CN115879642A - Construction split prediction-based real-time sensing method for broadband installation progress - Google Patents
Construction split prediction-based real-time sensing method for broadband installation progress Download PDFInfo
- Publication number
- CN115879642A CN115879642A CN202310015762.8A CN202310015762A CN115879642A CN 115879642 A CN115879642 A CN 115879642A CN 202310015762 A CN202310015762 A CN 202310015762A CN 115879642 A CN115879642 A CN 115879642A
- Authority
- CN
- China
- Prior art keywords
- time
- data
- construction
- sensing
- real
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 164
- 238000009434 installation Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000008447 perception Effects 0.000 claims abstract description 28
- 238000011156 evaluation Methods 0.000 claims abstract description 26
- 238000013210 evaluation model Methods 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000012821 model calculation Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 230000004069 differentiation Effects 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 18
- 238000012423 maintenance Methods 0.000 abstract description 12
- 230000004913 activation Effects 0.000 description 6
- 238000012790 confirmation Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
Images
Abstract
The invention discloses a construction split prediction-based real-time sensing method for broadband installation progress, which comprises the following steps of: s1, collecting system data; s2, establishing an installation construction progress real-time perception evaluation model through the collected system data; and S3, judging the construction progress according to the installation construction progress real-time perception evaluation model. According to the method, historical worksheet construction completion time data is obtained, the system automatically predicts the completion time, the historical similar data is used for evaluation, evaluation is carried out according to three dimensions of the service type, the cell standard address and the name of an assembly and maintenance worker, the similarity score is judged, the estimated time is more accurate, the broadband assembly construction process is minimally divided into 8 subtask nodes, the assembly construction progress is sensed in a refined mode, the residual completion time is calculated in real time according to the current construction progress, the accuracy of estimating the worksheet completion time is improved, and the estimation of the whole construction completion time is more accurate compared with the prior art.
Description
Technical Field
The invention relates to the field of network management in the telecommunication industry, in particular to a real-time sensing method for broadband installation progress based on construction split prediction.
Background
The main objective of the development of the sensing technology in foreign countries is to solve the operation and maintenance problem and the security problem of the network, and in the operation and maintenance problem, the current industry is not fully mature, and the cisco masters part of the leading network sensing technology, and network chip manufacturers such as boson and Barefoot, and internet users including amazon, microsoft and Facebook are proposed to make the industry standard DPT in the OCP, so as to provide the data forwarding level information of network load, time delay and jitter, and provide support for the intelligent and automatic network operation and maintenance. In terms of security guarantee, the network perception technology screens DDoS attack flow in network equipment in advance by analyzing the length distribution state of message flow, and helps firewall equipment to defend network attack of large-scale flow jointly.
The construction progress of the current broadband installation machine is estimated manually, the work order completion time is estimated by means of manual experience, accurate estimation and judgment cannot be carried out, the estimation time is not judged by the existing related technical scheme about the real-time progress perception of the construction of the broadband installation machine, the progress of the construction time of the work order cannot be accurately controlled by a limiting manual estimation mode, if a certain work order is seriously overtime, the next work order construction site cannot be reached in time, the work order cannot perform, the customer satisfaction is reduced, the customer service quality of an operator is seriously influenced, the work income of constructors is also influenced, the work order construction progress is accurately perceived, abnormal real-time early warning of the construction progress is realized, the method has important significance, and the existing manual experience judges whether the construction completion progress of the broadband installation work order has the following main defects in time or not:
1) The accuracy is hard to guarantee: in the field construction process, a constructor estimates whether the current work order can be completed in time or not and performs the next work order on time, and the estimation completely depends on manual experience, so that the estimation is easily influenced by personal subjective skill, professional knowledge and historical processing experience, the accuracy cannot be ensured, different judgment results of different persons are easy to appear, and the judgment of the accuracy is influenced.
2) Unexpected emergency: in the field construction process of constructors, if an emergency abnormal condition occurs, such as abnormal terminal data transmission, extra time is consumed for processing, the emergency condition cannot be evaluated and predicted in time, and the completion time cannot be accurately predicted.
