CN117557415A - Community resource management method and system based on intelligent property - Google Patents
Community resource management method and system based on intelligent property Download PDFInfo
- Publication number
- CN117557415A CN117557415A CN202311505855.5A CN202311505855A CN117557415A CN 117557415 A CN117557415 A CN 117557415A CN 202311505855 A CN202311505855 A CN 202311505855A CN 117557415 A CN117557415 A CN 117557415A
- Authority
- CN
- China
- Prior art keywords
- characteristic data
- real
- time
- data
- markov model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 32
- 230000007704 transition Effects 0.000 claims abstract description 133
- 239000011159 matrix material Substances 0.000 claims abstract description 104
- 238000012549 training Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000007476 Maximum Likelihood Methods 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000004044 response Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 13
- 230000006399 behavior Effects 0.000 description 8
- 238000010276 construction Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000004378 air conditioning Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
- G06Q50/163—Real estate management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2337—Non-hierarchical techniques using fuzzy logic, i.e. fuzzy clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B19/00—Alarms responsive to two or more different undesired or abnormal conditions, e.g. burglary and fire, abnormal temperature and abnormal rate of flow
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B27/00—Alarm systems in which the alarm condition is signalled from a central station to a plurality of substations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
Abstract
The invention relates to the technical field of community resource management, in particular to a community resource management method and system based on intelligent property, which calculate transition probabilities among states according to the modified historical characteristic data and generate a state transition matrix according to the transition probabilities among the states; constructing a Markov model, training the Markov model according to the state transition matrix, and outputting the trained Markov model; and importing the real-time characteristic data of each real-time characteristic data set into the trained Markov model for prediction deduction to obtain a prediction result. The data is processed by the advanced data processing technology, so that the data processing efficiency can be improved, the response speed of the system is improved, the reliability of the analyzed data is high, the prediction accuracy is improved, the remote intelligent analysis is realized, and the management cost is reduced.
Description
Technical Field
The invention relates to the technical field of community resource management, in particular to a community resource management method and system based on intelligent property.
Background
With the rapid development of smart property technologies and the increasing demands for community resource management, people are being prompted to pay attention to how to use the smart property technologies to improve the efficiency and convenience of community resource management. The community resource management method based on the intelligent property aims at integrating advanced technologies such as Internet of things, big data analysis and artificial intelligence, digitally managing various community resources, is particularly important for managing community elevators, and can intelligently analyze the running state of the elevator resources through remote monitoring of the community elevator resources so as to generate safety early warning and other functions in advance, thereby effectively protecting personal safety of community residents. The traditional community resource management has a plurality of problems, such as low data processing efficiency on the acquired community resources, and slow response speed of the early warning function; the processed data is low in reliability, the reliability of the prediction result is affected, and false alarm conditions often occur; the manpower is usually required for inspection and supervision, and the management cost is high. Therefore, research on community resource management methods based on smart property becomes a current hotspot and challenge.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a community resource management method and system based on intelligent property.
The technical scheme adopted by the invention for achieving the purpose is as follows:
the invention discloses a community resource management method based on intelligent property, which comprises the following steps:
acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and correcting the historical characteristic data to obtain corrected historical characteristic data of the target resource under various states;
calculating transition probabilities among the states according to the corrected historical characteristic data, and generating a state transition matrix according to the transition probabilities among the states; constructing a Markov model, training the Markov model according to the state transition matrix, and outputting the trained Markov model;
collecting real-time characteristic data of a target resource at a plurality of preset time nodes, and clustering the collected real-time characteristic data based on a fuzzy clustering algorithm to obtain a plurality of real-time characteristic data sets;
and importing the real-time characteristic data of each real-time characteristic data set into the trained Markov model for prediction deduction, obtaining a prediction result, generating alarm information according to the prediction result, and sending the alarm information to an intelligent property control terminal.
Further, in a preferred embodiment of the present invention, historical feature data corresponding to a target resource running under various states is obtained based on a big data network, and the historical feature data is corrected to obtain corrected historical feature data of the target resource under various states, specifically:
acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and carrying out standardized processing on the historical characteristic data so as to ensure that the historical characteristic data are on the same scale; wherein the status includes normal operation, partial failure, and complete failure;
a local outlier factor algorithm is introduced, the field size is determined through a cross verification mode, for each historical characteristic data, the mahalanobis distance between the historical characteristic data and other historical characteristic data is calculated, the calculated mahalanobis distances are arranged in an ascending order, and the distance of the kth mahalanobis distance nearest neighbor data is selected as a k distance;
for each historical characteristic data, calculating the maximum value of k distance between each historical characteristic data and each neighbor data as an reachable distance; the reachable distance is used for measuring the tightness degree between each historical characteristic data and the neighbor of each historical characteristic data;
For each data point, carrying out ratio processing on the reachable distance of the neighbor data and the reachable distance of the data point, so as to determine the outlier degree of the history feature data relative to the neighbor, and obtaining the local outlier factor value of the history feature data;
comparing the local outlier factor value of each historical characteristic data with a preset value; and if the local outlier factor value of certain historical characteristic data is larger than a preset value, screening the historical characteristic data to obtain corrected historical characteristic data.
