CN116542491B - Artificial intelligence task scheduling method and system based on deep learning - Google Patents

Artificial intelligence task scheduling method and system based on deep learning Download PDF

Info

Publication number
CN116542491B
CN116542491B CN202310780766.5A CN202310780766A CN116542491B CN 116542491 B CN116542491 B CN 116542491B CN 202310780766 A CN202310780766 A CN 202310780766A CN 116542491 B CN116542491 B CN 116542491B
Authority
CN
China
Prior art keywords
personnel
repair
rush
evaluation index
road
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.)
Active
Application number
CN202310780766.5A
Other languages
Chinese (zh)
Other versions
CN116542491A (en
Inventor
欧乐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Qishan Technology Co ltd
Original Assignee
Shenzhen Qishan Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Qishan Technology Co ltd filed Critical Shenzhen Qishan Technology Co ltd
Priority to CN202310780766.5A priority Critical patent/CN116542491B/en
Publication of CN116542491A publication Critical patent/CN116542491A/en
Application granted granted Critical
Publication of CN116542491B publication Critical patent/CN116542491B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • 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
    • G06Q10/20—Administration of product repair or maintenance
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention discloses an artificial intelligence task scheduling method and system based on deep learning, which relate to the technical field of task scheduling and comprise a first data acquisition module, a first-level marking module, a second data acquisition module, a second-level marking module and a screening module; the first data acquisition module acquires historical record information of power failures with the same property of the first repair personnel to generate a first repair evaluation index; the first-level marking module is used for comparing the acquired first-aid repair evaluation index with a first-aid repair evaluation index reference threshold, marking first-aid repair personnel as high-optional personnel and low-optional personnel, and transmitting the high-optional personnel marks and the low-optional personnel marks to the screening module. According to the invention, the information of the power faults with the same property and the information of the power faults reached by the emergency repair personnel are comprehensively considered, the emergency repair personnel are accurately screened through the dispatching indexes, the intelligent, accurate and optimal dispatching of the emergency repair personnel is realized, and the efficiency of the power emergency repair is greatly improved.