3) Influencing the performance of subsequent work orders: the construction progress can not be sensed in real time, the actual completion time of the work order can not be accurately predicted, overtime early warning can not be carried out in advance, the performance of the next work order is delayed, and the customer satisfaction is influenced.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a construction splitting prediction-based real-time sensing method for the broadband installation progress, so as to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
a real-time sensing method for the progress of a broadband installation machine based on construction split prediction comprises the following steps:
s1, collecting system data;
s2, establishing an installation construction progress real-time perception evaluation model through the collected system data;
and S3, judging the construction progress according to the installation construction progress real-time perception evaluation model.
Further, the step of collecting system data comprises the following steps:
s11, collecting the sample data of the installation work order;
s12, acquiring data of the installed worksheet sensing node;
s13, preprocessing the acquired data and adding the preprocessed data into a standard sample library;
and S14, taking the collected data as a model training sample and a model application sample.
Further, the step of establishing the installation construction progress real-time perception evaluation model through the collected system data comprises the following steps:
s21, preprocessing model training data of the real-time perception evaluation model of the installation construction progress;
s22, model calculation is carried out on the preprocessed data;
and S23, estimating the evaluation time according to the calculation result.
Further, the step of judging the construction progress according to the installed construction progress real-time perception evaluation model comprises the following steps:
s31, screening the data of the standard sample library;
s32, time consumption evaluation is conducted on the installed construction sensing node;
s33, carrying out real-time sensing calculation on the installation construction progress;
s34, sensing and processing the installation construction progress in real time;
and S35, carrying out real-time sensing closed-loop optimization on the installation construction progress.
Further, the preprocessing of the model training data of the installation construction progress real-time perception evaluation model comprises the following steps:
s211, performing primary screening on training data input by the model;
s212, forming a work order set by the preliminarily screened data;
s213, acquiring time data of each installed worksheet and calculating;
and S214, storing the calculated data into a standard sample library.
Further, a calculation formula for performing model calculation on the preprocessed data is as follows:
wherein the content of the first and second substances,
sensing the node segment time for the work order 1;
n is the total number of work orders;
Further, the estimating of the evaluation time according to the calculation result includes the steps of:
s231, preliminarily dividing the acquired work order data;
s232, judging the acquaintance according to the differentiation result;
s233, taking the work order completion time with the similarity judgment close as estimation time;
and S234, updating the mechanical energy of the work order data at the specified installation time.
Further, the screening of the standard sample bank data comprises the following steps:
s311, judging the number of the work orders, and estimating the average completion time of the data;
s312, taking the work order data of the same business condition, and removing isolated point data;
and S313, estimating according to the average completion time of the removed isolated point data.
Further, the real-time sensing calculation of the installation construction progress comprises the following steps:
s331, starting timing for entering a construction point;
s332, accumulating the consumed time of each installation construction progress sensing node in real time;
s333, reminding the time needed for the completion of the remaining progress;
and S334, comparing and judging the actual time consumption with the predicted time consumption, and sending out early warning and reminding according to a judgment result.
Further, the real-time sensing closed-loop optimization of the installation construction progress comprises the following steps:
and when the work order is not abnormal, and the time consumed by the work order and the estimated whole time consumed are within a preset error threshold, adding the time consumed by the work order into the sample library as an estimated time sample, and continuously adjusting the accuracy of the sample data.
The beneficial effects of the invention are as follows:
1. according to the method, through acquiring historical work order construction completion time data, after standard sample screening, mean value and standard value calculation, accuracy judgment, closed-loop optimization data and other operations are carried out, the system automatically predicts the completion time, compared with the prior art, the method is more accurate in subjective evaluation by using manual experience, carries out evaluation by using historical similar data, carries out evaluation according to three dimensions of a service type, a cell standard address and a maintenance worker name, judges a similarity score, enables the predicted time to be more accurate, minimally splits a broadband installation construction process into 8 subtask nodes, finely senses the installation construction progress, calculates the residual completion time in real time according to the current construction progress, improves the accuracy of prediction of the work order completion time, and compared with the prior art, the prediction of the time of the whole construction completion is more accurate.