Further, in a preferred embodiment of the present invention, transition probabilities between states are calculated according to the modified historical feature data, and a state transition matrix is generated according to the transition probabilities between states, specifically:
dividing the historical characteristic data of the target resource after being corrected under various states into different time periods to determine time intervals;
in each time interval, calculating the number of times of transferring the target resource from one state to another state, and obtaining the number of times of state transfer between different states; calculating transition probability between states according to the state transition times between different states;
constructing a state transition matrix, and filling the calculated transition probability into the state transition matrix; calculating the difference value between each transition probability in the state transition matrix, and generating a residual error according to the difference value between each transition probability;
Minimizing the sum of squares of the residuals based on a least square method to determine a fitness of the state transition matrix according to the minimized sum of squares of the residuals; judging whether the fitting degree of the state transition matrix meets the preset requirement, and if so, directly outputting the state transition matrix meeting the preset requirement;
if the preset requirement is not met, the transition probability among the states is recalculated, the state transition matrix is updated, and the state transition matrix meeting the preset requirement is output after the fitting degree of the state transition matrix meets the preset requirement.
Further, in a preferred embodiment of the present invention, a markov model is constructed, the markov model is trained according to the state transition matrix, and the trained markov model is output, which specifically includes:
performing feature vector decomposition on the state transition matrix to obtain feature vectors and corresponding feature values of the state transition matrix;
carrying out normalization processing on the feature vector of the state transition matrix to ensure that the sum of all elements is 1, and obtaining the steady-state distribution of the Markov chain; wherein, the steady-state distribution represents probability distribution of each state after the target resource passes a preset period;
Establishing a Markov model, initializing the initial node state of the Markov model according to the steady-state distribution of the Markov chain, and importing the state transition matrix into the Markov model; carrying out convolution processing on a state transition matrix imported into the Markov model, and acquiring convolution characteristics of the state transition matrix after the convolution processing;
defining initial training parameters of a Markov model according to the convolution characteristics and the initial node state, training the Markov model based on the initial training parameters until a training error convergence value is preset to a numerical value, and outputting model parameters;
calculating a log-likelihood function value of a Markov model according to the model parameters and combining a maximum likelihood estimation method, and if the log-likelihood function value is larger than a preset log-likelihood function value, indicating that the model parameters meet fitting requirements, and outputting the trained Markov model;
and if the log-likelihood function value is not greater than the preset log-likelihood function value, redefining initial training parameters of the Markov model, and continuing training the Markov model until the number-likelihood function value of the Markov model is greater than the preset log-likelihood function value, and outputting the trained Markov model.
Further, in a preferred embodiment of the present invention, the collected real-time feature data is clustered based on a fuzzy clustering algorithm to obtain a plurality of real-time feature data sets, which specifically includes:
determining the number of target resources, initializing a plurality of cluster clusters according to the number of target resources, and randomly generating an initial membership matrix according to the cluster clusters and the real-time characteristic data; wherein, the element in the initial membership matrix represents the membership degree of the real-time characteristic data belonging to a certain cluster, and the initial value is 0 or 1;
calculating a weighted average value of all real-time characteristic data in each cluster, so as to determine a fuzzy cluster center of each cluster according to the weighted average value; according to the fuzzy clustering center of each cluster, recalculating the membership degree of each real-time characteristic data belonging to each cluster in the cluster, and updating the initial membership degree matrix according to the calculated membership degree of each real-time characteristic data belonging to each cluster to obtain a membership degree matrix;
judging whether the difference between the membership matrix and the initial membership matrix is smaller than a preset threshold value; if the number of the membership degree matrixes is smaller than the threshold value, stopping iteration and outputting the final membership degree matrixes; if the number of the membership degree matrixes is not smaller than the preset threshold value, repeating the steps until the number of the membership degree matrixes is smaller than the threshold value, stopping iteration, and outputting the final membership degree matrixes;
Dividing each real-time characteristic data into a cluster with the highest membership degree according to the final membership degree matrix, outputting a clustering result, obtaining a plurality of initial real-time characteristic data sets according to the clustering result, and correcting the plurality of initial real-time characteristic data sets to obtain a plurality of real-time characteristic data sets.
Further, in a preferred embodiment of the present invention, the plurality of initial real-time feature data sets are modified to obtain a plurality of real-time feature data sets, which specifically includes:
acquiring real-time feature data in each initial real-time feature data set, introducing a Euclidean distance algorithm, and calculating Euclidean distances between the real-time feature data in each initial real-time feature data set and a fuzzy clustering center of the real-time feature data set through the Euclidean distance algorithm;
judging whether the Euclidean distance between the real-time feature data in the initial real-time feature data set and the fuzzy clustering center is larger than a preset Euclidean distance, if so, marking the real-time feature data as clustering abnormal data, and removing the clustering abnormal data in the corresponding initial real-time feature data set;
calculating Euclidean distance between the clustering abnormal data and the fuzzy clustering centers in the rest initial real-time characteristic data sets, and sequencing the Euclidean distance between the clustering abnormal data and the fuzzy clustering centers in the rest initial real-time characteristic data sets to obtain the minimum Euclidean distance;
If the minimum Euclidean distance is still larger than the preset Euclidean distance, the clustering abnormal data is indicated to be invalid data, and the clustering abnormal data is thoroughly screened out; if the minimum Euclidean distance is not greater than the preset Euclidean distance, clustering the clustering abnormal data again to an initial real-time characteristic data set corresponding to the minimum Euclidean distance;
repeating the steps until all the initial real-time feature data sets are corrected, and updating each initial real-time feature data set to obtain a plurality of real-time feature data sets.
