CN117057466A - City management component problem inspection method and system - Google Patents

City management component problem inspection method and system Download PDF

Info

Publication number
CN117057466A
CN117057466A CN202311027025.6A CN202311027025A CN117057466A CN 117057466 A CN117057466 A CN 117057466A CN 202311027025 A CN202311027025 A CN 202311027025A CN 117057466 A CN117057466 A CN 117057466A
Authority
CN
China
Prior art keywords
component
case
components
probability
attribute
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
Application number
CN202311027025.6A
Other languages
Chinese (zh)
Inventor
尹荣鹏
杨建民
刘海明
刘福辉
张啸
马述杰
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.)
Shandong Taihua Smart City Service Co ltd
Taihua Wisdom Industry Group Co Ltd
Original Assignee
Shandong Taihua Smart City Service Co ltd
Taihua Wisdom Industry Group 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 Shandong Taihua Smart City Service Co ltd, Taihua Wisdom Industry Group Co Ltd filed Critical Shandong Taihua Smart City Service Co ltd
Priority to CN202311027025.6A priority Critical patent/CN117057466A/en
Publication of CN117057466A publication Critical patent/CN117057466A/en
Pending legal-status Critical Current

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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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
    • G06Q10/20—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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • 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
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/60—Planning or developing urban green infrastructure

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Software Systems (AREA)
  • Development Economics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Educational Administration (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Game Theory and Decision Science (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a method and a system for inspecting problems of urban management components, which relate to the technical field of urban management, and are used for calculating the association degree of component attributes and case attributes with problems of the components based on historical component case data of urban management, and screening the component attributes and the case attributes according to the association degree to form a data set; training a prediction model by utilizing a data set; predicting the probability of occurrence of problems of all components through a trained prediction model, dividing key components, high-risk components and common components according to the probability, and respectively performing component inspection and verification; the method extracts the attribute with strong relevance to the occurrence of the problem of the component based on the component in the city management platform and the case information of the component, forms the data set of the problem of the component, trains a model through the data set, is used for predicting the probability of the problem of the component in a certain day in the future, and guides the inspection work to be more effectively implemented in a targeted manner based on the probability.

