Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

45results about How to "Realize advance prediction" patented technology

Vehicular access synergism anti-collision pre-warning system based on V2X

The invention discloses a vehicular access synergism anti-collision pre-warning system based on V2X. Aiming at judgment links of an anti-collision pre-warning decision in the beyond visual range of anintelligent connected vehicle, in combination with a V2X communication technology and an inertial navigation technology, an improved safe distance model is designed, and an anti-collision pre-warningsystem of the intelligent connected vehicle is constructed. A V2X communication module is mainly used for being responsible for data communication, including data broadcasting of the vehicle, detection of data of surrounding vehicles, and receiving of roadside end road traffic information; a positioning module comprises a GPS / BD sensor for obtaining position data of the vehicle, including the data of longitude and latitude, course angle, speed, elevation and the like; the sensors such as a posture data module, an accelerometer and a gyroscope are mainly used for obtaining posture data of thevehicle, including the data of vehicle acceleration, rotation angle and the like; and an inertial navigation module has the main functions of reducing a data cycle and improving the accuracy by usingan inertial navigation algorithm by utilizing the data of the sensors such as a GPS / BD module, the accelerometer and the gyroscope.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Electromobile battery protecting circuit

The invention discloses an electromobile battery protecting circuit which comprises a main circuit, a voltage detecting module, a battery loop current detecting module, a battery temperature detecting module, an electromobile inertia detecting module, an electromagnetic relay switch module and a singlechip control module, wherein the detecting modules are used for detecting the battery monomer voltage, the battery loop current and the battery temperature, transmitting signals to the singlechip control module, and analyzing the variation trend of the current, the voltage and the temperature. With the adoption of the circuit, the external voltage and current of an electromobile battery are detected and the the electromobile battery under abnormal states such as over-voltage, over-current, under-voltage and the like is cut off to be protected, the output features of the battery are predicated in advance, the charge abnormity of the battery is detected and protected, and furthermore, due to the inertia detection on an electromobile, a power supply circuit is cut off under the condition that the battery is in good condition when the electromobile has various faults, therefore, the the power supply circuit is prevented against battery combustion and explosion.
Owner:SOUTH CHINA UNIV OF TECH

Service system running state intelligent research and judgment system based on log, flow and service access

The invention discloses a service system running state intelligent research and judgment system based on logs, flow and service access, which reconstructs a comprehensive network management system technical architecture, and comprises the following steps of: constructing a distributed data storage platform by utilizing a plurality of databases; the kafka distributed deployment environment is utilized to realize unified collection and centralized pushing of data in the distributed data storage platform, and the data is sent to the comprehensive network management system; the comprehensive network management system constructs an application system port monitoring and physical storage monitoring system and a display system; and summarizing and integrating key service system operation logs, middleware operation logs and service process operation information according to the acquired data, and mining association relationships between different log modes and service system faults and low performance phenomena by utilizing a big data intelligent analysis method to form a key service system operation state intelligent research and judgment model. The method can effectively improve the guarantee capability of an information network and key services, and reduces the operation risk of a service system.
Owner:STATE GRID FUJIAN ELECTRIC POWER CO LTD

Management method and platform of virtualization system

The invention provides a management method and platform of a virtualization system. The method is applied to a cloud management platform of the virtualization system, and comprises the following steps: firstly monitoring at least two host nodes corresponding to the virtualization system through a monitor system in the cloud management platform to acquire the current state of each host node in at least two host nodes, and then determining the second host node is to be in a normal state from at least two host nodes when the monitor system predictively determines a fact that the first host node with the current state as the normal state in at least two host nodes is to be in abnormal state; and finally migrating at least one logic partition on the first host node to the second host node through a partition management system in the cloud management platform. Through the management method provided by the invention, the ahead prediction and migration of the possibly abnormal node can be realized, the service partition service interruption time is reduced, or the effect of not interrupting the service is achieved.
Owner:云宏信息科技股份有限公司