Further, in a preferred embodiment of the present invention, the real-time feature data of each real-time feature data set is imported into the trained markov model to perform prediction deduction, so as to obtain a prediction result, generate alarm information according to the prediction result, and send the alarm information to an intelligent property control terminal, where the method specifically includes:
the real-time characteristic data of each real-time characteristic data set is imported into the trained Markov model for prediction deduction, and a prediction result is obtained;
obtaining state information of each target resource in a preset time period according to the prediction result, and obtaining the state information as position information of the target resource of the preset type of state information when the state information is the preset type of state information;
And generating alarm information based on the state information as the position information of the target resource of the preset type of state information, and sending the alarm information to the intelligent property control terminal.
The invention discloses a community resource management system based on intelligent property, which comprises a memory and a processor, wherein a community resource management method program is stored in the memory, and when the community resource management method program is executed by the processor, the following steps are realized:
acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and correcting the historical characteristic data to obtain corrected historical characteristic data of the target resource under various states;
calculating transition probabilities among the states according to the corrected historical characteristic data, and generating a state transition matrix according to the transition probabilities among the states; constructing a Markov model, training the Markov model according to the state transition matrix, and outputting the trained Markov model;
collecting real-time characteristic data of a target resource at a plurality of preset time nodes, and clustering the collected real-time characteristic data based on a fuzzy clustering algorithm to obtain a plurality of real-time characteristic data sets;
And importing the real-time characteristic data of each real-time characteristic data set into the trained Markov model for prediction deduction, obtaining a prediction result, generating alarm information according to the prediction result, and sending the alarm information to an intelligent property control terminal.
The invention solves the technical defects existing in the background technology, and has the following beneficial effects: calculating transition probabilities among the states according to the corrected historical characteristic data, and generating a state transition matrix according to the transition probabilities among the states; constructing a Markov model, training the Markov model according to the state transition matrix, and outputting the trained Markov model; collecting real-time characteristic data of a target resource at a plurality of preset time nodes, and clustering the collected real-time characteristic data based on a fuzzy clustering algorithm to obtain a plurality of real-time characteristic data sets; and importing the real-time characteristic data of each real-time characteristic data set into the trained Markov model for prediction deduction, obtaining a prediction result, generating alarm information according to the prediction result, and sending the alarm information to an intelligent property control terminal. The data is processed by the advanced data processing technology, so that the data processing efficiency can be improved, the response speed of the system is improved, the reliability of the analyzed data is high, the prediction accuracy is improved, the remote intelligent analysis is realized, and the management cost is reduced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a first method flow diagram of a community resource management method based on smart property;
FIG. 2 is a second method flow chart of a community resource management method based on smart property;
FIG. 3 is a third method flow chart of a community resource management method based on smart property;
FIG. 4 is a system block diagram of a community resource management system based on smart property.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the first aspect of the present invention discloses a community resource management method based on smart property, comprising the following steps:
s102: acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and correcting the historical characteristic data to obtain corrected historical characteristic data of the target resource under various states;
s104: calculating transition probabilities among the states according to the corrected historical characteristic data, and generating a state transition matrix according to the transition probabilities among the states; constructing a Markov model, training the Markov model according to the state transition matrix, and outputting the trained Markov model;
s106: collecting real-time characteristic data of a target resource at a plurality of preset time nodes, and clustering the collected real-time characteristic data based on a fuzzy clustering algorithm to obtain a plurality of real-time characteristic data sets;
S108: and importing the real-time characteristic data of each real-time characteristic data set into the trained Markov model for prediction deduction, obtaining a prediction result, generating alarm information according to the prediction result, and sending the alarm information to an intelligent property control terminal.
Further, in a preferred embodiment of the present invention, historical feature data corresponding to a target resource running under various states is obtained based on a big data network, and the historical feature data is corrected to obtain corrected historical feature data of the target resource under various states, specifically:
acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and carrying out standardized processing on the historical characteristic data so as to ensure that the historical characteristic data are on the same scale; wherein the status includes normal operation, partial failure, and complete failure;
a local outlier factor algorithm is introduced, the field size is determined through a cross verification mode, for each historical characteristic data, the mahalanobis distance between the historical characteristic data and other historical characteristic data is calculated, the calculated mahalanobis distances are arranged in an ascending order, and the distance of the kth mahalanobis distance nearest neighbor data is selected as a k distance;
For each historical characteristic data, calculating the maximum value of k distance between each historical characteristic data and each neighbor data as an reachable distance; the reachable distance is used for measuring the tightness degree between each historical characteristic data and the neighbor of each historical characteristic data;
for each data point, carrying out ratio processing on the reachable distance of the neighbor data and the reachable distance of the data point, so as to determine the outlier degree of the history feature data relative to the neighbor, and obtaining the local outlier factor value of the history feature data;
comparing the local outlier factor value of each historical characteristic data with a preset value; and if the local outlier factor value of certain historical characteristic data is larger than a preset value, screening the historical characteristic data to obtain corrected historical characteristic data.
It should be noted that, the target resource includes, but is not limited to, an elevator, and the characteristic data of the target resource under each state of normal operation, partial failure and complete failure is obtained, where the characteristic data includes specific time of failure occurrence, duration of failure, failure repair condition, operation speed, elevator operation time, load data, environment data and the like. And the retrieved historical characteristic data is screened through a local outlier factor algorithm to screen outlier data, so that the reliability of the data is improved.