2. According to the method, node time data of 8 subtasks of the installation construction progress are automatically acquired through real-time system interface data calling in the installation construction process, then the installation construction progress real-time sensing evaluation model is used for fast calculation, the current work order completion evaluation time is obtained, the current work order completion evaluation time is compared with the current work order progress in real time, the residual completion time is estimated, the construction time consumption situation of installation and maintenance personnel is reminded in real time, the current time consumption and the estimated residual time are calculated in the whole construction process in a fully-automatic mode, the installation and maintenance personnel can control the current construction progress more efficiently, and the installation and maintenance construction efficiency is improved.
3. The invention can sense the construction progress of the installation in real time, and the system can automatically, timely and accurately judge whether the next work order can be performed on time or not so as to control the current construction time. When abnormal problems occur in construction, such as the system acquires a work order caused by a wrong resource information and the like, the construction time needs to be increased, the system can automatically remind constructors, the work order is dispatched or changed as soon as possible, next work order customer care work is carried out, and customer satisfaction is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a method for sensing the broadband installation progress in real time based on construction split prediction according to an embodiment of the invention;
FIG. 2 is a model processing diagram of a method for sensing the broadband installation progress in real time based on construction split prediction according to an embodiment of the invention;
FIG. 3 is a model usage flow chart of a method for sensing the broadband installed progress in real time based on construction split prediction according to an embodiment of the invention.
Detailed Description
For further explanation of the various embodiments, the drawings are provided as part of the present disclosure and serve primarily to illustrate the embodiments and to explain the principles of operation of the embodiments in conjunction with the description given herein, and to enable others of ordinary skill in the art to understand the principles and advantages of the present invention in conjunction with the reference thereto.
According to the embodiment of the invention, a real-time sensing method for the broadband installation progress based on construction split prediction is provided.
Referring to the drawings and the detailed description, the invention is further explained, as shown in fig. 1 to fig. 3, according to the method for sensing the broadband installed schedule in real time based on the construction split prediction, the method includes the following steps:
s1, collecting system data;
specifically, the system data acquisition method comprises the following steps:
s11, collecting the sample data of the installation work order;
specifically, the work order sample data of the past month is obtained, and the work order information needs to contain a work order code, a cell standard address, a maintenance worker name, a work order service type and a work order type.
Work order integral data example table
S12, acquiring data of the installed worksheet sensing node;
specifically, by calling a construction scheduling system interface, according to a work order code, acquiring a key time point of a work order construction process corresponding to the work order, wherein the key time point comprises time data of sensing nodes such as construction position card punching, terminal power-on activation, user registration, data issuing, network speed measurement, optical power test, customer confirmation evaluation, leaving a construction point and the like;
data example table
And S13, preprocessing the acquired data and adding the preprocessed data into a standard sample library.
Specifically, collected historical work order data is simply screened for one round, average work order completion time is calculated according to the same business, the same work order type and the same cell work order, and discrete isolated point data are removed. And if the maximum value and the minimum value are removed, namely 60% of data of which the integral completion time of the work order exceeds and is lower than the average time are removed, and the data which are input into the standard library are used for training and applying the installed construction progress real-time perception model.
Specifically, the collected system data comprises work order basic information and work order construction process time data, the collected historical loader work order data is used as a model training sample and a model application sample, and the whole scheme is divided into two parts, wherein one part is construction progress real-time perception modeling, and the other part is construction progress real-time perception application.
And S14, taking the collected data as a model training sample and a model application sample.
Specifically, the construction progress real-time perception modeling: the method comprises the steps of obtaining historical installed work order sample data, preprocessing the data, removing isolated point data, classifying according to service types, cell names and personnel names, and inputting the obtained data serving as a model. And then model calculation is carried out, the average value and the standard deviation of the time of the sensing node in the work order construction process are calculated, and a proper standard deviation threshold value and a time estimation accuracy judgment standard are adjusted. And model output is the estimated time of 8 sensing nodes in the construction process of the installation, the estimated time of the whole completion of the work order and the accuracy of the estimated time.