Hidden hazard management system and method of electric system

The invention discloses a hidden hazard management system and method of an electric system. The hidden hazard management system comprises a hidden hazard troubleshooting module, an alarming module anda rectifying module, wherein the hidden hazard troubleshooting module is used for utilizing running state information of the electric system to judge whether the electric system has hidden safety hazards or not; the alarming module is used for conducting alarming when the hidden hazard troubleshooting module judges that the electric system has the hidden safety hazards, and selecting a rectifyingscheme corresponding to the hidden safety hazards from a prestored rectifying scheme set. According to the hidden hazard management system and method of the electric system, by detecting the runningstate information of the electric system, whether the electric system has the hidden safety hazards or not is judged, and if yes, alarming can be conducted; meanwhile, the rectifying scheme corresponding to the hidden safety hazards is queried from the rectifying scheme set for user reference, advanced predicting of safety accidents is achieved, alarming is timely conducted to provide the corresponding rectifying scheme, it is ensured that a user can complete rectification timely aiming at the hidden safety hazards, the occurrence of the safety accidents is avoided, and the safety degree of the electric system is increased.
Owner:HANGZHOU KAIDA ELECTRIC POWER CONSTR +2

Heuristic routing method utilizing position information in shipborne adhoc network

InactiveCN102572998ASolve the problem of efficient data forwardingRealize advance predictionWireless communicationService modelGeographic site
The invention relates to a heuristic routing method utilizing position information in a shipborne adhoc network. The heuristic routing method is characterized by comprising three main modules, namely a geographical position based routing strategy, a topologic void crossing method and a topologic void prediction model, and two auxiliary modules, namely a geographical position service model and a wireless network constraint strategy. According to the heuristic routing method, the existence of the topologic void can be predicted in advance, and the topologic void can be crossed by a geographical information based heuristic algorithm, so that the core technical problem of high-efficiency data forwarding in the shipborne adhoc network is solved.
Owner:ZHEJIANG OCEAN UNIV

Power correction circuit anomaly detection method, system and circuit

The invention discloses a power correction circuit anomaly detection method, system and circuit. The method comprises the steps: collecting feedback loop voltage values, control loop voltage values and working currents outputted by multiple groups of power correction circuits and output voltages and output currents of a main power circuit; utilizing the output voltage and the output current corresponding to each group to obtain a plurality of groups of output power; averaging the multiple groups of output power to obtain average output power; when the average output power is smaller than a preset output power threshold value; if so, gradually judging whether the power outputted by the main power circuit and the voltage and current of the power correction circuit are in a normal range; whether the power correction circuit is abnormal due to device parameter drifting or not can be detected in advance, if the power correction circuit is abnormal, abnormal information can be reported as soon as possible, maintenance personnel are reminded to prepare for maintenance, early prediction of faults is achieved, it is ensured that a power source corresponding to the abnormal power correctioncircuit can be replaced in time, and problem diffusion is prevented.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Information processing method and mobile terminal

The embodiment of the invention discloses an information processing method and a mobile terminal. The mobile terminal comprises a data acquisition unit, a data processing unit and an operation unit, wherein the data acquisition unit is used for obtaining first signal strength data and auxiliary data of the mobile terminal and sending the first signal strength data and the auxiliary data to the data processing unit, wherein the auxiliary data comprises information of a position, where the mobile terminal is, and information of a base station, which the mobile terminal belongs to; the data processing unit is used for performing classified processing of the first signal strength data according to a preset classification manner so as to obtain a first class corresponding to the first signal strength data, inquiring pre-stored historical data corresponding to the first class based on the first class, and determining second signal strength data of the mobile terminal in a first time range based on the historical data; and the operation unit is used for correspondingly operating based on the second signal strength data determined by the data processing unit.
Owner:NUBIA TECHNOLOGY CO LTD

Coal mining accident prediction model determination and monitoring method, storage medium and electronic equipment

PendingCN108876009AReduce the incidence of accidents in coal minesImprove securityForecastingNeural architecturesCoal miningFeature set
The invention discloses a coal mining accident prediction model determination and monitoring method, a storage medium and electronic equipment. The method comprises the steps of analyzing acquired historical accident feature information to generat an accident feature set corresponding to a coal mining accident type, wherein the accident feature set comprises historical accident feature informationand accident feature value information; according to the accident feature value information and pre-stored feature word frequency threshold information, performing association analysis on the historical accident feature information to generate accident key factor information; analyzing the accident key factor information to generate key factor value information; according to the key factor valueinformation and a pre-stored association rule, performing association analysis on the accident key factor information to generate a key factor frequent item set; and according to the key factor frequent item set, generating an accident prediction mathematic model by using a BP neural network. According to the method, medium and equipment provided by the invention, through analyzing and performingassociation analysis on the historical accident feature information, the accident prediction mathematic model is generated, and the secure production of the coal mine is monitored in real time.
Owner:CHINA SHENHUA ENERGY CO LTD