As shown in fig. 2, in a further preferred embodiment of the present invention, transition probabilities between states are calculated according to the modified historical feature data, and a state transition matrix is generated according to the transition probabilities between states, specifically:
s202: dividing the historical characteristic data of the target resource after being corrected under various states into different time periods to determine time intervals;
s204: in each time interval, calculating the number of times of transferring the target resource from one state to another state, and obtaining the number of times of state transfer between different states; calculating transition probability between states according to the state transition times between different states;
s206: constructing a state transition matrix, and filling the calculated transition probability into the state transition matrix; calculating the difference value between each transition probability in the state transition matrix, and generating a residual error according to the difference value between each transition probability;
s208: minimizing the sum of squares of the residuals based on a least square method to determine a fitness of the state transition matrix according to the minimized sum of squares of the residuals; judging whether the fitting degree of the state transition matrix meets the preset requirement, and if so, directly outputting the state transition matrix meeting the preset requirement;
S210: if the preset requirement is not met, the transition probability among the states is recalculated, the state transition matrix is updated, and the state transition matrix meeting the preset requirement is output after the fitting degree of the state transition matrix meets the preset requirement.
It should be noted that, when acquiring the state transition matrix, it is first necessary to define a possible state space of the elevator, which includes various possible states of the elevator, such as normal operation, partial failure, complete failure, etc.; the historical feature data may be divided into different time periods, for example, the historical feature data may be divided by day, by week, or by month, in order to calculate transition probabilities between states. The number of transitions of the elevator from one state to another is calculated in each time interval, whereby the transition probability is obtained, e.g. the number of transitions from normal operation to partial failure, the number of transitions from partial failure to complete failure, etc. And calculating the fitting degree of the state transition matrix by a least square method to judge whether the state transition matrix meets the requirement, specifically, defining the fitting error of the state transition matrix, using residual errors to represent the difference between the observed value and the fitting value, for the state transition matrix, calculating the difference between each element to form the residual error, and obtaining the best fitting parameter by minimizing the square sum of the residual errors according to the least square method. The purpose of evaluating the state transition matrix by means of the degree of fit is to verify whether the matrix is able to accurately describe the state transition pattern in the observed data, the state transition matrix describing the probability of the system transitioning from one state to another, for which it is very important to evaluate the degree of fit of the state transition matrix, by comparing the differences between the actually observed state transition sequences and the sequences generated on the basis of the state transition matrix, the descriptive capacity of the state transition matrix can be quantified, and if the state transition matrix is able to accurately describe the observed state transition pattern, the degree of fit of the model will be high, whereas it will be low. The state transition matrix with high fitting degree can be obtained through the method, the state transition behavior of the system can be better understood, and the prediction and control capacity of the system behavior can be improved.
Further, in a preferred embodiment of the present invention, a markov model is constructed, the markov model is trained according to the state transition matrix, and the trained markov model is output, which specifically includes:
performing feature vector decomposition on the state transition matrix to obtain feature vectors and corresponding feature values of the state transition matrix;
carrying out normalization processing on the feature vector of the state transition matrix to ensure that the sum of all elements is 1, and obtaining the steady-state distribution of the Markov chain; wherein, the steady-state distribution represents probability distribution of each state after the target resource passes a preset period;
establishing a Markov model, initializing the initial node state of the Markov model according to the steady-state distribution of the Markov chain, and importing the state transition matrix into the Markov model; carrying out convolution processing on a state transition matrix imported into the Markov model, and acquiring convolution characteristics of the state transition matrix after the convolution processing;
defining initial training parameters of a Markov model according to the convolution characteristics and the initial node state, training the Markov model based on the initial training parameters until a training error convergence value is preset to a numerical value, and outputting model parameters;
Calculating a log-likelihood function value of a Markov model according to the model parameters and combining a maximum likelihood estimation method, and if the log-likelihood function value is larger than a preset log-likelihood function value, indicating that the model parameters meet fitting requirements, and outputting the trained Markov model;
and if the log-likelihood function value is not greater than the preset log-likelihood function value, redefining initial training parameters of the Markov model, and continuing training the Markov model until the number-likelihood function value of the Markov model is greater than the preset log-likelihood function value, and outputting the trained Markov model.
It should be noted that, a state transition matrix is constructed by collected historical characteristic data, and a markov model is established according to the state transition matrix, so that the state transition probability of the elevator failure is predicted by using the markov model. The state transition moment describes the probability of the elevator transferring between different states, and by calculating the eigenvectors of the state transition matrix, the steady-state distribution of the Markov chain can be obtained, wherein the steady-state distribution represents the long-term probability of each state, namely the probability of the elevator in the normal state, the partial fault state, the complete fault state and the like in a long time. And whether the Markov model meets the requirement in the training process is evaluated according to the maximum likelihood estimation, the fitting degree of the model on training data is evaluated by using the value of the log likelihood function, and in general, the larger the value of the log likelihood function is, the better the fitting degree of the model is indicated. The method can construct and obtain the Markov model with high reliability so as to improve the prediction accuracy and avoid the occurrence of the early warning condition.