The construction progress real-time perception application comprises the following steps: according to current loader work order information data, the same type sample data is screened according to three dimensions of service types, cell addresses and personnel names, the sample data is used as basic data for model evaluation, then the consumed time of the sensing nodes in the work order construction process is estimated through an installation construction progress real-time sensing evaluation model, finally, during actual construction, the execution time of the 8 sensing nodes is collected in real time, whether the estimated consumed time data is overtime or not is judged in advance, overtime early warning is carried out according to different conditions, the risk of the next work order is prevented from being performed, and measures such as task transfer, customer placation and the like can be carried out in time.
S2, establishing an installation construction progress real-time perception evaluation model through the collected system data;
specifically, the establishing of the installation construction progress real-time perception evaluation model through the collected system data comprises the following steps:
s21, preprocessing model training data of the real-time perception evaluation model of the installation construction progress;
specifically, the preprocessing of the model training data of the real-time perception evaluation model of the installed construction progress comprises the following steps:
s211, performing primary screening on training data input by the model;
specifically, the preliminary screening of sample data is required to be performed according to the service type of the current work order, work order processing personnel and a construction cell;
s212, forming a work order set by the preliminarily screened data;
specifically, the number of the set of the worksheets is not less than 5 and can be calculated;
s213, acquiring time data of each installed worksheet and calculating;
specifically, time data of each installed work order is taken and calculated, namely time stamps of 8 sensing nodes in the construction process of each work order are calculated, and the time of the two nodes is subtracted to obtain the specific consumption time (unit: minute) of each section of sensing node;
when the method is used specifically, if a broadband service installation machine is used for opening a model calculation result data example of the average construction time of a certain person in a work order;
construction position card punching-terminal power-up activation: 14 minutes;
terminal power on activation-user registration: 9 minutes;
user registration-data delivery: 9 minutes;
data issuing-network speed measurement: 8 minutes;
network speed measurement-optical power test: 3 minutes;
optical power test-customer confirmation: 3 minutes;
customer validation-leaving construction point: 2 minutes;
and removing relatively discrete isolated point data from the standard sample library data according to the time consumed by each sensing node section to obtain a group of relatively effective time data which is used as model input calculation.
An isolated point data elimination scheme for sensing time consumed by a node segment: and if the time difference is greater than 60% of the average time or less than 50% of the average time, eliminating the time data and ensuring the accuracy of calculation.
And S214, storing the calculated data into a standard sample library.
S22, performing model calculation on the preprocessed data;
specifically, the construction progress real-time perception model calculates the mean value and the standard deviation of perception node completion time of input installed worksheet training data, judges according to the standard deviation threshold value, obtains a proper mean value, and uses the mean value as model output data. And temporarily setting the standard deviation threshold of the sensing node time as 1, and eliminating isolated point data when the data exceeds 1.
The mean (expected) of the sensing node time is the midpoint (mean) of the installed worksheet sample set, but its information is limited, and the standard deviation describes the average of the distances of the individual sample points of the installed worksheet sample set to the mean.
Specifically, the calculation formula for performing model calculation on the preprocessed data is as follows:
wherein the content of the first and second substances,
sensing node segment time for the work order 1;
n is the total number of work orders;
And S23, estimating the evaluation time according to the calculation result.
Average door-to-door construction time model calculation result data example table (sensing node replaces name with letter, 5 installation worksheets are taken as an example, mean value and standard deviation are calculated according to formula)
The smaller the standard deviation factor, the better, representing a smaller difference between most values and their mean values. The estimated mean value is more accurate.
Specifically, the estimating the evaluation time according to the calculation result includes the following steps:
s231, preliminarily dividing the acquired work order data;
s232, judging the acquaintance according to the differentiation result;
s233, taking the work order completion time with the similarity judgment close as estimation time;
and S234, updating the mechanical energy of the work order data at the specified installation time.
And S3, judging the construction progress according to the installation construction progress real-time perception evaluation model.
Specifically, the installation construction progress real-time sensing process needs to screen sample database data according to current installation work order information, screen historical installation work order sample data according to three dimensions of a service type, a cell name and current processing personnel for evaluation calculation, obtain predicted time consumption of work order construction, simultaneously sense and compare the construction progress in real time, pre-judge whether a work order is overtime, if the pre-judgment is about to be overtime, take corresponding measures such as transfer and improvement immediately, and if the work order is finished on time finally, data enter a standard sample database.