Description

City management component problem inspection method and system
Technical Field
The application belongs to the technical field of urban management, and particularly relates to a method and a system for inspecting problems of urban management components.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
With the deep progress of construction of smart cities and urban management platforms in recent years, urban component management is becoming more and more important as an important component of smart urban management. With the improvement of urban management level, aiming at component management, the problem can be found more timely, the problem can be processed more rapidly, and higher requirements are provided for patrol managers.
The management of the components is carried out before, namely the information collector can carry out daily inspection according to the inspection route, the responsibility area of the information collector is inspected, and each component in the area is inspected. When a damage or other abnormal situation is found on the component, the problem is reported to the component, and then a professional department personnel is dispatched by the command center to deal with the problem.
The manual part inspection mode has the following defects: firstly, all components in a daily responsibility area of an information collector need to be inspected once, the workload is great, and the situation that manpower is insufficient and inspection is not finished exists; secondly, a large number of parts are required to be inspected repeatedly every day, so that the loss of the parts is easy to occur, and the situation that the remote parts are missed occurs; thirdly, if the information collector misses the component, the component can not be found and processed even if the problem occurs for a long time, and accident hidden trouble is easily caused.
Disclosure of Invention
In order to overcome the defects of the prior art, the application provides a method and a system for inspecting the problems of a city management component, which are based on components in a city management platform and case information of the components, extract attributes with strong relevance to the occurrence of problems of the components, form a data set of the problems of the components, train a model through the data set, and predict the probability of the occurrence of the problems of the components in a certain day in the future, and guide inspection work to be implemented more efficiently and specifically based on the probability.
To achieve the above object, one or more embodiments of the present application provide the following technical solutions:
the first aspect of the application provides a method for inspecting problems of urban management components.
A method for inspecting problems of an urban management component, comprising:
calculating the association degree of the component attribute and the case attribute with the problem of the component based on the historical component case data of city management, and screening the component attribute and the case attribute according to the association degree to form a data set;
training a prediction model by utilizing a data set, wherein the prediction model is used for predicting the probability of a problem of a component;
and predicting the probability of occurrence of problems of all the components through a trained prediction model, dividing key components, high-risk components and common components according to the probability, and respectively performing component inspection and verification.
Further, the component attributes include: component number, component name, component major class, major class number, component minor class, minor class number, component census time, responsible component, responsible department number, rights department number, maintenance department number, component material, component longitude, component latitude, location description;
the case attributes include: case number, case type, case major class number, case minor class number, problem type number, case occurrence position longitude and latitude, reporting problem time, reporting person, case state, case accessory, case description and address description.
Further, the calculating the association degree of the component attribute and the case attribute with the component occurrence problem specifically includes:
according to historical component case data, two attributes are added: reporting whether the component has a case or not and the normal working time of the component;
and calculating the association degree of all the attributes and whether the component has the case report attribute or not based on Scikit-learn.
Further, the screening component attribute and case attribute according to the association degree specifically includes: and taking a predetermined number of attributes according to the sequence of the association degree from large to small to form a data set.
Further, the prediction model takes a component as an input and outputs the probability of a problem on the same day.
Further, the judging conditions of the key parts in the key part list are as follows:
means for exceeding a preset first threshold value in probability of occurrence of a problem on the same day;
the judging conditions of the high-risk components in the high-risk component list are as follows:
the probability of occurrence of problems in the continuous T days exceeds a first threshold, the probability of occurrence of problems in the same day exceeds a second threshold, no record of the problems is reported, and T is the preset number of days;
wherein the first threshold is less than a second threshold; two thresholds are set based on the accuracy and recall of the prediction model after training.
Further, the method further comprises the following steps: periodically acquiring new data, and re-constructing a data set, training a prediction model and setting a threshold value.
A second aspect of the present application provides a system for problem inspection of urban management components.
A city management component problem inspection system comprises a data set construction module, a model training module and a component inspection module:
a dataset construction module configured to: calculating the association degree of the component attribute and the case attribute with the problem of the component based on the historical component case data of city management, and screening the component attribute and the case attribute according to the association degree to form a data set;
a model training module configured to: training a prediction model by utilizing a data set, wherein the prediction model is used for predicting the probability of a problem of a component;
a component inspection module configured to: and predicting the probability of occurrence of problems of all the components through a trained prediction model, dividing key components, high-risk components and common components according to the probability, and respectively performing component inspection and verification.
A third aspect of the present application provides a computer-readable storage medium having stored thereon a program which, when executed by a processor, implements steps in a method for problem inspection of urban management components according to the first aspect of the present application.
A fourth aspect of the present application provides an electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, the processor implementing the steps in a method for problem inspection of urban management components according to the first aspect of the present application when the program is executed.
The one or more of the above technical solutions have the following beneficial effects:
the application provides a method and a system for inspecting problems of urban management components, which are based on components in an urban management platform and case information of the components, extract attributes with strong relevance to problems of the components, form a data set of the problems of the components, train a model through the data set and are used for predicting the probability of the problems of the components in a certain day in the future, and guide inspection work based on the probability to be more effectively implemented.
According to the method, the values of the first threshold and the second threshold are adjusted according to the precision and the recall rate of the trained model, and trade-off is made between the precision and the recall rate, so that the parts with problems are predicted as much as possible.
The application divides the components into key components, high-risk components and common components, executes different inspection strategies for different types of components, reduces the workload, improves the inspection efficiency, and can discover and process problematic components earlier and more timely; for common components, periodic whole inspection achieves the best balance between reducing workload and component problem detection.
Additional aspects of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application.
Fig. 1 is a flow chart of a method of a first embodiment.
Fig. 2 is a diagram showing an example of the degree of association of the first embodiment.
Fig. 3 is a flowchart of the first embodiment parts list construction.
FIG. 4 is a graph of accuracy and recall versus threshold for the first embodiment.
Detailed Description
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Term interpretation:
information collector: is a personnel in the urban management department, which can patrol outdoors, collect the problems in the city and report the problems to the command center.
Responsibility area: refers to the patrol area for which the information collector is responsible.
Parts: refers to a management component in a digital city management information system in national standard GB/T30428.
A first threshold value: the probability of the problem of the prediction model prediction component exceeds the threshold value, and the prediction model prediction component is judged to be a key component and needs key inspection; this threshold is smaller and can be set to 40%.
A second threshold value: when the probability of the occurrence of problems of the prediction model prediction component exceeds the threshold value, judging as a suspected high-risk component, and further judging the high risk; this value is greater and can be set to 80%.
Key parts: the method refers to a part with the probability of occurrence of problems larger than a first threshold value, and the part is important to pay attention to when the part is required to be patrolled.
High-risk component: means that the continuous T-day component is a key component, the probability of the current day calculation problem is larger than a second threshold value, and no reporting problem exists; the probability of occurrence of problems of the components on the same day is high, and a command center is required to assign a special person to check.
Example 1
In one or more embodiments, a method for inspecting a problem of an urban management component is disclosed, as shown in fig. 1, including the steps of:
step S1: calculating the association degree of the component attribute and the case attribute with the problem of the component based on the historical component case data of city management, and screening the component attribute and the case attribute according to the association degree to form a data set;