Further, in a preferred embodiment of the present invention, the collected real-time feature data is clustered based on a fuzzy clustering algorithm to obtain a plurality of real-time feature data sets, which specifically includes:
determining the number of target resources, initializing a plurality of cluster clusters according to the number of target resources, and randomly generating an initial membership matrix according to the cluster clusters and the real-time characteristic data; wherein, the element in the initial membership matrix represents the membership degree of the real-time characteristic data belonging to a certain cluster, and the initial value is 0 or 1;
calculating a weighted average value of all real-time characteristic data in each cluster, so as to determine a fuzzy cluster center of each cluster according to the weighted average value; according to the fuzzy clustering center of each cluster, recalculating the membership degree of each real-time characteristic data belonging to each cluster in the cluster, and updating the initial membership degree matrix according to the calculated membership degree of each real-time characteristic data belonging to each cluster to obtain a membership degree matrix;
judging whether the difference between the membership matrix and the initial membership matrix is smaller than a preset threshold value; if the number of the membership degree matrixes is smaller than the threshold value, stopping iteration and outputting the final membership degree matrixes; if the number of the membership degree matrixes is not smaller than the preset threshold value, repeating the steps until the number of the membership degree matrixes is smaller than the threshold value, stopping iteration, and outputting the final membership degree matrixes;
Dividing each real-time characteristic data into a cluster with the highest membership degree according to the final membership degree matrix, outputting a clustering result, obtaining a plurality of initial real-time characteristic data sets according to the clustering result, and correcting the plurality of initial real-time characteristic data sets to obtain a plurality of real-time characteristic data sets.
The target number of resources is the number of elevators to be managed. The fuzzy clustering algorithm is a clustering method based on a fuzzy theory, and can divide data points into a plurality of fuzzy clustering clusters, and the acquired real-time characteristic data can be distinguished by the step to distinguish which data belongs to which elevator.
Further, in a preferred embodiment of the present invention, the plurality of initial real-time feature data sets are modified to obtain a plurality of real-time feature data sets, which specifically includes:
acquiring real-time feature data in each initial real-time feature data set, introducing a Euclidean distance algorithm, and calculating Euclidean distances between the real-time feature data in each initial real-time feature data set and a fuzzy clustering center of the real-time feature data set through the Euclidean distance algorithm;
Judging whether the Euclidean distance between the real-time feature data in the initial real-time feature data set and the fuzzy clustering center is larger than a preset Euclidean distance, if so, marking the real-time feature data as clustering abnormal data, and removing the clustering abnormal data in the corresponding initial real-time feature data set;
calculating Euclidean distance between the clustering abnormal data and the fuzzy clustering centers in the rest initial real-time characteristic data sets, and sequencing the Euclidean distance between the clustering abnormal data and the fuzzy clustering centers in the rest initial real-time characteristic data sets to obtain the minimum Euclidean distance;
if the minimum Euclidean distance is still larger than the preset Euclidean distance, the clustering abnormal data is indicated to be invalid data, and the clustering abnormal data is thoroughly screened out; if the minimum Euclidean distance is not greater than the preset Euclidean distance, clustering the clustering abnormal data again to an initial real-time characteristic data set corresponding to the minimum Euclidean distance;
repeating the steps until all the initial real-time feature data sets are corrected, and updating each initial real-time feature data set to obtain a plurality of real-time feature data sets.
In the clustering process of the data through the fuzzy clustering algorithm, the clustering error phenomenon is unavoidable because of huge data quantity, for example, the running speed data belonging to one elevator is clustered to the running data of the other elevator, and the data with the clustering error can be corrected by the method so as to make up the shortages of the fuzzy clustering algorithm, improve the data clustering accuracy and further improve the prediction accuracy.
As shown in fig. 3, in a further preferred embodiment of the present invention, the real-time feature data of each real-time feature data set is imported into the trained markov model to perform prediction deduction, so as to obtain a prediction result, and alarm information is generated according to the prediction result and sent to an intelligent property control terminal, specifically:
s302: the real-time characteristic data of each real-time characteristic data set is imported into the trained Markov model for prediction deduction, and a prediction result is obtained;
s304: obtaining state information of each target resource in a preset time period according to the prediction result, and obtaining the state information as position information of the target resource of the preset type of state information when the state information is the preset type of state information;
s306: and generating alarm information based on the state information as the position information of the target resource of the preset type of state information, and sending the alarm information to the intelligent property control terminal.
The real-time characteristic data in each real-time characteristic data set represents the characteristic data of the elevator at the corresponding position, and the real-time characteristic data in each real-time characteristic data set are sequentially imported into a trained Markov model for prediction and deduction to obtain a prediction result; the preset type state information is a fault state, which indicates that the elevator has extremely high probability of fault in a short time in the future, at the moment, alarm information is generated for the position information of the target resource of the preset type state information based on the state information, the alarm information is sent to the intelligent property control terminal, and then the intelligent property control terminal controls the alarm on the elevator at the corresponding position to give an alarm so as to remind a person to leave the elevator as soon as possible or remind the person to avoid taking the elevator, thereby improving personal safety and avoiding safety accidents.
In addition, in the step before the plurality of preset time nodes collect the real-time characteristic data of the target resource, the method further comprises the following steps:
acquiring a construction engineering three-dimensional model diagram of a community, acquiring position information of each target resource to be acquired and position information of a cloud platform, and marking the position information of each target resource to be acquired and the position information of the cloud platform in the construction engineering three-dimensional model diagram;
based on a ray tracing method, planning various signal acquisition channel schemes between each target resource to be acquired and a cloud platform according to the construction engineering three-dimensional model diagram; acquiring signal intersection nodes of all signal acquisition channel schemes;
acquiring node position information of each signal intersection node, searching a preset range area of each signal intersection node according to the node position information in a construction engineering three-dimensional model diagram to judge whether strong electric facilities exist in the preset range area of each signal intersection node, and eliminating corresponding signal acquisition channel schemes to obtain residual signal acquisition channel schemes if the strong electric facilities exist;
acquiring signal-to-noise ratios of signal acquisition channels in a residual signal acquisition channel scheme, constructing a ranking table, and ranking the signal-to-noise ratios of the signal acquisition channels in the residual signal acquisition channel scheme through the ranking table to obtain a ranking result;
And screening out the residual signal acquisition channel scheme corresponding to the maximum signal to noise ratio according to the sequencing result, wherein the residual signal acquisition channel scheme is the final signal acquisition channel scheme.
