51 results about "Demarcation point" patented technology

The invention relates to a digital human live broadcast method and system. The method comprises the following steps: acquiring a live broadcast room visual effect picture and a digital human live broadcast audio; generating digital human live broadcast content under the driving of the digital human live broadcast audio by taking the visual effect picture of the live broadcast room as a visual manuscript through an I2V model; in the process of playing the digital human live broadcast content, if the current interaction behavior of the user in the live broadcast room is monitored, generating digital human interaction content responding to the current interaction behavior; selecting an insertion frame from the key frames of the digital human live broadcast content so as to insert the digital human interaction content at the position of the insertion frame; the key frame is a video frame corresponding to a statement demarcation point in the digital human live broadcast content. According to the scheme provided by the invention, the contradiction between long content production period, high implementation cost and slow real-time interaction feedback in digital human live broadcast in related technologies can be solved.

The invention relates to a real-time interaction method and system for digital human live broadcast, electronic equipment and a program product. The method comprises the following steps: in response to an interactive behavior of a user, generating a first digital human audio for responding to the interactive behavior, generating a first digital human video for responding to the interactive behavior according to the first digital human audio, selecting an insertion frame from key frames of digital human live broadcast content, inserting the first digital human audio and the first digital human video at the position of the insertion frame, wherein the key frame is a video frame corresponding to the statement demarcation point in the digital human live broadcast content. According to the scheme provided by the invention, the first digital human audio and the first digital human video responding to the interaction behavior of the user can be generated, and the first digital human audio and the first digital human video are inserted into the digital human live broadcast content, so that the interaction content of the user is responded in real time; and meanwhile, the first digital human audio and the first digital human video are inserted into the statement demarcation point of the digital human live broadcast content, so that the current verbal skill is not rigidly interrupted.

The application relates to a hybrid energy storage capacity multi-objective optimization configuration method for power fluctuation suppression, determines grid-connected unbalanced power, establishes an OVMD mathematical model, determines an optimal modal decomposition layer number K, decomposes the grid-connected unbalanced power signal, and determines high and low frequency reconstruction component orders and a demarcation point of connotation modal components in combination with superconducting magnet charging and discharging cycle time, determines low frequency power components and high frequency components, takes the minimum full life cycle cost of the hybrid energy storage system and the minimum operation penalty cost as targets, establishes a superconducting-electrochemical hybrid energy storage capacity multi-objective configuration model, obtains a Pareto front solution set of optimization target parameters, and obtains a superconducting-electrochemical hybrid energy storage optimal configuration scheme. The beneficial effects are that the influence of subjective K value setting on the decomposition layer number is reduced, the applicability of VMD is improved, the global search capability is enhanced, the population diversity is increased, the algorithm convergence is improved, and the uniformity of the optimal solution distribution of the Pareto front is improved.

The invention relates to the field of electric variable measurement, in particular to an ammeter relay life evaluation method and system, and the method comprises the steps: obtaining the current data of a relay under different historical loads, calculating the current distortion damage degree of different loads, and obtaining a current distortion damage sequence sorted according to the magnitude of load current; adjusting the current distortion damage sequence to obtain a load current-distortion damage degree curve, obtaining a preset threshold value of a load grade demarcation point, and further obtaining load damage amounts of different load grades; calculating the service life loss degree of the relay according to the load damage amount of different load grades; acquiring historical data of a plurality of relays to train a preset LSTM model, and optimizing model parameters through a preset loss function to obtain a life estimation model; and acquiring real-time data of the relay, and inputting the real-time data into the life prediction model to complete evaluation of the real-time residual life of the relay. The method has the effect of accurately evaluating the service life of the relay.

The application discloses a network coverage area boundary generation method and device, comprising: obtaining base station data of a plurality of base stations; obtaining a target attribute feature, and determining a target base station matched with the target attribute feature and a non-target base station not matched with the target attribute feature from the plurality of base stations; for each non-target base station within a preset range around the target base station, constructing an elliptical coverage area with the non-target base station and the target base station as the long axis endpoints of the ellipse and combining the antenna horizontal lobe angles of the non-target base station and the target base station, and if there is no other base station in the elliptical coverage area, determining the non-target base station as an external adjacent base station of the target base station; for each external adjacent base station, determining a coverage area demarcation point between the external adjacent base station and the target base station; and determining a coverage area boundary of the target base station based on a plurality of coverage area demarcation points. The application solves the technical problem of low accuracy and low efficiency of a conventional network boundary determination scheme based on field testing and manual drawing.

The embodiment of the present disclosure provides a generative antenna optimization design method based on a generative adversarial network, and belongs to the technical field of antenna design. Specifically, the method comprises the following steps: forming an initial data set by combining structure parameters and performance parameters; dividing the initial data set into two types of samples with a preset median of antenna performance indicators as a dividing point, and taking the superior class samples after normalization as a training set; constructing a generative adversarial network and training it by using the training set; forming a second data set by combining new structure parameters and new performance parameters, merging the superior class samples of the last time with the superior class samples of the current time, dividing again to obtain a new training set to train a new generative adversarial network; generating multiple new antenna models by using the new generative adversarial network and simulating until the requirements are met; and inputting random noise into the trained generative adversarial network to obtain the normalized value of the antenna structure parameters. Through the scheme of the present disclosure, the optimization efficiency and accuracy are improved.

The invention relates to the technical field of pattern design, in particular to a pattern design cooperation method and system based on a cloud platform, and the method comprises the steps: obtaining pattern arrangement distribution and spacing change, dividing rhythm sections, marking demarcation points, comparing drawing actions with region directions, arranging drawing instructions, and extracting canvas tracks. And generating an operation path list, dividing a terminal task range, binding a task channel and outputting a multi-terminal drawing set. According to the method, rhythm sections are divided by analyzing pattern spacing changes, drawing actions are ranked in combination with region directions and spatial features, canvas tracks are rearranged to reduce path round-trip and repeated operation, path sections are distributed according to terminal reaching regions to form an independent operation range, drawing tasks are sequentially bound to a cloud channel, continuous advancing of multi-terminal drawing is guaranteed, and the drawing efficiency is improved. Cooperative conflicts are reduced, and the process stability and the overall consistency of parallel composition are improved.

The application provides a time difference determination method, device and equipment of array acoustic wave and a storage medium. The method detects array acoustic wave through an array acoustic logging device located at a target depth, divides a full frequency band of the array acoustic wave into a frequency band of Stoneley wave and a frequency band of transverse-longitudinal wave according to a frequency demarcation point of the array acoustic wave, determines a Stoneley wave window length according to a first window cycle number of the Stoneley wave and the frequency band of the Stoneley wave, determines a transverse-longitudinal wave window length according to a second window cycle number of the transverse-longitudinal wave and the frequency band of the transverse-longitudinal wave, determines a time window length of a slowness time correlation algorithm based on the Stoneley wave window length and the transverse-longitudinal wave window length, and determines a time difference value of each component wave based on the algorithm and the time window length. The embodiments of the application can determine a corresponding time window length for the target depth, avoid the problems of complexity and inaccuracy of manual setting, and thus improve logging efficiency and logging accuracy.

Systems and methods for dynamic base station functional split configuration management are provided. In one embodiment, a system for base station functional split management for uplink fronthaul traffic comprises: a baseband controller coupled to a plurality of radio units via a fronthaul network, wherein the plurality of radio units comprise a signal zone from which uplink signals are combined by the base station: a split controller configured to dynamically select and control a functional split of a respective uplink receive chain between the baseband controller and each of the plurality of radio units: wherein the functional split defines a demarcation point on the receive chain prior to which processing operations are executed by a radio unit and after which processing operations are executed by the baseband controller: wherein the split controller selects between a plurality of functional split options to dynamically control the functional split and the demarcation point.

The invention relates to the technical field of railway transportation, in particular to a railway electronic map construction method, device and equipment. A railway electronic map construction method comprises the steps that target elements are constructed, the target elements comprise station yard nodes, demarcation points, main lines and connecting lines, the station yard nodes are used for representing stations or parking lots in a railway, the demarcation points are end points of the station yard nodes, the main lines are used for connecting different stations based on the demarcation points, and the connecting lines are used for connecting different stations based on the demarcation points; the connecting line is used for connecting a parking lot in the station based on the demarcation point, and the main line and the connecting line are directed line segments; based on the target element, a railway electronic map is constructed, the railway electronic map comprises a macroscopic view angle, a mesoscopic view angle and a microscopic view angle, the macroscopic view angle is used for representing an inter-station structure, the mesoscopic view angle is used for representing a station yard structure, and the microscopic view angle is used for representing an in-station structure.

The invention relates to a text display and voice broadcast synchronization method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring an original character string needing to be displayed on a current page of a client and / or an original character string already displayed on the current page of the client; punctuation marks in the original character string are filtered, and a pure character string corresponding to the original character string can be obtained; obtaining the word number of a read character string in the pure character string; then, according to the word number of the pure character string and the word number of the read character string, a broadcast demarcation point used for segmenting the read character string and an unread character string in the pure character string can be determined; and based on the document object model, positioning to the broadcast demarcation point in real time, and displaying the original character string corresponding to the broadcast demarcation point on the current page so as to realize synchronous display of character display and voice broadcast of the original character string.

This application provides a mobile-assisted video-synchronized curling training data acquisition method, relating to the field of data acquisition technology, including the following steps: when the coordinate distance between any two curling stones is detected to be less than a first preset threshold, extract the velocity vectors of the two curling stones within a preset time before the collision, mark the curling stone with the larger modulus as the source curling stone, and mark the curling stone with the smaller modulus as the collided stone; using the moment of the collision as the dividing point, split the coordinate sequence of the source curling stone into a first pre-collision coordinate subsequence and a first post-collision coordinate subsequence, and assign a first data stream identifier; split the coordinate sequence of the collided stone into a second pre-collision coordinate subsequence and a second post-collision coordinate subsequence, and assign a second data stream identifier; encapsulate the coordinate subsequence with the first data stream identifier and the coordinate subsequence with the second data stream identifier into a data packet, and push it to the mobile terminal.

The invention discloses an energy balance control method and device based on a hybrid MMC, and relates to the technical field of electric power. The method comprises the following steps: acquiring a reference voltage of a bridge arm, a half-bridge sub-module output capability of the bridge arm and a full-bridge sub-module output capability of the bridge arm; dividing the input state of the half-bridge sub-module into active input and passive input according to the reference voltage, the output capability of the half-bridge sub-module and the output capability of the full-bridge sub-module; based on the reference voltage of the bridge arm and the output capability of the full-bridge sub-module, determining a passive input demarcation point of the half-bridge sub-module, and determining the capacitance voltage variation when the half-bridge sub-module is passively input; controlling the half-bridge sub-modules to carry out minimum active input; and determining the input condition of the full-bridge sub-module according to the input condition of the half-bridge sub-module, and performing energy balance control based on the input condition of the half-bridge sub-module and the input condition of the full-bridge sub-module. The hybrid MMC-based energy balance control method is used for realizing the hybrid MMC-based energy balance control function.

The invention provides a time difference determination method, device and equipment for array sound waves and a storage medium, and the method comprises the steps: detecting the array sound waves through an array sound wave logging device located at the underground target depth, and dividing the full frequency band of the array sound waves into the frequency band of stoneley waves and the frequency band of transverse and longitudinal waves according to the frequency demarcation point of the array sound waves; determining the window length of the stoneley wave according to the first window period number of the stoneley wave and the frequency band of the stoneley wave, and determining the window length of the transverse longitudinal wave according to the second window period number of the transverse longitudinal wave and the frequency band of the transverse longitudinal wave; therefore, the time window length of the slowness time correlation algorithm can be determined based on the Stoneley wave window length and the transverse and longitudinal wave window length, and the time difference value of each component wave can be determined based on the algorithm and the time window length. According to the embodiment of the invention, the corresponding time window length can be determined for the target depth, and the problems of complexity and inaccuracy of manual setting are avoided, so that the logging efficiency and the logging precision can be improved.

This application discloses a method, device, equipment, and medium for handling stray current in subways. In this embodiment, the electronic device obtains the leakage current linear density distribution function and then determines the optimal boundary point sequence. The optimal boundary point sequence fully considers load balance and structural safety, realizing the dynamic optimal division of the drainage section of the intelligent drainage cabinet, improving resource allocation efficiency, and thus accurately and effectively completing the closed-loop suppression of stray current.

The invention relates to the technical field of power grid line loss analysis, in particular to a line loss analysis system and method based on a medium-voltage power distribution network, and the system comprises a power grid information collection module, a power supply data collection module, a regional power consumption analysis module, a real-time monitoring module, a front-end analysis module and a terminal early warning module. The method comprises the following steps: analyzing the power consumption of power consumption users in a regional distribution range to obtain the power consumption tenses of the power consumption users in each time period, arranging the power consumption tenses according to a time sequence to obtain a tense arrangement order, dividing the tense arrangement order into a plurality of configuration time periods according to demarcation points, and in a mean peak section of each configuration time period, obtaining a plurality of configuration time periods; and calculating the interval line loss coefficient, and judging the line loss state in the whole configuration time period end according to the interval line loss coefficient, so that the data calculation amount in the peak period, the power utilization safety risk of the user due to the abnormal line loss in the peak period and the power utilization influence of the user are reduced.

The embodiment of the application provides a customer classification method and device, relates to the field of data analysis, and can also be applied to the financial field. The method comprises the following steps: dividing a customer set into an online consumption customer set and an offline consumption customer set, and respectively determining consumption intervals, consumption frequencies and consumption amounts; respectively performing clustering, and determining the dividing points of the consumption intervals, the consumption frequencies and the consumption amounts of the online consumption customer set and the offline consumption customer set according to the clustering results; and respectively determining the value classification results of each customer in the online consumption customer set and the offline consumption customer set according to the dividing points and a value classification rule. The embodiment of the application considers the differences in customer consumption behaviors in multiple scenarios, adopts a differentiated RFM value calculation mode, constructs different models and uses a segmentation mode, and finally obtains individualized classification results.

The application discloses a method for extracting effective information of time parameters of railway signal relays, which comprises the following steps: arranging all time parameter sequences obtained through electric parameter experiments, and performing data preprocessing on the parameter sequences; decomposing the time parameter sequences obtained after data preprocessing into components capable of representing different information; performing autocorrelation function solving on all the components to obtain autocorrelation function images of the components, and determining signal-to-noise demarcation points according to the autocorrelation function images; performing wavelet threshold denoising processing on the components containing noise, and then reconstructing the processed IMF components, the IMF components not denoised and residual components to obtain parameter sequences after denoising, and extracting effective information of the parameters from the parameter sequences after denoising. The application can adaptively perform denoising on the time parameter sequences, and the improved wavelet threshold denoising method is used for denoising processing, so that the superiority of the method for denoising the time parameters of railway relays to extract effective information of the parameters is embodied.

The invention discloses a fan blade audio signal noise reduction method, system and device and a storage medium, and the method comprises the steps: carrying out the variational mode decomposition of a noise-containing audio signal of a fan blade, selecting a part of a mode function component as a to-be-processed signal, and taking the remaining part as a remaining amount; randomly arranging the to-be-processed signals, reconstructing the to-be-processed signals and the residual quantity to obtain temporary signals, accumulating, superposing and repeating the temporary signals for a preset number of times, averaging the accumulated and superposed signals to obtain an initial noise reduction signal as a new noisy signal, and repeating the above steps for a preset number of iterations to obtain a signal with an enhanced signal-to-noise ratio; performing variational mode decomposition on the signal after signal-to-noise ratio enhancement again, and sorting according to the energy scales of new mode function components from large to small; and searching a local minimum value point of the sorted new modal function component as a demarcation point, retaining a high-frequency signal component before the demarcation point, and reconstructing to obtain a fan blade audio denoising signal, thereby completing the noise reduction of the fan blade audio signal.

The application relates to a pre-terminated optical cable packaging disc which comprises a barrel, an inner layer cable winding part and an outer layer cable winding part, one end of the barrel is provided with a sealing plate, the inner layer cable winding part is installed in the middle of the sealing plate, one end of the outer layer cable winding part is installed on the sealing plate, the outer layer cable winding part is sleeved outside the inner layer cable winding part to separate the space between the barrel and the inner layer cable winding part into an inner layer cable storage area and an outer layer cable storage area, and the outer layer cable winding part is provided with a communication port which communicates the inner layer cable storage area and the outer layer cable storage area. The space of the barrel is separated into the inner layer cable storage area and the outer layer cable storage area through the outer layer cable winding part, the inner layer cable storage area and the outer layer cable storage area are communicated through the communication port, the length demarcation points of the inner and outer layers of the optical cable can be transitioned, winding is then respectively performed on the inner layer cable storage area and the outer layer cable storage area, and finally the terminated parts at both ends of the optical cable can be wound to the top layer of the packaging disc, so that the packaging of the pre-terminated optical cable with a linear diameter greater than 5 mm, a multi-core bundle structure or a branch optical cable, and a certain length of sub-cables scattered from the terminated parts at both ends can be achieved.

The invention provides a high-concurrency transaction message processing method, system and device and a medium, and relates to the technical field of distributed transaction processing, and the method comprises the steps: receiving a plurality of transaction messages for the same target commodity, determining the sequence relation of each transaction message, and generating a message dependency relation graph; when a state change event is detected, inserting a state demarcation point on the logic time axis; according to the message dependency graph and the state demarcation point, identifying a transaction message set needing atomic processing, and distributing the transaction message set to a plurality of message queues; and in each message queue, processing the transaction messages according to the sequence relationship, when the transaction messages cross the state demarcation point, executing state consistency verification on the transaction messages crossing the state demarcation point, and adjusting the processing sequence of the transaction messages according to the verification result. The method and the device have the technical effect of preventing partial messages from being processed based on the expired service state so as to cause service logic errors.

The present invention discloses a method, device, terminal device and storage medium for optimizing power load forecast results, wherein the method includes: when the abnormal standard empirical probability is not greater than the probability threshold, establishing a first environmental monitoring window at the time when the abnormality occurs, otherwise, starting to establish a second environmental monitoring time window at the start time of the time period; when the number of second environmental monitoring time windows meets the window number threshold, setting the dividing point at the end time of the current window to divide the time period; when the abnormal window ratio in the left time period is greater than the ratio threshold, setting a new second environmental monitoring time window at the end time of the current window, otherwise, establishing a new second environmental monitoring time window at the time when the data is abnormal in the right time period; comparing the predicted environmental parameters of the window with the actual environmental parameters, and performing environmental parameter compensation when the two are inconsistent. The present invention provides an optimization method for power load forecast results and improves the accuracy of the forecast results.

The invention relates to the technical field of material fatigue performance evaluation and structural integrity detection, in particular to a multi-stage fatigue crack propagation demarcation point identification and evaluation method and system, electronic equipment and a medium. Comprising the following steps: acquiring test data and constructing a curve, calculating a derivative by adopting a sliding window and identifying candidate demarcation points, and determining the demarcation points in combination with material behavior verification; the invention further discloses electronic equipment and a computer readable storage medium applying the method. The problems that in the prior art, a crack propagation stage division method depends on manual interpretation, the subjectivity of an identification result is high, and unified standards are lacked are solved.

The present invention discloses a wing design method, terminal device, and storage medium. The method constructs an XOY plane, obtains the coordinates of the wing boundary grid points, and sorts the grid point coordinates. The adjacency relationship between the grid points on the wing boundary is determined based on the sorting result, and the wing boundary is divided into n segments based on the adjacency relationship. The origin of the XOY plane is the leading edge of the wing, the positive x-axis is the direction from the leading edge to the trailing edge of the wing, and the direction perpendicular to the x-axis and pointing upward is the positive y-axis. A determination is made as to whether the n-segment cycle of the wing boundary has ended. If so, the cycle ends. Otherwise, a tridiagonal matrix is ​​constructed for each segment of the boundary curve. The type of boundary condition at the segment demarcation point is determined, and the boundary condition and the tridiagonal matrix are combined to calculate the expression of the wing curve for the i-th segment. The method effectively reduces the error between the calculated shape and the actual shape, thereby greatly improving the accuracy of the computational simulation.

The application discloses a kind of applied to the calibration method and circuit of pipeline successive approximation type ADC, by input signal and residual signal injection Dither signal, and using Dither_2 signal corresponding to the estimated value Dd2 of digital domain and the gain estimation value of residual signal VR' after injection is calibrated, gain value after calibration is obtained;Using gain value after calibration, digital code D1 and digital code D2 are spliced, to realize the calibration of interstage gain error, output the output signal to be mismatched calibration;The corresponding Dither signal is subtracted in digital domain to the output signal to be mismatched calibration, to find demarcation point, the maximum value of the interval before each demarcation point and the minimum value of the interval after each demarcation point are used to represent the weight mismatch information of the corresponding capacitor of demarcation point;To obtain corresponding error amount by using LMS algorithm to constantly iterate, realize the mismatch calibration of the output signal to be mismatched calibration, to improve the quantization accuracy and linearity of ADC.

The application discloses a multi-link intelligent tolling cross-region clearing method and system based on machine learning, and particularly relates to the field of cross-region networking tolling intelligent clearing, which comprises the following steps: sorting the tolling records corresponding to the same vehicle in the target account period according to the record time, mapping each tolling record to the corresponding charging position, generating a passing sequence, determining the passing interval between adjacent tolling records according to the passing sequence, setting a demarcation point at the intersection position of the passing interval and the region boundary, and cutting the passing sequence according to the demarcation point to generate a tolling responsibility section; the application solves the problems of cross-region revenue distortion and subsequent repeated back calculation caused by taking the whole passing as the minimum clearing object in the prior art by cutting the same passing into multiple tolling responsibility sections according to the region boundary, performing hierarchical discrimination based on the responsibility section characteristic value, and respectively entering the account according to the discrimination result.

The invention discloses a precision-variable Tanh activation function fitting method, which comprises the following steps of: dividing the positive axis input of a Tanh function into a linear region (0, 1.156) and a saturation region (1.156, + infinity) based on the characteristics of the Tanh function, and setting target absolute precision epsilon 0 to determine a demarcation point x0 of a linear function y = x and a trapezoidal function, y = x fitting is adopted in a linear region, it is ensured that the error does not exceed epsilon 0 through segmented iteration in a trapezoidal region, optimization constant tempset fitting is adopted in a saturation region, and negative semi-axis fitting or negative number rejection processing is achieved through the property of a Tanh odd function. By means of the mode, it can be guaranteed that the accuracy of the AI model is reduced within a certain range, hardware resources are greatly reduced, and the requirements for low-power-consumption, small-area and high-speed deployment of the neural network terminal are met.

The present application belongs to the field of automatic detection, and specifically discloses a kind of measurement method and device of rolling bar wire cutting waste size, method includes: obtaining the original image of bar wire cutting waste and pre-processing;The contour of pre-processing image is marked to generate corresponding binary label, and is divided into multiple image-label subgraphs of the same size;Image-label subgraph is divided into training data set and verification data set, and neural network model is trained and verified;The image of sample to be measured is pre-processed and input into the trained neural network model to output multiple segmentation subgraphs;Based on the position information of segmentation subgraph, the complete segmentation image of sample to be measured is obtained after merging segmentation subgraph;The minimum circumscribed rectangle of complete segmentation image is obtained, and the demarcation point of irregular section and regular section on sample to be measured is determined by means of minimum circumscribed rectangle, and the size of irregular section of sample to be measured is obtained based on demarcation point.The present application has higher detection accuracy.

The invention relates to a power distribution network fault rapid positioning method, device and equipment based on a distributed power supply. The method comprises the following steps: determining a plurality of active sub-regions in a dynamic topology model of a power distribution network by taking a distributed power supply grid-connected point and a main network contact node as demarcation points, and determining a target sub-region according to normalized electrical quantity data and transient electrical quantity data; determining a fault line segment according to the fault feature parameters of the target sub-region and a preset fusion positioning criterion; determining a fault local interval in the fault line segment according to the line parameters of the fault line segment and the transient electrical quantity data of the fault line segment; and determining a reference distance between the fault point and the target measurement node according to the transient electrical quantity data and the line parameters in the dynamic topology model, and determining the position of the fault point in the fault local interval according to the reference distance. The method adapts to a complex active scene after the distributed power supply is connected, and achieves the quick, accurate and reliable positioning of the fault of the power distribution network.

The application discloses a kind of power failure judging method and system, the present application includes using backtracking algorithm traversing all fault users in fault user list, generate the line fault range corresponding to different transformer station area;According to the fault judgment type of the line corresponding to the preset voltage grade line, the fault line in line fault range is judged, and the corresponding fault positioning information is generated according to the judgment result;Correlate fault positioning information with the fault user information in fault user list, generate fault management list data;According to the division of fault management list data in different jurisdiction, generate the corresponding work order and output.The technical problem that the existing technology needs rush repair personnel to verify the real range of fault, which leads to the technical problem that the work burden of rush repair personnel is increased.The application confirms the power grid fault type by using big data, and accurately confirms the fault boundary point, feeds back to the relevant staff and customers through work order information, reduces the complaints generated by customers because of power failure and needs to dial the phone to report trouble.