Description

Artificial intelligence task scheduling method and system based on deep learning
Technical Field
The invention relates to the technical field of task scheduling, in particular to an artificial intelligence task scheduling method and system based on deep learning.
Background
The power rush repair refers to a process of rapidly scheduling rush repair personnel and resources so as to rapidly restore power supply when a power system fails or fails. Power repair is typically an urgent and complex task that requires quick and efficient locating of the cause of the fault and repair to minimize power interruption time and scope of impact.
When a user reports a power failure or power failure, a power company or a related mechanism receives the report and records the specific situation and position of the failure, a dispatching center analyzes the reason and the range of the failure according to the report content and decides to send proper rush repair personnel to the site, the rush repair personnel go to the failure site for site investigation and failure positioning, equipment, lines, transformers and the like may need to be checked, testing instruments and tools are used for determining the specific position and the property of the failure, and once the failure positioning is determined, the rush repair personnel can take corresponding measures to repair as soon as possible. This may include replacing faulty equipment, repairing damaged wires, reconnecting broken wires, and the like.
The prior art has the following defects: in the prior art, when task scheduling is performed on the emergency repair personnel, the emergency repair personnel are mostly scheduled according to experience by combining the relevant skills of the emergency repair personnel and the properties of power faults, the intelligent degree is low and the accurate optimal scheduling can not be realized by adopting the scheduling mode, the efficiency of power emergency repair can be reduced, and the practicability is poor.
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide an artificial intelligent task scheduling method and system based on deep learning.
In order to achieve the above object, the present invention provides the following technical solutions: an artificial intelligence task scheduling system based on deep learning comprises a first data acquisition module, a first-level marking module, a second data acquisition module, a second-level marking module and a screening module;
the first data acquisition module acquires the history record information of the power faults with the same properties of the emergency repair personnel, generates an emergency repair evaluation index and transmits the emergency repair evaluation index to the first-level marking module;
the first-level marking module is used for comparing the acquired first-aid repair evaluation index with a first-aid repair evaluation index reference threshold, marking first-aid repair personnel as high-optional personnel and low-optional personnel, and transmitting the high-optional personnel marks and the low-optional personnel marks to the screening module;
the second data acquisition module acquires information of the power failure position reached by the emergency repair personnel, generates a road condition assessment index and transmits the road condition assessment index to the secondary marking module;
the second-level marking module is used for comparing the acquired road condition evaluation index with a road condition evaluation index reference threshold value, marking the rush-repair personnel as high-response personnel and low-response personnel, and transmitting the high-response personnel marks and the low-response personnel marks to the screening module;
and the screening module screens out the rush-repair personnel with the high selectable personnel mark and the high reaction personnel mark at the same time, and selects the rush-repair personnel with the optimal scheduling from the screened rush-repair personnel.
Preferably, the historical record information of the power failures with the same property by the rush-repair personnel comprises the rush-repair rate and the failure determination time length of the power failures with the same property, and after the collection, the first data collection module respectively marks the rush-repair rate and the failure determination time length of the power failures with the same property asAnd->。
Preferably, the same-property power failure repair rateNamely, the success rate of the power faults with the same property is salvaged by a rush-repair personnel, and the obtained logic is as follows:
counting the power failure processing records of the similar types in the past by the emergency repair personnel, calibrating the total number of failure types similar to the target failure as Xa, and calibrating the number of times of emergency repair success in Xa as Xb, thereby obtaining the power failure emergency repair rate with the same propertyThe expression calculated is: />；
Fault determination durationThe average duration of the power faults with the same property is determined by emergency repair personnel, and the steps of obtaining are as follows:
s1: the time length of the rush-repair personnel going to the fault site for on-site investigation is marked as T1;
s2: the time length of fault diagnosis and positioning of the rush-repair personnel according to the information obtained by on-site investigation and collection is marked as T2;
s3: calibrating the time length for completing the repair plan of fault positioning to be T3;
s4: marking the time length for the repair personnel to execute repair work according to the repair plan as T4;
s5: calibrating the time length for performing fault repair verification after the repair work is completed as T5;
s6: calculating the duration of the single-time determination of the same-property power faults, and calibrating the duration of the single-time determination of the same-property power faults as T, wherein the expression of T calculation is as follows:；
after the time length of the electric power faults with the same property is obtained in a single time, the times of determining the faults by the emergency repair personnel and the time length corresponding to the determined faults are obtained, the time length corresponding to the determined faults is marked as Tu, and then the time length is determined by the faultsThe expression calculated is: />U represents the number of failure determination times, u=1, 2, 3, 4, … …, +.>，/>Is a positive integer.
