate quality mark with the most same frequency is determined as the quality mark of the to-be-evaluated data. According to the method, quality evaluation is carried out on the new energy grid-connected data based on vector matching and linear correlation, real-time evaluation on the quality of different types of new energy out-of-disease data is achieved through the method, and the quality evaluation effect is good.