Specifically, the step of judging the construction progress according to the installation construction progress real-time perception evaluation model comprises the following steps:
s31, screening the data of the standard sample library;
specifically, the screening of the standard sample library data comprises the following steps:
s311, judging the number of the work orders, and estimating the average completion time of the data;
and firstly, judging the number of the work orders meeting the three conditions at the same time, and if the number of the work orders is more than 5 and the standard difference value of the overall completion time is less than 1, estimating the average completion time of the historical data. If the content is less than 5, screening in the second step is carried out;
and if the work order simultaneously meeting the two conditions of contract service and the cell is more than 5 and the standard difference value of the overall completion time is less than 1, estimating the average completion time of the historical data according to the obtained average completion time. If the content is less than 5, screening in the third step;
s312, taking the work order data of the same business condition, and removing isolated point data;
and S313, estimating according to the average completion time of the removed isolated point data.
Specifically, work order data of the same business condition is taken, isolated point data is removed, the standard difference value of the overall completion time is smaller than 1, and then estimation is carried out according to the average completion time of the historical data.
Specifically, the historical data samples are divided preliminarily according to the installation work orders of the same service type, the similarity degree of the current work order execution is judged according to whether the current work order execution is similar to that of the same cell and the same processing personnel, the work order completion time with the highest similarity degree is taken as the estimated time, and the work order samples are updated every other week.
The similarity degree is divided as follows: and only installing the work order with the same business, wherein the similarity is 30%, installing the work order with the same business and the same cell, wherein the similarity is 70%, installing the work order with the same business and the same cell and the same processing personnel, wherein the similarity is 90%, and the higher the similarity value is, the higher the accuracy of the evaluation time is.
S32, time consumption evaluation is conducted on the installed construction sensing node;
during specific application, after the data of the evaluation sample library are obtained, the time consumed by the installation worksheet of the current service is calculated according to the sensing node completion time estimation model.
Example (c): the number of the work orders of the same service and the same cell in the current work order and the sample library is more than 5, and the estimated consumption time of each sensing node is calculated according to a time estimation model (the average value is rounded) as follows:
construction position card punching-terminal power-up activation: expected to take 13 minutes;
terminal power on activation-user registration: the predicted time takes 10 minutes;
user registration-data delivery: the expected time to take 8 minutes;
data issuing-network speed measurement: it is expected to take 7 minutes;
network speed measurement-optical power test: expected to take 4 minutes;
optical power test-customer confirmation: it is expected to take 3 minutes;
customer validation-leaving construction point: expected to take 2 minutes;
the total elapsed time was predicted to be 47 minutes with 70% accuracy.
S33, carrying out real-time sensing calculation on the installation construction progress;
specifically, the real-time sensing calculation of the installation construction progress comprises the following steps:
s331, starting timing for entering a construction point;
s332, accumulating the consumed time of each installation construction progress sensing node in real time;
s333, reminding the time needed for the completion of the remaining progress;
and S334, comparing and judging the actual time consumption with the predicted time consumption, and sending out early warning and reminding according to a judgment result.
During specific application, the estimated time consumed by each progress sensing node is assumed to be known in the current work order, and 20 minutes of journey time is needed for arriving at the time of the next work order.
Construction position card punching-terminal power-up activation: expected to take 13 minutes and actually 14 minutes;
terminal power on activation-user registration: the expected 10 minutes actually took 10 minutes;
user registration-data delivery: an actual time of 9 minutes is expected to take 8 minutes;
data issuing-network speed measurement: expected to take 7 minutes and actually 9 minutes;
network speed measurement-optical power test: expected to take 4 minutes to go on;
optical power test-customer confirmation: expected to take 3 minutes;
customer validation-leaving construction point: expected to take 2 minutes;
currently, the work order construction takes an additional 4 minutes, and the estimated completion time is 9 minutes.
S34, sensing and processing the installation construction progress in real time;
specifically, when the construction progress is sensed to be overtime possibly, the constructor is reminded that the work order is about to be overtime.