Preferably, the power failure repair rate with the same property is obtainedAnd fault determination duration->After that, establishing a rush repair evaluation index +.>Generating a model and generating a rush repair evaluation index +.>The formula according to is:
in (1) the->、/>The repair rate of the power failure with the same property is +.>And fault determination duration->The weight factor coefficient of (2) is larger than 0.
Preferably, the obtained first-aid repair evaluation indexIndex->Comparing the reference threshold values, if the rush repair evaluation index is +.>Is greater than or equal to the first-aid repair evaluation index->The first-level marking module marks the first-aid repair personnel as high-choice personnel, and if the first-aid repair evaluation index is +.>Less than the first-aid repair evaluation index->And marking the emergency repair personnel as low selectable personnel through a first-level marking module by referring to the threshold value.
Preferably, the information of the power failure position reached by the rush-repair personnel comprises an arrival distance, a road surface leveling coefficient and a roadblock coefficient, and after acquisition, the arrival distance, the road surface leveling coefficient and the roadblock coefficient are respectively calibrated as、/>And。
Preferably, the distance of arrivalNamely the distance between the emergency repair personnel and the fault occurrence position, the position of the emergency repair personnel and the fault occurrence position are positioned through the millimeter wave radar, and the arrival distance +.>；
Road surface flatness coefficientNamely the ratio of the uneven pavement area to the road area, the steps of obtaining are as follows:
s1: acquiring data of a road by using a millimeter wave radar;
s2: the collected road data is imported into a computer, and data processing and analysis are carried out;
s3: defining a threshold value of the road surface unevenness according to the selected evaluation standard, and regarding the area of the road surface, the height difference of which exceeds the threshold value of the road surface unevenness, as unevenness according to the threshold value of the road surface unevenness;
s4: calculating the area of the area considered to be uneven according to the measured data;
s5: comparing the calculated uneven area with the total road area to obtain the ratio of the uneven area of the road surface to the road area;
s6: obtaining road surface flatness coefficient through ratio of road surface unevenness area to road surface area；
Roadblock coefficientThe logic obtained is as follows:
determining the length of the part of the road which is blocked and forbidden to pass due to the road construction at the position where the fault occurs by the rush-repair personnel through the millimeter wave radar, marking the length of the part of the road which is blocked and forbidden to pass due to the road construction at the position where the fault occurs by the rush-repair personnel as L1, determining the total length of the road at the position where the fault occurs by the rush-repair personnel through the millimeter wave radar, marking the total length of the road at the position where the fault occurs by the rush-repair personnel as L2, and obtaining the road barrier coefficientThe obtained calculation expression is:。
preferably, the distance of arrival is obtainedRoad surface flatness coefficient->Roadblock coefficient->After that, the road condition evaluation index is established>Generating a model and generating a road condition evaluation index +.>The formula according to is:
in (1) the->、/>、/>Distance of arrival +.>Road surface flatness coefficient->Roadblock coefficient->The values of the weight factor coefficients of (2) are all larger than 0;
the acquired road condition evaluation indexAnd road condition evaluation index->Comparing with a reference threshold value, if the road condition evaluation index is +.>Is greater than or equal to the road condition evaluation index->The first-aid repair personnel are marked as low-response personnel through the second-level marking module by referring to the threshold value, and if the road condition evaluation index is +.>Less than road condition evaluation index +.>And marking the emergency repair personnel as high-response personnel through a secondary marking module by referring to the threshold value.
Preferably, the screening module screens out the rush-repair personnel with the high selectable personnel marks and the high reactive personnel marks at the same time, and the rush-repair evaluation index of the screened rush-repair personnel is evaluatedAnd road condition evaluation index->Establishing an analysis model based on deep learning, generating a scheduling index, calibrating the scheduling index as DDZk according to the formula:
in (1) the->、/>Respectively evaluating indexes for rush repairAnd road condition evaluation index->The values of the preset proportion coefficients of the error correction factors are all larger than 0, A is an error correction factor, and the value is 0.9654;
after the scheduling index DDZk of the rush-repair personnel is obtained, the scheduling index DDZk generated by the rush-repair personnel is established into a data set P, and thenV represents the total number of scheduling indexes in the data set P, v is a positive integer, the scheduling indexes DDZk generated in the data set P are ordered in sequence, and the rush repair personnel corresponding to the maximum value of the scheduling indexes DDZk are screened out.
An artificial intelligence task scheduling method based on deep learning comprises the following steps:
collecting historical record information of power failures with the same property of the rush-repair personnel to generate a rush-repair evaluation index；
The obtained first-aid repair evaluation indexIndex->Comparing the reference threshold values, and marking the rush repair personnel as high selectable personnel and low selectable personnel;
collecting information of the emergency repair personnel reaching the power failure position, and generating a road condition assessment index；
The acquired road condition evaluation indexAnd road condition evaluation index->Comparing the reference threshold values, and marking the rush repair personnel as high-reaction personnel and low-reaction personnel;
screening out the rush-repair personnel with the high selectable personnel mark and the high reactive personnel mark, and selecting the rush-repair personnel with the optimal scheduling from the screened rush-repair personnel.
In the technical scheme, the invention has the technical effects and advantages that:
according to the invention, the rush-repair evaluation index is generated by collecting the historical record information of the power faults with the same property of the rush-repair personnel, the road condition evaluation index is generated by collecting the information of the power faults reached by the rush-repair personnel, the rush-repair evaluation index and the road condition evaluation index are combined to generate the scheduling index, the information of the power faults with the same property of the rush-repair personnel and the information of the power faults reached by the rush-repair personnel are comprehensively considered, the precise screening is carried out on the rush-repair personnel through the scheduling index, the intelligent, precise and optimal scheduling is carried out on the rush-repair personnel, and the efficiency of the power rush-repair is greatly improved.
Drawings
For a clearer description of embodiments of the present application or of the solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments described in the present invention, and that other drawings may be obtained according to these drawings for a person skilled in the art.
FIG. 1 is a schematic block diagram of an artificial intelligence task scheduling method and system based on deep learning.
FIG. 2 is a flow chart of a method and system for scheduling artificial intelligence tasks based on deep learning.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
The invention provides an artificial intelligence task scheduling system based on deep learning as shown in figure 1, which comprises a first data acquisition module, a first-level marking module, a second data acquisition module, a second-level marking module and a screening module;
the first data acquisition module acquires the history record information of the power faults with the same properties of the emergency repair personnel, generates an emergency repair evaluation index and transmits the emergency repair evaluation index to the first-level marking module;
the historical record information of the power failures with the same property by the rush-repair personnel comprises the rush-repair rate and the failure determination time length of the power failures with the same property, and after the collection, the first data collection module respectively marks the rush-repair rate and the failure determination time length of the power failures with the same property asAnd->；
The repair rate of the electric power faults with the same property, namely the success rate of the repair personnel for repairing the electric power faults with the same property, and checking the treatment records of the electric power faults with similar types in the past, particularly the types of the faults similar to the target faults, if the repair personnel successfully solve the electric power faults with the same property in the past, the repair personnel has experience and knowledge for treating the faults, and the more times of the repair are successful, the thicker the experience and knowledge for treating the faults are;
electric power failure rush-repair rate of the same propertyThe logic obtained is as follows:
counting the power failure processing records of the similar types in the past by the emergency repair personnel, calibrating the total number of failure types similar to the target failure as Xa, and calibrating the number of times of emergency repair success in Xa as Xb, thereby obtaining the power failure emergency repair rate with the same propertyThe expression calculated is: />；
Fault determination durationThe average duration of the power faults with the same property is determined by emergency repair personnel, and the steps of obtaining are as follows:
s1: the time length of the rush-repair personnel going to the fault site for on-site investigation is marked as T1;
the emergency repair personnel can check affected equipment, lines, transformers and the like, and collect necessary information such as fault phenomena, observed problems and the like;
s2: the time length of fault diagnosis and positioning of the rush-repair personnel according to the information obtained by on-site investigation and collection is marked as T2;
the possible reasons of the faults are analyzed by the rush repair personnel, and the test instrument and the test equipment are used for measurement and detection so as to determine the specific positions of the fault points;
s3: calibrating the time length for completing the repair plan of fault positioning to be T3;
the rush repair personnel can determine necessary repair measures, required equipment and materials, and make work flow and time schedule and the like;
s4: marking the time length for the repair personnel to execute repair work according to the repair plan as T4;
the repair personnel can replace damaged equipment, repair circuits, adjust parameters and the like to solve faults and restore power supply;
s5: calibrating the time length for performing fault repair verification after the repair work is completed as T5;
the repair personnel can test and check the repaired equipment and system to ensure that the fault is solved and normal operation is restored;
s6: calculating the duration of the single-time determination of the same-property power faults, and calibrating the duration of the single-time determination of the same-property power faults as T, wherein the expression of T calculation is as follows:；
after the time length of the electric power faults with the same property is obtained in a single time, the times of determining the faults by the emergency repair personnel and the time length corresponding to the determined faults are obtained, the time length corresponding to the determined faults is marked as Tu, and then the time length is determined by the faultsThe expression calculated is: />U represents the number of failure determination times, u=1, 2, 3, 4, … …, +.>，/>Is a positive integer;
the power failure repair rate with the same property is obtainedAnd fault determination duration->Then, a first-aid repair evaluation index generation model is established to generate a first-aid repair evaluation index ++>The formula according to is:
in (1) the->、/>The repair rate of the power failure with the same property is +.>And fault determination duration->Weight factor series of (2)
The number and the value are all larger than 0, and the weight factors in the formula are used for balancing the duty ratio of each item of data in the formula, so that the accuracy of a calculation result is promoted;