Wafer transmission monitoring method and wafer transmission monitoring device

The invention relates to a wafer transmission monitoring method and a wafer transmission monitoring device. The wafer transmission monitoring method comprises the following steps of acquiring the transmission track data of a plurality of standard wafers; obtaining a reference distribution interval of the wafer transmission track offset according to the plurality of pieces of standard wafer transmission track data; acquiring the transmission track data of a plurality of wafers to be tested; acquiring a to-be-measured distribution interval of the wafer transmission track offset according to theplurality of pieces of to-be-measured wafer transmission track data; and judging whether the median of the to-be-detected distribution interval deviates from the median of the reference distribution interval, and if so, determining that the wafer transmission is abnormal. According to the invention, the method achieves the prediction of the severe wafer transmission fault is predicted in advance,and the severe abnormal transmission fault caused by the accumulation of small wafer transmission faults is avoided.
Owner:SHANGHAI GUONA SEMICON TECH CO LTD

Resource delivery data processing method and device, server, system and medium

The invention relates to a resource delivery data processing method and device, a server, a system and a medium. The method comprises the following steps: predicting a delivery result of a target resource according to features of the target resource to obtain a prediction result; monitoring the prediction result, and generating prediction information corresponding to the prediction result; and sending the prediction information to the resource delivery client, so that the resource delivery client displays the prediction information. Therefore, the predictability and interpretability of the delivery result are improved, and the resource delivery person can conveniently adjust the delivery plan in a targeted manner and make a reasonable resource delivery decision in time, so that the experience effect of the resource delivery person is improved.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD

Rolling bearing residual life prediction method based on LSTM and TDNN

The invention discloses a rolling bearing residual life prediction method based on LSTM and TDNN, and the method comprises the steps: (1) extracting the time domain features of an original vibration signal of a training bearing, forming a time domain feature set, and carrying out the minimum-maximum normalization processing of each feature; (2) constructing a health factor by using at least two nonlinear functions, then constructing a mapping relation between training features and the health factor and a mapping relation between the health factor and the residual life percentage by using LSTM and TDNN in sequence, and constructing an LSTM-TDNN residual life prediction model; and (3) inputting test bearing vibration data, after feature extraction and normalization processing, obtaining a residual life estimation value according to the LSTM-TDNN prediction model, and giving out comprehensive evaluation of prediction accuracy. The rolling bearing residual life prediction result is more accurate, unification of high precision and strong conservative is achieved, the method can be effectively applied to rolling prediction maintenance tasks, and the maintenance cost is reduced.
Owner:SHANDONG UNIV OF SCI & TECH

A Tool Life Prediction Method

The invention discloses a cutter service life predicting method. A spindle current signal of a machining machine table is collected through a current sensor, and the real-time current signal and the historical current signal are obtained; the feature value of the current signal is extracted through feature learning; current signal data cleaning is conducted according to the feature value of the current signal, and real-time input data and historical input data re obtained separately; the relation between the current signal and the service life of a cutter is analyzed through a machine learningand deep learning method, and after training is conducted with the historical input data serve as a training sample, a cutter service life prediction model is built; and the real-time input data serve as a test sample to be input into the cutter service life prediction model for testing, and a cutter service life prediction assessment result is obtained. By collecting the spindle current data ofa machine tool and the operation and historical data of machine tools of the same types, the cutter state is monitored in real time and the residual life of the cutter is predicted through a big dataanalysis platform, potential safety hazards in the production process are greatly reduced, and the rate of finished produced products is improved.
Owner:CHENGDU UNION BIG DATA TECH CO LTD