step S2: training a prediction model by utilizing a data set, wherein the prediction model is used for predicting the probability of a problem of a component;
step S3: and predicting the probability of occurrence of problems of all the components through a trained prediction model, dividing key components, high-risk components and common components according to the probability, and respectively performing component inspection and verification.
The following describes in detail the implementation procedure of a method for inspecting problems of urban management components according to this embodiment.
The present embodiment is divided into three parts: the first part is to screen out the attribute with strong relevance according to the attribute of the urban management component and the information attribute of the case, and construct a data set; the second part is a training predictive model; the third part is application of a prediction model, namely, a key part list and a high-risk part list are constructed based on the probability of part occurrence problems, so as to guide the patrol work.
First part building data set
The components are management components in a digital city management information system in national standard GB/T30428, so that the component attributes are the same, but the component types of each city are different, the cases of different component types are different, and the actual attributes of the cases are also different, so that the city management system of each city needs to construct a unique data set according to the related attributes of a specific city to train a prediction model; the data processing and training modes are the same, but the data sets are different, the trained prediction models are also different, the prediction models between cities cannot be used mutually, and the specific construction method is as follows:
(1) The method comprises the steps of obtaining existing data in a metropolitan system platform database, wherein the existing data comprises an associated part table and a case table.
The data attributes in the component table are: part number, part name, part major class, major class number, part minor class, minor class number, part census time, responsible part, responsible department number, rights department number, maintenance department number, part material, part longitude, part latitude, location description.
The data attributes in the case table are: case number, case type, case major class number, case minor class number, problem type number, case occurrence position longitude and latitude, reporting problem time, reporting person, case state, case accessory, case description and address description.
The purpose of the prediction model is to predict the probability of a problem occurring in a component at a certain time, and one important attribute related to the problem is that the normal working time reportTimeLong of the component is not in the existing data of the database, but can be obtained by calculation through the existing data, namely the distance between the problem time of reporting the component and a time node to be predicted, for example, the problem case of the component A is reported once in 2023 and 20 months, and the problem probability of occurring in the component A is predicted after the processing, and the normal working time of the component A is the difference value between the two time nodes.
To facilitate the following calculation of the degree of association, an attribute is added: whether the part has a case report hasCase or not, and the case report refers to the case that the part has a report and is not processed.
(2) Based on Scikit-learn, calculating association degree, screening attribute and constructing data set
The data in the two tables are led out from the database to a csv file, the csv file is loaded to the Scikit-learn, the association degree of each attribute and the attribute of whether the component has a case report or not is calculated, and the sorting from big to small is carried out, and the result is shown in figure 2.
From the ordering result, nine attributes with strong relevance from top to bottom are respectively: whether the component has a case report hasCase, the normal working time reportTimeLong of the component, the material of the component, the component type compType, the maintenance unit con code, the ownership unit belongCode, the responsibility unit dutyCode, the longitude and the latitude latitudes. It can be seen that the probability of a problem with a component is mainly related to the normal working time of the component, i.e. how long the component has been working normally, the maximum relation, the material of the component, the type of the component, the maintenance unit, etc.
The nine attributes are selected to form a data set, and the data set is divided into a training set and an evaluation set which are respectively used for training and evaluation.
Training of second part predictive model
Eight attribute information of the component except for the component report with the case or not is taken as input, the component report with the case or not is taken as output, and a prediction model is obtained through training of an SGDClassifier gradient descent classifier in the Scikit_Learn, and the model outputs the probability of the problem of the component on a specified date.
Application of third part predictive model
The probability of the problem of the parts in a certain day in the future is obtained through the trained prediction model, and the key part list and the high-risk part list are obtained through the probability of the problem, so that the patrol work is guided to be performed more effectively.
Specifically, at a fixed time in the early morning, for example, 3 am, the peak of the system is mainly avoided, a great amount of calculation is performed in the relative idle time, the system pressure is reduced, and the first layer of key component detection is performed, as shown in fig. 3, specifically:
predicting the probability of problem occurrence on the same day by all the components in the city through a prediction model; the probability exceeds a first threshold value, which indicates that the component has a problem in the high probability today, needs to be subjected to important inspection, is stored in an important component list L1, then according to the responsibility grid information in the component information in the L1, the L1 is split into n important component lists according to the responsibility grid, and the important component lists are respectively issued to mobile terminals of corresponding responsibility grid information collectors according to inspection staff configured in the responsibility grid; according to the received key component list, an acquirer can pointedly and mainly inspect the key component in the inspection process; thus, the workload is reduced, the inspection efficiency is improved, and the problematic components can be discovered and processed earlier and more timely.
After predicting the key component list every day, performing a second-layer high-risk component detection logic, specifically:
if one part exceeds the first threshold value for 5 continuous days and the probability of the current day exceeds the second threshold value and the part has no record of reporting the problem, the part is listed as a high-risk part and added into a high-risk part list L2; the high-risk component list L2 is directly sent to a command center, and the command center assigns information collectors to the components to go to check within a specified check time, so that the high-risk components can be confirmed timely.
The values of the first threshold and the second threshold can be adjusted according to Precision and Recall of the trained model, specifically:
as shown in fig. 4, a function diagram of precision and recall under different thresholds is drawn, the x-axis is a threshold, the y-axis is precision and recall, and values corresponding to the target precision and target recall are selected according to the function diagram. For the first threshold, accuracy and recall may be weighted as much as possible, accuracy may be somewhat lower, focus on recall, and ensure that the component in question is predicted as much as possible, even if there is some false alarm. For the second threshold, the required precision is higher, the recall rate can be slightly lower, and the prediction accuracy of the high-risk component is ensured.
According to the scheme, the existing scheme of carrying out all component inspection every day is adjusted to the scheme of inspecting key components and checking high-risk components every day, and other common components are used as a common component list, and the system prescribes the whole inspection once a week, so that the timely detection processing of component problems is ensured to the greatest extent under the condition of reducing the workload, and the best balance is achieved between the workload reduction and the component problem detection.
In this embodiment, the validity of the inspection method is related to the construction of the data set, the training of the model, and the setting of the threshold value, and in order to improve the validity, new data may be periodically acquired, and the construction of the data set, the training of the prediction model, and the setting of the threshold value may be performed again.
Specifically, every month, the component cases of the month are collected, a new data set is constructed, the prediction model is retrained, the trained model is evaluated by an evaluation set, the accuracy is obtained, the accuracy is compared with the accuracy of the previous model, the first threshold value and the second threshold value are adjusted, the model and the threshold value are improved continuously, and the prediction level of the model is maintained and improved.
Example two
In one or more embodiments, a system for component inspection of municipal administration is disclosed, comprising a dataset construction module, a model training module, and a component inspection module:
a dataset construction module configured to: calculating the association degree of the component attribute and the case attribute with the problem of the component based on the historical component case data of city management, and screening the component attribute and the case attribute according to the association degree to form a data set;
a model training module configured to: training a prediction model by utilizing a data set, wherein the prediction model is used for predicting the probability of a problem of a component;
a component inspection module configured to: and predicting the probability of occurrence of problems of all the components through a trained prediction model, dividing key components, high-risk components and common components according to the probability, and respectively performing component inspection and verification.
Example III
An object of the present embodiment is to provide a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs steps in a method for problem inspection of urban management components according to an embodiment of the present disclosure.
Example IV
An object of the present embodiment is to provide an electronic apparatus.
An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps in a method for problem inspection of urban management components according to the first embodiment of the disclosure when executing the program.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (10)