the formula shows that the higher the power failure repair rate of the same property of the repair personnel is, the shorter the failure determination time is, namely the repair evaluation indexThe larger the expression value of the system shows that the higher the probability of the success of the emergency repair personnel to the fault, the lower the emergency repair rate of the power faults with the same property by the emergency repair personnel, and the longer the fault determination time length, namely the emergency repair evaluation index ∈ ->The smaller the expression value of the fault is, the smaller the probability that the emergency repair personnel succeeds in repairing the fault is;
the first-level marking module is used for comparing the acquired first-aid repair evaluation index with a first-aid repair evaluation index reference threshold, marking first-aid repair personnel as high-optional personnel and low-optional personnel, and transmitting the high-optional personnel marks and the low-optional personnel marks to the screening module;
the obtained first-aid repair evaluation indexIndex->Comparing the reference threshold values, if the rush repair evaluation index is +.>Is greater than or equal to the first-aid repair evaluation index->The reference threshold value shows that the probability of the success of the rush repair of the fault by the rush repair personnel is high, marking the emergency repair personnel as high selectable personnel through the first-level marking module, and if the emergency repair evaluation index is +.>Less than the first-aid repair evaluation index->The first-level marking module is used for marking the first-level repair personnel as low-selectable personnel if the first-level repair personnel is used for repairing the fault successfully;
the second data acquisition module acquires information of the power failure position reached by the emergency repair personnel, generates a road condition assessment index and transmits the road condition assessment index to the secondary marking module;
the information of the power failure position reached by the emergency repair personnel comprises an arrival distance, a road surface leveling coefficient and a roadblock coefficient, and after acquisition, the arrival distance, the road surface leveling coefficient and the roadblock coefficient are respectively calibrated as、/>And +.>；
Distance of arrivalNamely the distance between the emergency repair personnel and the fault occurrence position, the position of the emergency repair personnel and the fault occurrence position are positioned through the millimeter wave radar, and the arrival distance +.>；
Road surface flatness coefficientNamely the ratio of the uneven pavement area to the road area, the steps of obtaining are as follows:
s1: acquiring data of a road by using a millimeter wave radar;
measuring elevation or height information of the road surface;
s2: the collected road data is imported into a computer, and data processing and analysis are carried out;
analyzing and extracting the road surface by using image processing and computer vision technology;
s3: defining a threshold value of road surface unevenness according to the selected evaluation standard (determining a threshold value of the road surface height difference to judge whether the road surface is uneven according to international standard or local regulation), and regarding an area of the road surface with the height difference exceeding the threshold value of the road surface unevenness as unevenness according to the threshold value of the road surface unevenness;
s4: calculating the area of the area considered to be uneven according to the measured data;
measuring the area of the region by using an image processing algorithm or GIS software, and adding the areas of all the regions defined as uneven regions to obtain the total uneven area;
s5: comparing the calculated uneven area with the total road area to obtain the ratio of the uneven area of the road surface to the road area;
s6: obtaining road surface flatness coefficient through ratio of road surface unevenness area to road surface area；
Roadblock coefficientThe logic obtained is as follows:
determining the length of the part of the road which is blocked and forbidden to pass due to the road construction at the position where the fault occurs by the rush-repair personnel through the millimeter wave radar, marking the length of the part of the road which is blocked and forbidden to pass due to the road construction at the position where the fault occurs by the rush-repair personnel as L1, determining the total length of the road at the position where the fault occurs by the rush-repair personnel through the millimeter wave radar, marking the total length of the road at the position where the fault occurs by the rush-repair personnel as L2, and obtaining the road barrier coefficientThe obtained calculation expression is:；
acquiring arrival distanceRoad surface flatness coefficient->Roadblock coefficient->After that, the road condition evaluation index is established>Generating a model and generating a road condition evaluation index +.>The formula according to is:
in (1) the->、/>、/>Distance of arrival +.>Road surface flatness coefficient->Roadblock coefficient->The weight factor of the formula is greater than 0, wherein the weight factor is used for balancing the duty ratio of each item of data in the formula, so that the accuracy of a calculation result is promoted;
the formula shows that the longer the arrival distance is, the larger the road surface flatness coefficient is, the larger the roadblock coefficient is, namely the road condition evaluation indexThe larger the expression value of the system is, the longer the reaction time of the emergency repair personnel to go to the fault occurrence place is, the less timely the emergency repair personnel to go to the fault occurrence place is, the shorter the arrival distance is, the smaller the road surface leveling coefficient is, the smaller the road barrier coefficient is, namely the road condition evaluation index +.>The smaller the expression value of the system is, the shorter the reaction time for the emergency repair personnel to go to the fault occurrence place is, and the more timely the emergency repair personnel to go to the fault occurrence place is;
the secondary marking module is used for obtaining the road condition evaluation indexAnd road condition evaluation index->Comparing the reference threshold values, marking the rush-repair personnel as high-reaction personnel and low-reaction personnel, and transmitting the high-reaction personnel marks and the low-reaction personnel marks to a screening module;