The strong electric facilities include a high-voltage switch cabinet, a power distribution cabinet, a generator and the like. Before the real-time characteristic data of the target resource are acquired, a reasonable acquisition channel can be planned and screened through the method, so that the phenomena of data loss and drift in the data acquisition process are reduced, the integrity and the precision of a data source are improved, the difficulty of subsequent data processing is reduced, and the processing efficiency is improved.
Furthermore, the method comprises the following steps:
acquiring real-time image information in a target resource, and identifying the real-time image information to identify whether a user exists in the target resource;
if the image information exists, carrying out feature extraction on the real-time image information based on an ORB algorithm to obtain a plurality of sparse feature points, constructing a three-dimensional coordinate system, and importing the sparse feature points into the three-dimensional coordinate system;
calculating Manhattan distances of the sparse feature points in the three-dimensional coordinate system, and screening a plurality of pairs of nearest sparse feature point pairs according to the Manhattan distances;
acquiring the median coordinate position points of each sparse feature point pair, and converting all the median coordinate position points into new feature points; generating dense feature points according to the sparse feature points and the new feature points; acquiring point cloud data of each dense feature point, and constructing a user feature model diagram according to the point cloud data;
Collecting a preset feature model diagram of community users, collecting behavior preference information of the users, constructing a knowledge graph, and importing the preset feature model diagram of each user and the corresponding behavior preference information into the knowledge graph;
calculating Euclidean distance values between the user feature model diagram and a preset feature model diagram in a knowledge graph through an Euclidean distance algorithm, and determining similarity according to the Euclidean distance values to obtain a plurality of similarities;
sequencing the multiple similarities to obtain maximum similarity, acquiring a preset feature model diagram corresponding to the maximum similarity, generating a search tag according to the preset feature model diagram corresponding to the maximum similarity, searching the knowledge graph based on the search tag to obtain behavior preference information of the user in the target resource, and transmitting the behavior preference information of the user in the target resource to the intelligent property control terminal
It should be noted that, the behavior preference information includes light rays, air-conditioning temperature, elevator running speed, etc. that the user prefers, when the user enters the elevator, the user identity is identified, so as to intelligently pair out the behavior preference information of the user, and thus, the light, air-conditioning, etc. in the elevator are adjusted to the range of the user preference through the control terminal. If there are multiple users, the adjustment can be done in an averaging manner.
As shown in fig. 4, the second aspect of the present invention discloses a community resource management system based on smart property, the community resource management system includes a memory 20 and a processor 60, the memory 20 stores a community resource management method program, and when the community resource management method program is executed by the processor 60, the following steps are implemented:
acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and correcting the historical characteristic data to obtain corrected historical characteristic data of the target resource under various states;
calculating transition probabilities among the states according to the corrected historical characteristic data, and generating a state transition matrix according to the transition probabilities among the states; constructing a Markov model, training the Markov model according to the state transition matrix, and outputting the trained Markov model;
collecting real-time characteristic data of a target resource at a plurality of preset time nodes, and clustering the collected real-time characteristic data based on a fuzzy clustering algorithm to obtain a plurality of real-time characteristic data sets;
And importing the real-time characteristic data of each real-time characteristic data set into the trained Markov model for prediction deduction, obtaining a prediction result, generating alarm information according to the prediction result, and sending the alarm information to an intelligent property control terminal.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. The community resource management method based on the intelligent property is characterized by comprising the following steps of:
acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and correcting the historical characteristic data to obtain corrected historical characteristic data of the target resource under various states;
calculating transition probabilities among the states according to the corrected historical characteristic data, and generating a state transition matrix according to the transition probabilities among the states; constructing a Markov model, training the Markov model according to the state transition matrix, and outputting the trained Markov model;
collecting real-time characteristic data of a target resource at a plurality of preset time nodes, and clustering the collected real-time characteristic data based on a fuzzy clustering algorithm to obtain a plurality of real-time characteristic data sets;
And importing the real-time characteristic data of each real-time characteristic data set into the trained Markov model for prediction deduction, obtaining a prediction result, generating alarm information according to the prediction result, and sending the alarm information to an intelligent property control terminal.
2. The community resource management method based on intelligent property according to claim 1, wherein the method is characterized in that the historical characteristic data corresponding to the target resource running under various states is obtained based on a big data network, and the historical characteristic data is corrected to obtain the corrected historical characteristic data of the target resource under various states, specifically:
acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and carrying out standardized processing on the historical characteristic data so as to ensure that the historical characteristic data are on the same scale; wherein the status includes normal operation, partial failure, and complete failure;
a local outlier factor algorithm is introduced, the field size is determined through a cross verification mode, for each historical characteristic data, the mahalanobis distance between the historical characteristic data and other historical characteristic data is calculated, the calculated mahalanobis distances are arranged in an ascending order, and the distance of the kth mahalanobis distance nearest neighbor data is selected as a k distance;
For each historical characteristic data, calculating the maximum value of k distance between each historical characteristic data and each neighbor data as an reachable distance; the reachable distance is used for measuring the tightness degree between each historical characteristic data and the neighbor of each historical characteristic data;
for each data point, carrying out ratio processing on the reachable distance of the neighbor data and the reachable distance of the data point, so as to determine the outlier degree of the history feature data relative to the neighbor, and obtaining the local outlier factor value of the history feature data;
comparing the local outlier factor value of each historical characteristic data with a preset value; and if the local outlier factor value of certain historical characteristic data is larger than a preset value, screening the historical characteristic data to obtain corrected historical characteristic data.