Aeration control device

The invention relates to the technical field of aquaculture oxygen aeration, and particularly discloses an oxygen aeration control device which comprises an electric control box. A power switch, an alternating-current contactor, a wiring terminal, a cell, a solar cell panel, an air temperature and humidity sensor and a controller are arranged on the electric control box, wherein the alternating-current contactor is used for controlling an oxygen aerator to be opened or closed, the wiring terminal is used for being connected with a power line, the solar cell panel is used for charging the cell, and the controller is arranged on the electric control box. The controller predicts a dissolved oxygen numerical value by processing a voltage value of the cell and air temperature and humidity values of the air temperature and humidity sensor and controls the alternating-current contactor according to the dissolved oxygen numerical value. According to the oxygen aeration control device, the dissolved oxygen numerical value can be predicted in advance, then, the oxygen aerator is controlled to be opened and closed according to the predicted result and the preset higher limiting value and the preset lower limiting value, the water dissolved oxygen value is not required to be directly detected, the hysteretic phenomenon of oxygen aeration can not occur, the oxygen aeration effect is good, the oxygen aeration efficiency is high, and the automation degree and the intelligentized degree are high.
Owner:CHINA AGRI UNIV

Method and device for processing dirty data in data exchange operation

The invention provides a method and a device for processing dirty data in data exchange operation. The method comprises the following steps: receiving dirty data information uploaded by any one or more working nodes in a working node set; adding the dirty data information into a dirty data sample set, wherein the dirty data sample set comprises the dirty data information received from the workingnode set; and analyzing the dirty data sample set to obtain a detection rule for a destination database, the detection rule being used for being issued to the working node set, so that the working nodes in the working node set predict dirty data information in the data information to be provided to the destination database according to the detection rule. By means of the technical scheme, the dirty data information can be rapidly checked, even if dirty data occurs, interruption of data exchange operation cannot be caused, continuous operation of data exchange operation of the working nodes canbe achieved, the dirty data processing efficiency in the data exchange process can be improved, and the data exchange operation efficiency is effectively improved.
Owner:HANGZHOU DT DREAM TECH

Well drilling overflow working condition identification method and device

The invention discloses a well drilling overflow working condition identification method and device. The method comprises the following steps: acquiring well drilling historical data; based on a wavelet transform algorithm, performing genetic algorithm training of overflow point thresholds on the drilling historical data to obtain a threshold of each kind of feature data; the threshold value is used for carrying out mutation point detection on the feature data; acquiring various characteristic data of the drilling well from the real-time logging data of the drilling well; performing wavelet transform processing on each kind of feature data, and extracting high-frequency signal features of each kind of feature data; according to the threshold value of each kind of feature data and the high-frequency signal features of each kind of feature data, overflow point identification is conducted on the multiple kinds of feature data of the drilling well. According to the invention, the efficiency and accuracy of drilling overflow condition identification can be improved; and meanwhile, the overflow working condition can be subjected to early prediction and early warning, and the drilling safety is improved.
Owner:BC P INC CHINA NAT PETROLEUM CORP +2

A system and method for predicting and controlling the forming quality of additively manufactured parts

The embodiment of the present invention discloses a system for predicting and controlling the forming quality of an additively manufactured part, including an additive manufacturing module, an image acquisition module, an image processing and feature extraction module, a prediction module and a process parameter adjustment module. The invention collects and processes images of molten pool, plume and spatter, and extracts various characteristic parameters of the three regions of molten pool, plume and spatter; uses LSTM network to predict the forming quality of the workpiece after n seconds; When the forming quality parameters of the predicted parts exceed the alarm value, adjust the process parameters in time and continue the subsequent processing; when the predicted forming quality parameters of the parts exceed the shutdown value, an alarm will be issued in time and the machine will be stopped, which improves the production of additive manufacturing parts. quality, reducing material loss. The embodiment of the present invention also discloses a method for predicting and controlling by using the above-mentioned system for predicting and controlling the forming quality of an additively manufactured part.
Owner:SHANTOU UNIV

Carrie rocket data prediction method and device, storage medium and electronic device