the acquired road condition evaluation indexAnd road condition evaluation index->Comparing with a reference threshold value, if the road condition evaluation index is +.>Is greater than or equal to the road condition evaluation index->The reference threshold value indicates that the reaction time of the emergency repair personnel to the fault occurrence position is long, indicates that the emergency repair personnel to the fault occurrence position is not timely, the rush repair personnel are marked as low-response personnel through the secondary marking module, and if the road condition assessment index is +.>Less than road condition evaluation index +.>The reference threshold value indicates that the reaction time for the emergency repair personnel to go to the fault occurrence place is short, and indicates that the emergency repair personnel go to the fault occurrence place timely, and the emergency repair personnel are marked as high-reaction personnel through the secondary marking module;
the screening module screens out the rush-repair personnel with the high selectable personnel mark and the high reaction personnel mark at the same time, and selects the rush-repair personnel with the optimal scheduling from the screened rush-repair personnel;
the rush-repair personnel with the high selectable personnel marks and the high reactive personnel marks are screened out through the screening module, and the rush-repair personnel with the high selectable personnel marks and the high reactive personnel marks are screened outIs an index of first-aid repair assessment of first-aid repair personnelAnd road condition evaluation index->
Establishing an analysis model based on deep learning, generating a scheduling index DDZk, calibrating the scheduling index to be DDZk, and according to the formula:
in the method, in the process of the invention,、/>evaluation index for rush repair respectively>And road condition evaluation index->The values of the preset proportion coefficients of the error correction factors are all larger than 0, A is an error correction factor, and the value is 0.9654;
the emergency repair personnel with the high selectable personnel marks and the high reactive personnel marks are screened out and then the scheduling index calculation is carried out, so that the accurate screening can be realized, the screening times are greatly reduced, and the screening efficiency is improved;
the formula shows that the larger the first-aid repair evaluation index is, the smaller the road condition evaluation index is, namely the larger the representation value of the scheduling index DDZk is, the more the first-aid repair personnel accords with the scheduling standard, the smaller the first-aid repair evaluation index is, the larger the road condition evaluation index is, namely the smaller the representation value of the scheduling index DDZk is, the more the first-aid repair personnel does not accord with the scheduling standard;
after the scheduling index DDZk of the rush-repair personnel is obtained, the scheduling index DDZk generated by the rush-repair personnel is established into a data set P, and thenV represents the total number of scheduling indexes in the data set P, v is a positive integer, the scheduling indexes DDZk generated in the data set P are ordered according to the sequence, and the rush-repair personnel corresponding to the maximum value of the scheduling indexes DDZk are screened out, so that the rush-repair personnel can be accurately and optimally scheduled, the intelligent degree is higher, and the power rush-repair efficiency can be greatly improved;
the invention provides an artificial intelligence task scheduling method based on deep learning as shown in fig. 2, which comprises the following steps:
collecting historical record information of power failures with the same property of the rush-repair personnel to generate a rush-repair evaluation index；
The obtained first-aid repair evaluation indexIndex->Comparing the reference threshold values, and marking the rush repair personnel as high selectable personnel and low selectable personnel;
collecting information of the emergency repair personnel reaching the power failure position, and generating a road condition assessment index；
The acquired road condition evaluation indexAnd road condition evaluation index->Comparing the reference threshold values, and marking the rush repair personnel as high-reaction personnel and low-reaction personnel;
screening out the rush-repair personnel with the high selectable personnel mark and the high reaction personnel mark at the same time, and selecting the rush-repair personnel with the optimal scheduling from the screened rush-repair personnel;
the embodiment of the invention provides an artificial intelligence task scheduling method based on deep learning, which is realized by the artificial intelligence task scheduling system based on deep learning, and the concrete method and the flow of the artificial intelligence task scheduling method based on deep learning are detailed in the embodiment of the artificial intelligence task scheduling system based on deep learning, and are not repeated here.
According to the invention, the rush-repair evaluation index is generated by collecting the historical record information of the power faults with the same property of the rush-repair personnel, the road condition evaluation index is generated by collecting the information of the power faults reached by the rush-repair personnel, the rush-repair evaluation index and the road condition evaluation index are combined to generate the scheduling index, the information of the power faults with the same property of the rush-repair personnel and the information of the power faults reached by the rush-repair personnel are comprehensively considered, the precise screening is carried out on the rush-repair personnel through the scheduling index, the intelligent, precise and optimal scheduling is carried out on the rush-repair personnel, and the efficiency of the power rush-repair is greatly improved.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
While certain exemplary embodiments of the present invention have been described above by way of illustration only, it will be apparent to those of ordinary skill in the art that modifications may be made to the described embodiments in various different ways without departing from the spirit and scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive of the scope of the invention, which is defined by the appended claims.
It is noted that relational terms such as first and second, and the like, if any, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on 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 application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (2)

1. The artificial intelligence task scheduling system based on deep learning is characterized by comprising a first data acquisition module, a first-level marking module, a second data acquisition module, a second-level marking module and a screening module;
the first data acquisition module acquires historical record information of power failures with the same property and rush-repair personnel to generate a rush-repair evaluation indexAnd the rush repair evaluation index ++>Transmitting to a first-level marking module;
the historical record information of the power failures with the same property by the rush-repair personnel comprises the rush-repair rate and the failure determination time length of the power failures with the same property, and after the data are collected, the first data collection module is used for determining the rush-repair rate and the failure determination of the power failures with the same propertyThe fixed time periods are respectively calibrated asAnd->；
Electric power failure rush-repair rate of the same propertyNamely, the success rate of the power faults with the same property is salvaged by a rush-repair personnel, and the obtained logic is as follows:
counting the power failure processing records of the similar types in the past by the emergency repair personnel, calibrating the total number of failure types similar to the target failure as Xa, and calibrating the number of times of emergency repair success in Xa as Xb, thereby obtaining the power failure emergency repair rate with the same propertyThe expression calculated is: />；
Fault determination durationThe average duration of the power faults with the same property is determined by emergency repair personnel, and the steps of obtaining are as follows:
s1: the time length of the rush-repair personnel going to the fault site for on-site investigation is marked as T1;
s2: the time length of fault diagnosis and positioning of the rush-repair personnel according to the information obtained by on-site investigation and collection is marked as T2;
s3: calibrating the time length for completing the repair plan of fault positioning to be T3;
s4: marking the time length for the repair personnel to execute repair work according to the repair plan as T4;
s5: calibrating the time length for performing fault repair verification after the repair work is completed as T5;
s6: calculating a time length for determining the same-property power faults at a timeAnd (3) calibrating the duration of the single-time determined power faults with the same property as T, and expressing the calculation of T as follows:；
after the time length of the electric power faults with the same property is obtained in a single time, the times of determining the faults by the emergency repair personnel and the time length corresponding to the determined faults are obtained, the time length corresponding to the determined faults is marked as Tu, and then the time length is determined by the faultsThe expression calculated is:n, u represents the number of failure determination times, u=1, 2, 3, 4, … …, n being a positive integer;
the power failure repair rate with the same property is obtainedAnd fault determination duration->After that, establishing the rush repair evaluation indexGenerating a model and generating a rush repair evaluation index +.>The formula according to is:
in (1) the->、/>Respectively the same-property power failure rush repairRate->And fault determination duration->The values of the weight factor coefficients of (2) are all larger than 0;
the first-level marking module is used for obtaining the first-aid repair evaluation indexIndex->Comparing the reference threshold values, marking the rush-repair personnel as high-choice personnel and low-choice personnel, and transmitting the high-choice personnel marks and the low-choice personnel marks to a screening module;
the obtained first-aid repair evaluation indexIndex->Comparing the reference threshold values, and if the emergency repair evaluation index is highIs greater than or equal to the first-aid repair evaluation index->The first-level marking module marks the first-aid repair personnel as high-choice personnel, and if the first-aid repair evaluation index is +.>Less than the first-aid repair evaluation index->With reference to the threshold value, the first-level marking module marks the first-aid repair personnel as low selectable personnelA member;
the second data acquisition module acquires information of the power failure position reached by the emergency repair personnel and generates a road condition assessment indexAnd evaluate the road condition index +.>Transmitting to a secondary marking module;
the information of the power failure position reached by the emergency repair personnel comprises an arrival distance, a road surface leveling coefficient and a roadblock coefficient, and after acquisition, the arrival distance, the road surface leveling coefficient and the roadblock coefficient are respectively calibrated as、/>And +.>；
Distance of arrivalNamely the distance between the emergency repair personnel and the fault occurrence position, the position of the emergency repair personnel and the fault occurrence position are positioned through the millimeter wave radar, and the arrival distance +.>；
Road surface flatness coefficientNamely the ratio of the uneven pavement area to the road area, the steps of obtaining are as follows:
s1: acquiring data of a road by using a millimeter wave radar;
s2: the collected road data is imported into a computer, and data processing and analysis are carried out;
s3: defining a threshold value of the road surface unevenness according to the selected evaluation standard, and regarding the area of the road surface, the height difference of which exceeds the threshold value of the road surface unevenness, as unevenness according to the threshold value of the road surface unevenness;
s4: calculating the area of the area considered to be uneven according to the measured data;
s5: comparing the calculated uneven area with the total road area to obtain the ratio of the uneven area of the road surface to the road area;
s6: obtaining road surface flatness coefficient through ratio of road surface unevenness area to road surface area；
Roadblock coefficientThe logic obtained is as follows:
determining the length of the part of the road which is blocked and forbidden to pass due to the road construction at the position where the fault occurs by the rush-repair personnel through the millimeter wave radar, marking the length of the part of the road which is blocked and forbidden to pass due to the road construction at the position where the fault occurs by the rush-repair personnel as L1, determining the total length of the road at the position where the fault occurs by the rush-repair personnel through the millimeter wave radar, marking the total length of the road at the position where the fault occurs by the rush-repair personnel as L2, and obtaining the road barrier coefficientThe obtained calculation expression is:；
acquiring arrival distanceRoad surface flatness coefficient->Roadblock coefficient->Then, establishing road condition evaluation indexGenerating a model and generating a road condition evaluation index +.>The formula according to is:
in (1) the->、/>、/>Distance of arrival +.>Road surface flatness coefficient->Roadblock coefficient->The values of the weight factor coefficients of (2) are all larger than 0;
the secondary marking module is used for obtaining the road condition evaluation indexAnd road condition evaluation index->Comparing the reference threshold values, and marking the emergency repair personnel as high-reaction personnel and low-reaction personnelPersonnel, and transmitting the high-reaction personnel marks and the low-reaction personnel marks to a screening module;
the acquired road condition evaluation indexAnd road condition evaluation index->Comparing with a reference threshold, if the road condition evaluation index isIs greater than or equal to the road condition evaluation index->The first-aid repair personnel are marked as low-response personnel through the second-level marking module by referring to the threshold value, and if the road condition evaluation index is +.>Less than road condition evaluation index +.>Marking the rush repair personnel as high-response personnel through a second-level marking module by referring to the threshold value;
the screening module screens out the rush-repair personnel with the high selectable personnel mark and the high reaction personnel mark at the same time, and selects the rush-repair personnel with the optimal scheduling from the screened rush-repair personnel;
screening out the rush-repair personnel with the high selectable personnel mark and the high reactive personnel mark through a screening module, and screening out the rush-repair evaluation index of the rush-repair personnelAnd road condition evaluation index->Establishing an analysis model based on deep learning, generating a scheduling index, calibrating the scheduling index as DDZk according to the formula:
in (1) the->、/>Evaluation index for rush repair respectively>And road condition evaluation index->The values of the preset proportion coefficients of the error correction factors are all larger than 0, A is an error correction factor, and the value is 0.9654;
after the scheduling index DDZk of the rush-repair personnel is obtained, the scheduling index DDZk generated by the rush-repair personnel is established into a data set P, and thenV represents the total number of scheduling indexes in the data set P, v is a positive integer, the scheduling indexes DDZk generated in the data set P are ordered in sequence, and the rush repair personnel corresponding to the maximum value of the scheduling indexes DDZk are screened out.
2. An artificial intelligence task scheduling method based on deep learning, which is realized by the artificial intelligence task scheduling system based on deep learning as claimed in claim 1, and is characterized by comprising the following steps:
collecting historical record information of power failures with the same property of the rush-repair personnel to generate a rush-repair evaluation index；
The obtained first-aid repair evaluation indexIndex->Comparing the reference threshold values, and marking the rush repair personnel as high selectable personnel and low selectable personnel;
collecting information of the emergency repair personnel reaching the power failure position, and generating a road condition assessment index；
The acquired road condition evaluation indexAnd road condition evaluation index->Comparing the reference threshold values, and marking the rush repair personnel as high-reaction personnel and low-reaction personnel;
screening out the rush-repair personnel with the high selectable personnel mark and the high reactive personnel mark, and selecting the rush-repair personnel with the optimal scheduling from the screened rush-repair personnel.
CN202310780766.5A 2023-06-29 2023-06-29 Artificial intelligence task scheduling method and system based on deep learning Active CN116542491B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310780766.5A CN116542491B (en) 2023-06-29 2023-06-29 Artificial intelligence task scheduling method and system based on deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310780766.5A CN116542491B (en) 2023-06-29 2023-06-29 Artificial intelligence task scheduling method and system based on deep learning

Publications (2)

Publication Number Publication Date
CN116542491A CN116542491A (en) 2023-08-04
CN116542491B true CN116542491B (en) 2024-03-22

Family

ID=87454505

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310780766.5A Active CN116542491B (en) 2023-06-29 2023-06-29 Artificial intelligence task scheduling method and system based on deep learning

Country Status (1)

Country Link
CN (1) CN116542491B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105069555A (en) * 2015-07-22 2015-11-18 广东电网有限责任公司中山供电局 Resource scheduling method and resource scheduling system for first-aid repair of power grid
CN112884185A (en) * 2021-03-25 2021-06-01 广东科学技术职业学院 Distribution network resource first-aid repair optimal scheduling method based on tabu search algorithm
CN112966882A (en) * 2021-04-15 2021-06-15 四川中电启明星信息技术有限公司 Power distribution network scheduling method based on space-time global matching
CN113077161A (en) * 2021-04-14 2021-07-06 华北电力大学 Emergency repair decision method for emergency robot in power distribution room
CN114372687A (en) * 2021-12-28 2022-04-19 浪潮通信信息系统有限公司 Command and scheduling method, device, equipment and product for fault processing

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105069555A (en) * 2015-07-22 2015-11-18 广东电网有限责任公司中山供电局 Resource scheduling method and resource scheduling system for first-aid repair of power grid
CN112884185A (en) * 2021-03-25 2021-06-01 广东科学技术职业学院 Distribution network resource first-aid repair optimal scheduling method based on tabu search algorithm
CN113077161A (en) * 2021-04-14 2021-07-06 华北电力大学 Emergency repair decision method for emergency robot in power distribution room
CN112966882A (en) * 2021-04-15 2021-06-15 四川中电启明星信息技术有限公司 Power distribution network scheduling method based on space-time global matching
CN114372687A (en) * 2021-12-28 2022-04-19 浪潮通信信息系统有限公司 Command and scheduling method, device, equipment and product for fault processing

Also Published As

Publication number Publication date
CN116542491A (en) 2023-08-04

Similar Documents

Publication Publication Date Title
Tseng et al. Determination of burn‐in parameters and residual life for highly reliable products
CN104461896B (en) Aerospace system key software evaluation method based on credible attribute
CN101738991B (en) Method for detecting out-of-specification quality of product and estimating actually measured value of product
CN1862278A (en) Method and system for predicting remaining life for motors featuring on-line insulation condition monitor
CN101272580B (en) Self-adapting mobile base station system reliability estimation method based on feedback
CN103400310A (en) Method for evaluating power distribution network electrical equipment state based on historical data trend prediction
CN104218570A (en) Method and system for online evaluating overall measuring errors of electric energy measuring device
CN108287327A (en) Metering automation terminal fault diagnostic method based on Bayes's classification
CN110276385A (en) Mechanical part remaining life prediction technique based on similitude
CN113721182B (en) Method and system for evaluating reliability of online performance monitoring result of power transformer
CN116542491B (en) Artificial intelligence task scheduling method and system based on deep learning
CN111553581B (en) Equipment maintainability evaluation model based on entropy value
CN110991793A (en) Aviation security equipment identification resource allocation method
CN110288325A (en) A kind of construction problem amelioration method
US8103476B2 (en) Abnormal simulation signal analysis methods and abnormal signal simulation analysis module for 4˜20mA instrumental system
KR20230082887A (en) Apparatus for predicting equipment failure using learning data based on maintenance history and method thereof
Chen et al. The effect of linear regression modeling approaches on determining facility wide energy savings
Hao et al. Review on Verification and Validation technology in integrated health management system
CN105303315B (en) A kind of power equipment reliability appraisal procedure counted and maintenance randomness influences
CN111090037A (en) Reliability detection method for instrument control card
KR101950584B1 (en) Comparison test method of measurement devices
CN106708638A (en) System error detection method and apparatus
Grbac et al. Quantifying value of adding inspection effort early in the development process: A case study
CN105656453A (en) Optical fiber current transducer random noise real-time filtering method based on time sequence
Lopes et al. Quantification of uncertainty of performance measures using graph theory

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
GR01 Patent grant
GR01 Patent grant