The construction progress overtime judgment method comprises the following steps: and comparing and judging the estimated completion time and the actual consumed time of the whole work order, which specifically comprises the following steps:
equation 1:0< (actual time consumption + estimated time consumption of remaining nodes) -estimated time for completing the work order < estimated time for completing the work order by 20%;
if the formula 1 is met, the system automatically reminds that overtime is about to occur: XX minutes remain from the next work order appointment time, please grasp the time.
Equation 2: actual time consumption + estimated time consumption of the remaining nodes-estimated work order completion time > estimated work order completion time of 20%;
if formula 2 is satisfied, the representative is overtime, the next work order is changed or forwarded, and the customer is pacified.
And S35, carrying out real-time sensing closed-loop optimization on the installation construction progress.
Specifically, the real-time sensing closed-loop optimization of the installation construction progress comprises the following steps:
and when the work order is not abnormal, and the time consumed by the completion of the work order and the time consumed by the estimation of the whole are larger than a preset error threshold, adding the work order into a sample library as an estimation time sample, and continuously adjusting the accuracy of the sample data.
Specifically, the construction process of the installed door relates to a plurality of construction steps, and the construction process comprises the steps of entering a construction point, outdoor construction (port selection, fiber pulling and the like), indoor construction (wiring and the like), terminal power-on activation, registration, data issuing, speed measurement, optical power test, customer confirmation evaluation and leaving of the construction point from the time when the door arrives at the construction point to the time when the door leaves the construction point.
For can perception installation construction progress, draw the installation work progress 8 steps that the accessible system automatically obtained the data perception progress: the method comprises the steps of construction position entering, terminal power-on activation, registration, data issuing, speed measurement, optical power testing, customer confirmation evaluation and leaving of a construction point, finishing time is calculated according to the 8 step nodes respectively, and then an installation construction progress sensing model is established.
In summary, according to the technical scheme of the invention, after the operations of standard sample screening, mean value and standard value calculation, accuracy judgment, closed-loop optimization data and the like are performed by acquiring historical work order construction completion time data, the system automatically predicts the completion time, compared with the prior art, the system is more accurate in subjective evaluation by using the manual experience, evaluates by using historical similar data, evaluates according to three dimensions of the service type, the cell standard address and the name of an assembly maintainer, and judges the similarity score, so that the predicted time is more accurate, the broadband assembly construction process is minimally divided into 8 subtask nodes, the assembly construction progress is finely sensed, the residual completion time is calculated in real time according to the current construction progress, the accuracy of the estimation of the work order completion time is improved, and compared with the prior art, the estimation of the time for the whole construction is more accurate.
In addition, the invention automatically acquires node time data of 8 subtasks of the installation construction progress through real-time system interface data calling in the installation construction process, then quickly calculates through an installation construction progress real-time perception evaluation model to obtain the current worksheet completion evaluation time, compares the current worksheet completion evaluation time with the current worksheet progress in real time, estimates the residual completion time consumption, and reminds the installation and maintenance personnel of the construction time consumption situation in real time, and the whole construction process, the current time consumption and the estimated residual time consumption are calculated in a fully automatic manner, so that the installation and maintenance personnel can control the current construction progress more efficiently, and the installation and maintenance construction efficiency is improved.
In addition, the invention can sense the construction progress of the installation in real time, and the system can automatically, timely and accurately judge whether the next work order can be performed on time or not so as to control the current construction time. When abnormal problems occur in construction, such as the system acquires a resource information error and the like to cause a work order, the construction time needs to be increased, the system can automatically remind constructors to transfer or modify the work order as soon as possible, and the next work order customer care work is carried out, so that the customer satisfaction is improved.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A construction split prediction-based real-time sensing method for the broadband installation progress is characterized by comprising the following steps:
s1, collecting system data;
s2, establishing an installation construction progress real-time perception evaluation model through the collected system data;
and S3, judging the construction progress according to the installation construction progress real-time sensing evaluation model.
2. The method for sensing the broadband installed progress in real time based on construction split prediction as claimed in claim 1, wherein the collecting system data comprises the following steps:
s11, collecting the sample data of the installation work order;
s12, acquiring data of the sensing nodes of the installation work orders;
s13, preprocessing the acquired data and adding the preprocessed data into a standard sample library;
and S14, taking the collected data as a model training sample and a model application sample.