The invention discloses a method and a device for predicting data of a carrier rocket, a storage medium and an electronic device. The method comprises the following steps: step S101, determining a weighting coefficient vector K; 102, calculating a weighted prediction value set ZP_final based on that weight coefficient vector K; Step S103: based on the comparison result of the weighted prediction value set ZP_final and the actual value of the rocket test data corresponding thereto, all weighted prediction values in the weighted prediction value set ZP_final are outputted. The present application combines the AR model as a stochastic model with the regression analysis model as a deterministic model, and is applied to the prediction of rocket test data, so as to not only measure the influenceof a certain factor, but also predict the upcoming data according to the already tested data.
Owner:PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV

Point cloud model plant and analysis algorithm for identifying and early warning plant diseases and insect pests

The invention discloses a point cloud model plant and an analysis algorithm for identifying and early warning plant diseases and insect pests thereof, and relates to the technical field of agricultural prevention and control. The analysis algorithm comprises the following steps: performing closed culture on common pests in agricultural production at the present stage by taking mollusks, crustaceans, bees and aphids as basic experiment objects in a data laboratory, and performing control variable experiment research on temperature, humidity and illumination intensity of a culture environment; observing the survival rate change of the agricultural pests in different environment factors, and establishing an information table through a table. According to the method, an environmental factor three-dimensional database is constructed during a data experiment, and algorithm basic data is constructed by using a relationship between environmental factors and the survival rate of agricultural pests; and then, a predicted value is provided according to environmental factor data of the current year determined by fitting environmental factor data of previous years, so that advanced prediction of plant diseases and insect pests is realized.
Owner:太原市晋阳湖管理处

A TDNN-based precipitation forecasting method for grassland areas in northern China

The invention discloses a method for predicting rainfall in the grassland area of northern China based on TDNN. The method comprises steps: the input variables P (t-1), P (t-2), P (t-3) and output variables P (t) of the TDNN prediction model being determined; obtaining the training data and test data of TDNN prediction model; importing the training data into the TDNN prediction model, and trainingthe TDNN prediction model; the input variables of the test data being imported into the trained TDNN prediction model, the output results of the TDNN prediction model and the actual observed rainfallbeing compared, and the MAE and RMSE being calculated; comparing the training precision of MAE and RMSE of each TDNN prediction model; if MAE and RMSE are less than the expected precision, the training of TDNN prediction model being completed; otherwise, the model parameters being adjusted and retrained. The invention solves the technical problem that the prediction accuracy is not high due to the inability to accurately describe the time relationship between the inputs of the model in the conventional rainfall prediction model.
Owner:TIANJIN UNIV

Method and system for obtaining music beat information in real time

The present invention relates to the technical field of signal processing, and discloses a method and system for obtaining music tempo information in real time. The method includes: tracking and receiving music signals in real time, and performing discrete sampling on the music signals to obtain a sampling sequence; The sequence determines the historical path set of the beat starting point of the music signal prediction segment; predicts the beat period of the newly received music signal; determines the beat starting point of the subsequent music signal according to the historical path set of the beat starting point and the predicted beat period. The invention can realize real-time tracking and prediction of music signals, and provide accurate information for real-time operation of various beats.
Owner:HEFEI IFLYTEK TOYCLOUD TECH

A Calculation Method Applicable to Strip Temperature in Rapid Cooling Section of Continuous Annealing Unit

The invention discloses a calculation method suitable for the strip steel temperature in the fast cooling section of a continuous annealing unit, belongs to the technical field of continuous annealing, solves how to effectively avoid the measurement error caused by the temperature detected by a sensor, and realizes accurate prediction of the performance of the exit strip steel The problem, the steps include strip specific heat capacity c, strip mass m, strip temperature T when entering the fast cooling zone r , The comprehensive radiation coefficient C of the sample to the cooling wall L , the average temperature of the cooling gas T b , contact area S, furnace temperature T j , gas ejection velocity v, airflow spacing l, etc.; by accurately forecasting the strip outlet temperature in the fast cooling section of the continuous annealing unit, the quality of the finished strip can be predicted in advance. Forecasting can adjust and control the inlet temperature of the continuous annealing section and the furnace temperature in time to achieve the ideal strip steel outlet temperature, which ensures the high-speed production of the continuous annealing unit, improves the production efficiency, and increases the economic benefits of the enterprise.
Owner:BAOSTEEL ZHANJIANG IRON & STEEL CO LTD

Online model maintenance time point analysis method and device, equipment and medium