1. A method for inspecting a problem of an urban management component, comprising:
calculating the association degree of the component attribute and the case attribute with the problem of the component based on the historical component case data of city management, and screening the component attribute and the case attribute according to the association degree to form a data set;
training a prediction model by utilizing a data set, wherein the prediction model is used for predicting the probability of a problem of a component;
and predicting the probability of occurrence of problems of all the components through a trained prediction model, dividing key components, high-risk components and common components according to the probability, and respectively performing component inspection and verification.
2. The method for inspecting problems of municipal administration components according to claim 1, wherein said component attributes comprise: component number, component name, component major class, major class number, component minor class, minor class number, component census time, responsible component, responsible department number, rights department number, maintenance department number, component material, component longitude, component latitude, location description;
the case attributes include: case number, case type, case major class number, case minor class number, problem type number, case occurrence position longitude and latitude, reporting problem time, reporting person, case state, case accessory, case description and address description.
3. The method for inspecting problems of urban management components according to claim 1, wherein the calculating of the association degree between the component attribute and the case attribute and the component occurrence problem is specifically as follows:
according to historical component case data, two attributes are added: reporting whether the component has a case or not and the normal working time of the component;
and calculating the association degree of all the attributes and whether the component has the case report attribute or not based on Scikit-learn.
4. The method for inspecting problems of urban management components according to claim 3, wherein the screening component attributes and case attributes according to the association degree comprises the following specific steps: and taking a predetermined number of attributes according to the sequence of the association degree from large to small to form a data set.
5. The method of claim 1, wherein the predictive model takes the component as input and outputs the probability of a problem occurring on the same day.
6. The method for inspecting problems of urban management components according to claim 1, wherein the judging conditions of the key components in the key component list are as follows:
means for exceeding a preset first threshold value in probability of occurrence of a problem on the same day;
the judging conditions of the high-risk components in the high-risk component list are as follows:
the probability of occurrence of problems in the continuous T days exceeds a first threshold, the probability of occurrence of problems in the same day exceeds a second threshold, no record of the problems is reported, and T is the preset number of days;
wherein the first threshold is less than a second threshold; two thresholds are set based on the accuracy and recall of the prediction model after training.
7. The method for inspecting problems of urban management components according to claim 1, further comprising: periodically acquiring new data, and re-constructing a data set, training a prediction model and setting a threshold value.
8. The city management component problem inspection system is characterized by comprising a data set construction module, a model training module and a component inspection module:
a dataset construction module configured to: calculating the association degree of the component attribute and the case attribute with the problem of the component based on the historical component case data of city management, and screening the component attribute and the case attribute according to the association degree to form a data set;
a model training module configured to: training a prediction model by utilizing a data set, wherein the prediction model is used for predicting the probability of a problem of a component;
a component inspection module configured to: and predicting the probability of occurrence of problems of all the components through a trained prediction model, dividing key components, high-risk components and common components according to the probability, and respectively performing component inspection and verification.
9. An electronic device, comprising:
a memory for non-transitory storage of computer readable instructions; and
a processor for executing the computer-readable instructions,
wherein the computer readable instructions, when executed by the processor, perform the method of any of the preceding claims 1-7.
10. A storage medium, characterized by non-transitory storing computer-readable instructions, wherein the instructions of the method of any one of claims 1-7 are performed when the non-transitory computer-readable instructions are executed by a computer.
CN202311027025.6A 2023-08-15 2023-08-15 City management component problem inspection method and system Pending CN117057466A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311027025.6A CN117057466A (en) 2023-08-15 2023-08-15 City management component problem inspection method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311027025.6A CN117057466A (en) 2023-08-15 2023-08-15 City management component problem inspection method and system

Publications (1)

Publication Number Publication Date
CN117057466A true CN117057466A (en) 2023-11-14

Family

ID=88654775

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311027025.6A Pending CN117057466A (en) 2023-08-15 2023-08-15 City management component problem inspection method and system

Country Status (1)

Country Link
CN (1) CN117057466A (en)

Similar Documents

Publication Publication Date Title
WO2018213012A1 (en) Estimation of damage prevention with building retrofit
CN111639845B (en) Emergency plan validity assessment method considering integrity and operability
CN104966172A (en) Large data visualization analysis and processing system for enterprise operation data analysis
CN106327087A (en) Test task assignment method
CN112785458A (en) Intelligent management and maintenance system for bridge health big data
CN109816226B (en) Method and system for evaluating disaster prevention and risk avoidance capabilities of park green land
CN114267178B (en) Intelligent operation maintenance method and device for station
US20240142063A1 (en) Method for troubleshooting potential safety hazards of compressor in smart gas pipeline network and internet of things system thereof
CN114519524A (en) Enterprise risk early warning method and device based on knowledge graph and storage medium
CN114693025A (en) Intelligent park maintenance method and system
CN115170980B (en) Gas pipeline high consequence area intelligent identification method based on satellite image identification
CN112150098A (en) Electric power facility anti-terrorism security supervision method and system
CN114399235B (en) Method and system for judging disaster risk level based on rain condition data
CN111966746A (en) Meteorological disaster prevention and reduction flow monitoring system and monitoring method thereof
CN116543303A (en) Bridge plate type rubber support disease identification and detection method based on deep learning
CN103942251A (en) Method and system for inputting high altitude meteorological data into database based on multiple quality control methods
CN116739317B (en) Mining winch automatic management and dispatching platform, method, equipment and medium
Strauss et al. Performance indicators for an objective assessment and through-life management of bridges and tunnels
CN117114412A (en) Safety pre-control method and device for dangerous chemical production enterprises
CN110399537B (en) Artificial intelligence technology-based warning situation space-time prediction method
CN117057466A (en) City management component problem inspection method and system
CN112200399A (en) Earthquake disaster risk assessment and economic loss prediction method
KR102525491B1 (en) Method of providing structure damage detection report
CN116882695A (en) Automatic inspection method, device, computer equipment and storage medium
CN113191170B (en) Public facility two-dimensional code damage inspection effectiveness prediction method and system

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