3. The method for sensing the installation progress of the broadband based on the construction splitting prediction in real time as claimed in claim 2, wherein the step of establishing the installation construction progress real-time sensing evaluation model through the collected system data comprises the following steps:
s21, preprocessing model training data of the real-time perception evaluation model of the installation construction progress;
s22, performing model calculation on the preprocessed data;
and S23, estimating the evaluation time according to the calculation result.
4. The method for sensing the wide-band installation progress in real time based on the construction splitting prediction as claimed in claim 3, wherein the step of judging the construction progress according to the installation construction progress real-time sensing evaluation model comprises the following steps:
s31, screening the data of the standard sample library;
s32, time consumption evaluation is conducted on the installed construction sensing node;
s33, carrying out real-time sensing calculation on the installation construction progress;
s34, sensing and processing the installation construction progress in real time;
and S35, carrying out real-time sensing closed-loop optimization on the installation construction progress.
5. The method for sensing the wide-band installed progress in real time based on the construction split prediction as claimed in claim 4, wherein the preprocessing of the model training data of the installed construction progress real-time sensing evaluation model includes the following steps:
s211, performing primary screening on training data input by the model;
s212, forming a work order set by the preliminarily screened data;
s213, acquiring time data of each installed worksheet and calculating;
and S214, storing the calculated data into a standard sample library.
6. The method for sensing the wide-band installed progress in real time based on construction and split prediction according to claim 5, wherein a calculation formula for performing model calculation on the preprocessed data is as follows:
wherein the content of the first and second substances,
sensing the node segment time for the work order 1;
n is the total number of work orders;
7. The method for sensing the wide-band installed progress in real time based on construction splitting prediction as claimed in claim 6, wherein the estimating of the evaluation time according to the calculation result comprises the following steps:
s231, preliminarily dividing the acquired work order data;
s232, judging the acquaintance according to the differentiation result;
s233, taking the work order completion time with the similarity judgment close as estimation time;
and S234, updating the mechanical energy of the work order data at the set time.
8. The construction splitting prediction-based real-time sensing method for the wide-band installed progress of the machine as claimed in claim 7, wherein the step of screening the standard sample library data comprises the following steps:
s311, judging the number of the work orders, and estimating the average completion time of the data;
s312, taking the work order data of the same business condition, and removing isolated point data;
and S313, estimating according to the average completion time of the removed isolated point data.
9. The method for sensing the wide-band installed progress in real time based on construction split prediction according to claim 8, wherein the real-time sensing calculation of the installed construction progress comprises the following steps:
s331, starting timing for entering a construction point;
s332, accumulating the consumed time of each installation construction progress sensing node in real time;
s333, reminding the time needed for the completion of the remaining progress;
and S334, comparing and judging the actual time consumption with the predicted time consumption, and sending out early warning and reminding according to a judgment result.