3. The community resource management method based on intelligent property according to claim 1, wherein the calculating of transition probability between states according to the modified historical feature data and the generating of state transition matrix according to transition probability between states are specifically as follows:
dividing the historical characteristic data of the target resource after being corrected under various states into different time periods to determine time intervals;
In each time interval, calculating the number of times of transferring the target resource from one state to another state, and obtaining the number of times of state transfer between different states; calculating transition probability between states according to the state transition times between different states;
constructing a state transition matrix, and filling the calculated transition probability into the state transition matrix; calculating the difference value between each transition probability in the state transition matrix, and generating a residual error according to the difference value between each transition probability;
minimizing the sum of squares of the residuals based on a least square method to determine a fitness of the state transition matrix according to the minimized sum of squares of the residuals; judging whether the fitting degree of the state transition matrix meets the preset requirement, and if so, directly outputting the state transition matrix meeting the preset requirement;
if the preset requirement is not met, the transition probability among the states is recalculated, the state transition matrix is updated, and the state transition matrix meeting the preset requirement is output after the fitting degree of the state transition matrix meets the preset requirement.
4. The community resource management method based on intelligent property according to claim 1, wherein a markov model is constructed, training is performed on the markov model according to the state transition matrix, and the trained markov model is output, specifically:
Performing feature vector decomposition on the state transition matrix to obtain feature vectors and corresponding feature values of the state transition matrix;
carrying out normalization processing on the feature vector of the state transition matrix to ensure that the sum of all elements is 1, and obtaining the steady-state distribution of the Markov chain; wherein, the steady-state distribution represents probability distribution of each state after the target resource passes a preset period;
establishing a Markov model, initializing the initial node state of the Markov model according to the steady-state distribution of the Markov chain, and importing the state transition matrix into the Markov model; carrying out convolution processing on a state transition matrix imported into the Markov model, and acquiring convolution characteristics of the state transition matrix after the convolution processing;
defining initial training parameters of a Markov model according to the convolution characteristics and the initial node state, training the Markov model based on the initial training parameters until a training error convergence value is preset to a numerical value, and outputting model parameters;
calculating a log-likelihood function value of a Markov model according to the model parameters and combining a maximum likelihood estimation method, and if the log-likelihood function value is larger than a preset log-likelihood function value, indicating that the model parameters meet fitting requirements, and outputting the trained Markov model;
And if the log-likelihood function value is not greater than the preset log-likelihood function value, redefining initial training parameters of the Markov model, and continuing training the Markov model until the number-likelihood function value of the Markov model is greater than the preset log-likelihood function value, and outputting the trained Markov model.
5. The community resource management method based on intelligent property according to claim 1, wherein the method is characterized in that the collected real-time characteristic data is clustered based on a fuzzy clustering algorithm to obtain a plurality of real-time characteristic data sets, and specifically comprises the following steps:
determining the number of target resources, initializing a plurality of cluster clusters according to the number of target resources, and randomly generating an initial membership matrix according to the cluster clusters and the real-time characteristic data; wherein, the element in the initial membership matrix represents the membership degree of the real-time characteristic data belonging to a certain cluster, and the initial value is 0 or 1;
calculating a weighted average value of all real-time characteristic data in each cluster, so as to determine a fuzzy cluster center of each cluster according to the weighted average value; according to the fuzzy clustering center of each cluster, recalculating the membership degree of each real-time characteristic data belonging to each cluster in the cluster, and updating the initial membership degree matrix according to the calculated membership degree of each real-time characteristic data belonging to each cluster to obtain a membership degree matrix;
Judging whether the difference between the membership matrix and the initial membership matrix is smaller than a preset threshold value; if the number of the membership degree matrixes is smaller than the threshold value, stopping iteration and outputting the final membership degree matrixes; if the number of the membership degree matrixes is not smaller than the preset threshold value, repeating the steps until the number of the membership degree matrixes is smaller than the threshold value, stopping iteration, and outputting the final membership degree matrixes;
dividing each real-time characteristic data into a cluster with the highest membership degree according to the final membership degree matrix, outputting a clustering result, obtaining a plurality of initial real-time characteristic data sets according to the clustering result, and correcting the plurality of initial real-time characteristic data sets to obtain a plurality of real-time characteristic data sets.
6. The community resource management method based on intelligent property according to claim 5, wherein the correction is performed on a plurality of initial real-time feature data sets to obtain a plurality of real-time feature data sets, specifically:
acquiring real-time feature data in each initial real-time feature data set, introducing a Euclidean distance algorithm, and calculating Euclidean distances between the real-time feature data in each initial real-time feature data set and a fuzzy clustering center of the real-time feature data set through the Euclidean distance algorithm;
judging whether the Euclidean distance between the real-time feature data in the initial real-time feature data set and the fuzzy clustering center is larger than a preset Euclidean distance, if so, marking the real-time feature data as clustering abnormal data, and removing the clustering abnormal data in the corresponding initial real-time feature data set;
Calculating Euclidean distance between the clustering abnormal data and the fuzzy clustering centers in the rest initial real-time characteristic data sets, and sequencing the Euclidean distance between the clustering abnormal data and the fuzzy clustering centers in the rest initial real-time characteristic data sets to obtain the minimum Euclidean distance;
if the minimum Euclidean distance is still larger than the preset Euclidean distance, the clustering abnormal data is indicated to be invalid data, and the clustering abnormal data is thoroughly screened out; if the minimum Euclidean distance is not greater than the preset Euclidean distance, clustering the clustering abnormal data again to an initial real-time characteristic data set corresponding to the minimum Euclidean distance;
repeating the steps until all the initial real-time feature data sets are corrected, and updating each initial real-time feature data set to obtain a plurality of real-time feature data sets.