PendingCN113919526ASolve problems that cannot be predicted in advanceRealize advance predictionForecastingComplex mathematical operationsOnline modelResult set
The invention relates to an artificial intelligence technology, and discloses an online model maintenance time point analysis method, which comprises the steps of extracting a sample business set and a quality inspection label from a business database within the maintenance time of an online quality inspection model; performing quality detection on the sample business set by using an offline mirror image model of an online quality detection model to obtain a detection result set; comparing the quality inspection labels of the detection result set and the sample business set to obtain model accuracy; obtaining a model accuracy rate corresponding to each historical maintenance time in a historical time period, and fitting according to each model accuracy rate to obtain an accuracy rate regression curve; and calculating model prediction accuracy of the online quality inspection model at different time points by using the accuracy regression curve to obtain a maintenance time point. The invention further provides an online model maintenance time point analysis device, electronic equipment and a storage medium. The invention can accurately predict the necessary maintenance time of the online model.
Owner:PING AN BANK CO LTD

Heuristic routing method utilizing position information in shipborne adhoc network

The invention relates to a heuristic routing method utilizing position information in a shipborne adhoc network. The heuristic routing method is characterized by comprising three main modules, namely a geographical position based routing strategy, a topologic void crossing method and a topologic void prediction model, and two auxiliary modules, namely a geographical position service model and a wireless network constraint strategy. According to the heuristic routing method, the existence of the topologic void can be predicted in advance, and the topologic void can be crossed by a geographical information based heuristic algorithm, so that the core technical problem of high-efficiency data forwarding in the shipborne adhoc network is solved.
Owner:ZHEJIANG OCEAN UNIV

User complaint amount prediction method and device, computer equipment and storage medium

The invention relates to a user complaint amount prediction method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a website feature index corresponding to a to-be-predicted logistics website and index data corresponding to the website feature index; inputting the index data into a pre-trained complaint prediction model to determine a change trend of the index data through the complaint prediction model, and obtaining predicted index data corresponding to the index data according to the change trend, determining a predicted complaint amount and / or a predicted complaint rate of the logistics network according to the prediction index data; and obtaining the predicted complaint amount and / or the predicted complaint rate output by the complaint prediction model as the user complaint amount of the logistics network, thereby realizing advanced prediction of the customer complaint condition, and by using the index data of the corresponding characteristic index of the logistics network, being capable of fitting the business condition of the logistics network, and improving the user experience. And the prediction accuracy of the user complaint amount is improved.
Owner:SF TECH

Request response state determination method and device, equipment and storage medium

The embodiment of the invention discloses a request response state determination method and device, equipment and a storage medium. The method comprises the following steps: acquiring request information; performing vectorization processing on the request information, and determining a target feature vector sequence; inputting the target feature vector sequence into a predetermined target state prediction model, and determining the response state of the request information according to the output of the target state prediction model; the problem of difficulty in fault analysis and positioning is solved, the target state prediction model is trained in advance, the request information is vectorized to obtain the target feature vector sequence, the target feature vector sequence is input into the target state prediction model for response state prediction, and the response state of the request information is predicted in advance. The situation that the fault cannot be accurately positioned due to the fact that the number of transaction data is large after the fault occurs is avoided, the response state of each piece of request information is automatically predicted, the workload of workers is reduced, and the working efficiency and the system reliability are improved.
Owner:AGRICULTURAL BANK OF CHINA

Method and device for determining key monitoring pipe section of oil-gas pipeline

The invention discloses a method and device for determining a key monitoring pipe section of an oil and gas pipeline, and belongs to the technical field of risk evaluation of oil and gas pipelines. The area where the oil and gas pipeline is located is divided into the multiple local areas, then the population distribution data in each local area is obtained, the population number in each local area is determined, then the target local area and the corresponding key monitoring pipe section are determined, manual inspection and statistics do not need to be relied on any more, and the working efficiency is improved. Besides, according to the current population distribution data and the historical population distribution data, predicted population distribution data are obtained, then a predicted key monitoring pipe section is finally determined, the pipe section which may be the key monitoring pipe section in the future can be predicted in advance, advanced prediction of the key monitoringpipe section is achieved, and technicians can carry out early warning in advance conveniently.
Owner:PETROCHINA CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products