10. The construction splitting prediction-based real-time sensing method for the wide-band installed progress, according to claim 9, is characterized in that the real-time sensing closed-loop optimization of the installed construction progress comprises the following steps:
and when the work order is not abnormal, and the time consumed by the work order and the estimated whole time consumed are within a preset error threshold, adding the time consumed by the work order into the sample library as an estimated time sample, and continuously adjusting the accuracy of the sample data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310015762.8A CN115879642A (en) | 2023-01-06 | 2023-01-06 | Construction split prediction-based real-time sensing method for broadband installation progress |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310015762.8A CN115879642A (en) | 2023-01-06 | 2023-01-06 | Construction split prediction-based real-time sensing method for broadband installation progress |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115879642A true CN115879642A (en) | 2023-03-31 |
Family
ID=85758148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310015762.8A Pending CN115879642A (en) | 2023-01-06 | 2023-01-06 | Construction split prediction-based real-time sensing method for broadband installation progress |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879642A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114922A (en) * | 2023-10-24 | 2023-11-24 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
| CN117114452A (en) * | 2023-10-23 | 2023-11-24 | 中科云谷科技有限公司 | Method, processor, device and storage medium for determining construction scheme |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111636891A (en) * | 2020-06-08 | 2020-09-08 | 中铁高新工业股份有限公司 | Real-time shield attitude prediction system and construction method of prediction model |
| CN113095786A (en) * | 2021-04-20 | 2021-07-09 | 广联达科技股份有限公司 | Delay prediction method and prediction device for construction project |
| CN113222564A (en) * | 2021-06-09 | 2021-08-06 | 合肥优尔电子科技有限公司 | Progress management system and method based on BIM system |
| CN113379324A (en) * | 2021-07-06 | 2021-09-10 | 山东电力工程咨询院有限公司 | Construction site whole-course monitoring method and system |
-
2023
- 2023-01-06 CN CN202310015762.8A patent/CN115879642A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111636891A (en) * | 2020-06-08 | 2020-09-08 | 中铁高新工业股份有限公司 | Real-time shield attitude prediction system and construction method of prediction model |
| CN113095786A (en) * | 2021-04-20 | 2021-07-09 | 广联达科技股份有限公司 | Delay prediction method and prediction device for construction project |
| CN113222564A (en) * | 2021-06-09 | 2021-08-06 | 合肥优尔电子科技有限公司 | Progress management system and method based on BIM system |
| CN113379324A (en) * | 2021-07-06 | 2021-09-10 | 山东电力工程咨询院有限公司 | Construction site whole-course monitoring method and system |
Non-Patent Citations (1)
| Title |
|---|
| 何敏杰 等: "基于模糊算法的施工进度动态分析模型 与进度预警机制", 土木工程与管理学报 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114452A (en) * | 2023-10-23 | 2023-11-24 | 中科云谷科技有限公司 | Method, processor, device and storage medium for determining construction scheme |
| CN117114452B (en) * | 2023-10-23 | 2024-01-09 | 中科云谷科技有限公司 | Method, processor, device and storage medium for determining construction scheme |
| CN117114922A (en) * | 2023-10-24 | 2023-11-24 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
| CN117114922B (en) * | 2023-10-24 | 2024-01-26 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115879642A (en) | Construction split prediction-based real-time sensing method for broadband installation progress | |
| CA3059918C (en) | Technician control system | |
| CN112734284B (en) | Flow industrial energy consumption optimization decision system and method for improving accuracy of evaluation result | |
| CN116415923B (en) | Intelligent gas work order implementation management method and Internet of things system and device | |
| CN116703009B (en) | Operation reference information generation method of photovoltaic power generation energy storage system | |
| KR101049405B1 (en) | Bridge asset management system | |
| CN114971356A (en) | Electric power engineering project progress prediction system and method | |
| KR20200007334A (en) | Apparatus and method for managing counselor schedule | |
| KR102411674B1 (en) | Method for providing financial service information | |
| CN111932106A (en) | Effective and practical cloud manufacturing task and service resource matching method | |
| CN108154276A (en) | Attendance analysis method based on image identification and machine learning | |
| CN117093822A (en) | Industrial brain data analysis platform based on industrial knowledge graph | |
| CN115511395B (en) | Method, device, equipment and storage medium for allocating prison positions | |
| CN116386813A (en) | Method, device, equipment and storage medium for balancing load between operations | |
| CN115689529A (en) | Labor management platform based on human resources | |
| CN113344443B (en) | Project process analysis and evaluation system and method based on big data | |
| CN115496628A (en) | Smart hotel management system | |
| CN114140241A (en) | Abnormity identification method and device for transaction monitoring index | |
| CN111275306B (en) | Elevator reconstruction evaluation method and elevator reconstruction evaluation system | |
| CN113449923A (en) | Multi-model object market quotation prediction method and device | |
| CN116432990B (en) | Collaborative filtering algorithm-based power task decision analysis method | |
| CN111178647A (en) | Method, system and computer storage medium for pushing work order | |
| CN111709594A (en) | Economic management data analysis system | |
| CN116090702B (en) | ERP data intelligent supervision system and method based on Internet of things | |
| CN117391644B (en) | Parameter adjustment method, device, equipment and medium in contract management process |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230331 |
|
| RJ01 | Rejection of invention patent application after publication |