7. The community resource management method based on intelligent property according to claim 1, wherein the real-time feature data of each real-time feature data set is imported into the trained markov model to conduct prediction deduction, a prediction result is obtained, alarm information is generated according to the prediction result, and the alarm information is sent to a intelligent property control terminal, specifically:
The real-time characteristic data of each real-time characteristic data set is imported into the trained Markov model for prediction deduction, and a prediction result is obtained;
obtaining state information of each target resource in a preset time period according to the prediction result, and obtaining the state information as position information of the target resource of the preset type of state information when the state information is the preset type of state information;
and generating alarm information based on the state information as the position information of the target resource of the preset type of state information, and sending the alarm information to the intelligent property control terminal.
8. The community resource management system based on the intelligent property is characterized by comprising a memory and a processor, wherein the memory stores a community resource management method program, and when the community resource management method program is executed by the processor, the following steps are realized:
acquiring historical characteristic data corresponding to the target resource running under various states based on a big data network, and correcting the historical characteristic data to obtain corrected historical characteristic data of the target resource under various states;
calculating transition probabilities among the states according to the corrected historical characteristic data, and generating a state transition matrix according to the transition probabilities among the states; constructing a Markov model, training the Markov model according to the state transition matrix, and outputting the trained Markov model;
Collecting real-time characteristic data of a target resource at a plurality of preset time nodes, and clustering the collected real-time characteristic data based on a fuzzy clustering algorithm to obtain a plurality of real-time characteristic data sets;
and importing the real-time characteristic data of each real-time characteristic data set into the trained Markov model for prediction deduction, obtaining a prediction result, generating alarm information according to the prediction result, and sending the alarm information to an intelligent property control terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311505855.5A CN117557415A (en) | 2023-11-13 | 2023-11-13 | Community resource management method and system based on intelligent property |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311505855.5A CN117557415A (en) | 2023-11-13 | 2023-11-13 | Community resource management method and system based on intelligent property |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117557415A true CN117557415A (en) | 2024-02-13 |
Family
ID=89817894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311505855.5A Pending CN117557415A (en) | 2023-11-13 | 2023-11-13 | Community resource management method and system based on intelligent property |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557415A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743877A (en) * | 2024-02-20 | 2024-03-22 | 江苏雷博微电子设备有限公司 | Intelligent detection method for component faults of glue spraying machine |
-
2023
- 2023-11-13 CN CN202311505855.5A patent/CN117557415A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743877A (en) * | 2024-02-20 | 2024-03-22 | 江苏雷博微电子设备有限公司 | Intelligent detection method for component faults of glue spraying machine |
| CN117743877B (en) * | 2024-02-20 | 2024-05-03 | 江苏雷博微电子设备有限公司 | Intelligent detection method for component faults of glue spraying machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111124840B (en) | Method and device for predicting alarm in business operation and maintenance and electronic equipment | |
| CN111368890A (en) | Fault detection method and device and information physical fusion system | |
| CN110570012B (en) | Storm-based power plant production equipment fault early warning method and system | |
| CN112529204A (en) | Model training method, device and system | |
| CN111176953B (en) | Abnormality detection and model training method, computer equipment and storage medium | |
| CN117557415A (en) | Community resource management method and system based on intelligent property | |
| WO2014173272A1 (en) | Layout method and layout system for monitoring units of digital man-machine interface | |
| CN115454778A (en) | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment | |
| CN116737510B (en) | Data analysis-based intelligent keyboard monitoring method and system | |
| CN116862081B (en) | Operation and maintenance method and system for pollution treatment equipment | |
| CN115204536A (en) | Building equipment fault prediction method, device, equipment and storage medium | |
| CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
| CN116794510A (en) | Fault prediction method, device, computer equipment and storage medium | |
| CN117494072B (en) | Method and system for monitoring operation state of battery-changing cabinet based on data fusion | |
| CN110597792A (en) | Multistage redundant data fusion method and device based on synchronous line loss data fusion | |
| CN108197347B (en) | method for detecting geographic space distribution uniformity of continuous irregular area sampling points | |
| CN112836843B (en) | Base station out-of-service alarm prediction method and device | |
| CN116714469A (en) | Charging pile health monitoring method, device, terminal and storage medium | |
| CN113891342A (en) | Base station inspection method and device, electronic equipment and storage medium | |
| CN111614504A (en) | Power grid regulation and control data center service characteristic fault positioning method and system based on time sequence and fault tree analysis | |
| CN113986673A (en) | Fault correlation method and device and computer readable storage medium | |
| CN109492913B (en) | Modular risk prediction method and device for power distribution terminal and storable medium | |
| CN115241981B (en) | Active power distribution network monitoring method based on big data | |
| CN117495357B (en) | Electric power data supervision system and method based on big data | |
| CN108364076B (en) | Building repair action prediction model, repair action prediction method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |