CN115271544B - Method and device for reducing noise complaint rate, electronic equipment and storage medium - Google Patents
Method and device for reducing noise complaint rate, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115271544B CN115271544B CN202211133752.6A CN202211133752A CN115271544B CN 115271544 B CN115271544 B CN 115271544B CN 202211133752 A CN202211133752 A CN 202211133752A CN 115271544 B CN115271544 B CN 115271544B
- Authority
- CN
- China
- Prior art keywords
- complaint
- noise
- factors
- target
- rate
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 238000010801 machine learning Methods 0.000 claims abstract description 16
- 238000010219 correlation analysis Methods 0.000 claims abstract description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 10
- 238000012352 Spearman correlation analysis Methods 0.000 claims description 6
- 238000007417 hierarchical cluster analysis Methods 0.000 claims description 6
- 238000012098 association analyses Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000007418 data mining Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000018612 quorum sensing Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
-
- 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
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the specification relates to the technical field of computers, in particular to a method and a device for reducing a noise complaint rate, electronic equipment and a storage medium. Wherein, the method comprises the following steps: acquiring noise complaint data and influence factors thereof of a target city; performing correlation analysis on the noise complaint rate and the influence factors to determine target influence factors to be applied from the influence factors; performing regression modeling on a preset machine learning model by using the noise complaint data and the target influence factors to obtain a prediction model for predicting the noise complaint rate of each complaint administrative region; the prediction model is explained by utilizing a preset model interpreter to determine the contribution degree of each target influence factor to the prediction capability of the prediction model; and determining an output result for reducing the noise complaint rate of the complaint administrative area based on the contribution degree of each target influence factor to the prediction capability of the prediction model. The technical scheme of the specification can solve the technical problem of reducing the complaint rate of the urban noise.
Description
Technical Field
The embodiment of the specification relates to the technical field of computers, in particular to a method and a device for reducing a noise complaint rate, electronic equipment and a storage medium.
Background
Noise refers to sound generated in industrial production, construction, transportation, and social life that interferes with the surrounding living environment. The noise pollution is a phenomenon that noise is generated when the noise exceeds a noise emission standard or a prevention and control measure is not adopted according to law, and the noise interferes with normal life, work and study of other people.
The urban noise complaint data is actually the result of 'human as a sensor' and 'quorum sensing', is the most direct subjective reaction of people to noise, and can help people to understand noise pollution from the human perspective.
In view of the above, there is a need for a method, an apparatus, an electronic device and a storage medium for reducing a noise complaint rate to solve the technical problem of reducing the urban noise complaint rate.
Disclosure of Invention
In order to solve the technical problem of how to reduce the urban noise complaint rate, embodiments of the present specification provide a method, an apparatus, an electronic device, and a storage medium for reducing the noise complaint rate.
In a first aspect, an embodiment of the present specification provides a method for reducing a noise complaint rate, including:
acquiring noise complaint data and influence factors thereof of a target city; the noise complaint data comprises a complaint number and a complaint administrative region, and the ratio of the complaint number to the area of the complaint administrative region is the noise complaint rate of the complaint administrative region;
performing correlation analysis on the noise complaint rate and the influence factors to determine target influence factors to be applied from the influence factors;
performing regression modeling on a preset machine learning model by using the noise complaint data and the target influence factors to obtain a prediction model for predicting the noise complaint rate of each complaint administrative region;
interpreting the prediction model by using a preset model interpreter to determine the contribution degree of each target influence factor to the prediction capability of the prediction model;
and determining an output result for reducing the noise complaint rate of the complaint administrative area based on the contribution degree of each target influence factor to the prediction capability of the prediction model.
In one possible design, the association analysis includes Spearman correlation analysis and/or hierarchical clustering analysis.
In one possible design, the machine learning model is an XGBoost model.
In one possible design, the model interpreter may be a SHAP.
In one possible design, the influencing factors include traffic noise-like factors, demographic-like factors, land utilization-like factors, and building morphology-like factors.
In one possible design, the determining an output result for reducing the noise complaint rate based on the degree of contribution of each of the target influencing factors to the predictive capability of the predictive model includes:
determining a first target influence factor of which the contribution degree is greater than a preset contribution degree threshold value based on the contribution degree of each target influence factor to the prediction capability of the prediction model;
removing demographic factors from the first target influence factors to obtain second target influence factors;
and determining an output result for reducing the noise complaint rate based on the contribution degree of each second target influence factor to the prediction capability of the prediction model.
In one possible design, the determining the output result for reducing the noise complaint rate based on the degree of contribution of each second target influence factor to the predictive capability of the predictive model includes:
for each second target influence factor, performing:
adjusting the initial value of the current second target influence factor to predict by using the adjusted prediction model, so as to obtain a change curve of the current noise complaint rate of the complaint administrative area;
determining a target value of a current second target influence factor corresponding to the intersection point of the two curves based on a change curve of the current noise complaint rate of the complaint administrative region and a preset intervention measure cost curve;
and adjusting the initial value of the current second target influence factor to the target value to serve as an output result for reducing the noise complaint rate of the complaint administration area.
In a second aspect, embodiments of the present specification further provide an apparatus for reducing a noise complaint rate, including:
the acquisition module is used for acquiring noise complaint data of a target city and influence factors thereof; the noise complaint data comprises a complaint number and a complaint administrative region, and the ratio of the complaint number to the area of the complaint administrative region is the noise complaint rate of the complaint administrative region;
the correlation analysis module is used for performing correlation analysis on the noise complaint rate and the influence factors so as to determine target influence factors to be applied from the influence factors;
the regression modeling module is used for carrying out regression modeling on a preset machine learning model by utilizing the noise complaint data and the target influence factors so as to obtain a prediction model for predicting the noise complaint rate of each complaint administrative region;
the interpretation module is used for interpreting the prediction model by utilizing a preset model interpreter so as to determine the contribution degree of each target influence factor to the prediction capability of the prediction model;
and the determining module is used for determining an output result for reducing the noise complaint rate of the complaint administrative region based on the contribution degree of each target influence factor to the prediction capability of the prediction model.
In a third aspect, an embodiment of the present specification further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and the processor executes the computer program to implement the method according to any embodiment of the present specification.
In a fourth aspect, the embodiments of the present specification further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed in a computer, the computer program causes the computer to execute the method according to any one of the embodiments of the present specification.
The embodiment of the specification provides a method, a device, electronic equipment and a storage medium for reducing noise complaint rate, firstly noise complaint data and influence factors of a target city are obtained, then correlation analysis is carried out on the noise complaint rate and the influence factors to determine target influence factors to be applied from the influence factors, regression modeling is carried out on a preset machine learning model by using the noise complaint data and the target influence factors to obtain a prediction model for predicting the noise complaint rate of each complaint administrative region, then the prediction model is explained by using a preset model interpreter to determine the contribution degree of each target influence factor to the prediction capability of the prediction model, and finally an output result for reducing the noise complaint rate of the complaint administrative region is determined based on the contribution degree of each target influence factor to the prediction capability of the prediction model. Therefore, the technical problem of reducing the complaint rate of urban noise can be solved by the scheme.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the description below are some embodiments of the present specification, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for reducing a noise complaint rate according to an embodiment of the present disclosure;
fig. 2 is a hardware architecture diagram of an electronic device provided in an embodiment of the present specification;
FIG. 3 is a block diagram of an apparatus for reducing a complaint rate of noise according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of the contribution degree of each target influence factor obtained by interpreting the prediction model according to an embodiment of the present specification.
Detailed Description
In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure more clear, the technical solution in the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are a part of the embodiments of the present disclosure, but not all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts based on the embodiments of the present disclosure belong to the protection scope of the present disclosure.
Referring to fig. 1, an embodiment of the present disclosure provides a method for reducing a noise complaint rate, where the method includes:
step 100: acquiring noise complaint data and influence factors thereof of a target city; the noise complaint data comprises the number of complaints and the complaint administrative regions, and the ratio of the number of complaints to the area of the complaint administrative regions is the noise complaint rate of the complaint administrative regions;
step 102: performing correlation analysis on the noise complaint rate and the influence factors to determine target influence factors to be applied from the influence factors;
step 104: performing regression modeling on a preset machine learning model by using the noise complaint data and the target influence factors to obtain a prediction model for predicting the noise complaint rate of each complaint administrative region;
step 106: the prediction model is explained by utilizing a preset model interpreter to determine the contribution degree of each target influence factor to the prediction capability of the prediction model;
step 108: and determining an output result for reducing the noise complaint rate of the complaint administrative area based on the contribution degree of each target influence factor to the prediction capability of the prediction model.
In the embodiment of the specification, noise complaint data and influence factors of a target city are firstly acquired, then correlation analysis is performed on the noise complaint rate and the influence factors to determine target influence factors to be applied from the influence factors, then regression modeling is performed on a preset machine learning model by using the noise complaint data and the target influence factors to obtain a prediction model for predicting the noise complaint rate of each complaint administrative area, the prediction model is explained by using a preset model interpreter to determine the contribution degree of each target influence factor to the prediction capability of the prediction model, and finally an output result for reducing the noise complaint rate of the complaint administrative area is determined based on the contribution degree of each target influence factor to the prediction capability of the prediction model. Therefore, the technical problem of reducing the complaint rate of urban noise can be solved by the scheme.
The manner in which the various steps shown in fig. 1 are performed is described below.
With respect to step 100:
for example,
the city selected as the target city in the present specification is new york city, and the noise complaint data (437713 pieces of noise complaint data in 2018) originated from 311 hot line platform in new york city, which is shown in table 1 (showing location, time and complaint type). The noise complaint data comprises the number of complaints and the complaint administrative areas, and the ratio of the number of complaints to the area of the complaint administrative areas is the noise complaint rate of the complaint administrative areas. The method and the device do not specifically limit the division of the administrative area, for example, when the administrative area is a community, the number of complaints in the same community is counted, and the ratio of the number of complaints in the community to the area of the community is calculated to be the community noise complaint rate.
TABLE 1 New York City noise complaint data example
In addition, the embodiments of the present specification also collect factors that may affect noise complaints in the complaint administrative area, including but not limited to traffic noise type factors, demographic type factors, land utilization type factors, and building form type factors of the complaint administrative area, where the demographic type factors, land utilization type factors, and building form type factors all include influence factors of the secondary classification, as shown in table 2.
TABLE 2 factors that may affect the number of noise complaints
With respect to step 102:
in step 102, by performing correlation analysis on the noise complaint rate and the influencing factors, the target influencing factors to be applied can be determined from all the factors possibly influencing the noise complaint number in table 2, so as to facilitate regression modeling applied to the subsequent prediction model.
In one embodiment of the invention, the association analysis includes Spearman correlation analysis and/or hierarchical clustering analysis.
Upon Spearman correlation analysis of all possible influencing factors with noise complaint rate (i.e. noise complaint density), the inventors found that: the noise complaint rate is more relevant to the demographic factors and the building form factors; by performing hierarchical clustering analysis on all possible influencing factors and the noise complaint rate (namely, the noise complaint density), the inventor finds that: some land utilization factors and building form factors have strong similarity, so the land utilization factors and the building form factors can be classified into one category; there is also a strong similarity between some demographic and land use like factors.
It should be noted that Spearman correlation analysis and hierarchical clustering analysis are well known to those skilled in the art and will not be described herein.
With respect to step 104:
since the noise complaint rate and the influence factor are subjected to correlation analysis, the data amount of the prediction model in the regression modeling in step 104 can be simplified.
It can be known that, in principle, the prediction model constructed by each complaint administrative area by using the historical noise complaint data of the administrative area and the target influence factor is only adapted to the administrative area, so the obtained prediction model is not used for predicting the noise complaint rate of other administrative areas or other cities, but is used for obtaining the noise complaint rate corresponding to the target influence factor by adjusting the initial value of the target influence factor in the following steps, further obtaining a change curve of the noise complaint rate, and finally preparing for outputting a proposal for reducing the noise complaint rate of the administrative area.
In one embodiment of the present description, the machine learning model is an XGBoost model.
The XGBoost model is an extensible machine learning system for Tree lifting, and is implemented based on an algorithm of a Gradient lifting Decision Tree (GBDT). The basic idea of the XGboost is the same as that of the GBDT, but some optimization is realized, for example, the second derivative makes the loss function more accurate; the regular term avoids tree overfitting; block storage may be computed in parallel, etc. XGBoost has the characteristics of high efficiency, flexibility and portability, is widely applied in the fields of data mining, recommendation systems and the like, and is widely recognized in many machine learning and data mining challenges.
Of course, the machine learning model may also be a neural network model, and is not particularly limited herein.
For step 106:
in one embodiment of the present description, the model interpreter is a SHAP.
The XGBoost model is usually better in accuracy in prediction than the linear model, but at the same time, the interpretability of the linear model is lost, so the XGBoost model is generally considered as a black box model.
For the purpose of interpreting the black box model, the method of SHAP value can be used. SHAP is a unified framework for interpreting predictions, which assigns the importance of a particular prediction to each feature. The SHAP value is used as a uniform measure of feature importance, i.e., the Shapley value of the conditional expectation function of the original model.
In the combined application with the XGBoost model, for each prediction sample, the XGBoost model generates a prediction value, and the SHAP value is the value allocated to each feature in the sample, and reflects the influence of the feature in each sample and the positive and negative of the influence.
Of course, the model interpreter may also be a feature importance (feature importance) or a partial dependency graph (partial dependency plot), which is not specifically limited herein. It should be noted that although Feature importance generated by the XGBoost model can intuitively reflect the importance of the Feature, the specific relationship between the Feature and the final prediction result, such as positive correlation, negative correlation or more complex correlation, cannot be judged, so that the widely applicable method of the SHAP value is used to explain the model.
For example, R of the trained predictive model 2 0.9794, which satisfies the prediction accuracy. The optimal parameters of the prediction model are as follows: max _ depth =3,min_child_weight =3,gamma =0.1,collemple_bylevel =1,collemple_bytre =0.8,reg_alpha =0.2,learing_rate =0.01,max_delta_step =0,n_estimators =5000,nthread =1,subsample =0.7, seed =1000, scale _pos _weight =0.1.
The results of the XGBoost model and the SHAP value interpretation are shown in fig. 4, where the objective influence factor contributing the most is the dwelling unit, the second is the low income population, and of the top five objective influences, three are demographic type factors, and two are architectural morphology type factors.
For step 108:
in an embodiment of the present specification, step 108 may specifically include:
determining a first target influence factor of which the contribution degree is greater than a preset contribution degree threshold value based on the contribution degree of each target influence factor to the prediction capability of the prediction model;
eliminating demographic factors from the first target influence factors to obtain second target influence factors;
and determining an output result for reducing the noise complaint rate based on the contribution degree of each second target influence factor to the prediction capability of the prediction model.
In this embodiment, the target influence factor to be adjusted for the noise complaint rate can be more definitely reduced by determining the first target influence factor of which the contribution degree is greater than the preset contribution degree threshold; the demographic factors are removed from the first target factors, so that the cost of subsequent intervention measures is considered, because if the demographic factors are the main factors causing high noise complaint rate, the corresponding intervention measures generally limit the population, which obviously is not conventional. Thus, in considering the target contributors that reduce the rate of noise complaints, demographic categories need to be eliminated from the first target contributor.
In an embodiment of the present specification, the step "determining an output result for reducing the noise complaint rate based on the degree of contribution of each second target influence factor to the prediction capability of the prediction model" may specifically include:
for each second target influence factor, executing:
adjusting the initial value of the current second target influence factor to predict by using the adjusted prediction model, thereby obtaining a change curve of the current noise complaint rate of the complaint administrative region;
determining a target value of a current second target influence factor corresponding to the intersection point of the two curves based on a change curve of the current noise complaint rate of the complaint administrative region and a preset intervention measure cost curve;
and adjusting the initial value of the current second target influence factor to a target value to serve as an output result for reducing the noise complaint rate of the complaint administrative area.
In this embodiment, initial values of the second target influence factors are respectively adjusted, so that a variation curve of each noise complaint rate of the complaint administrative area is obtained by using the adjusted prediction model, and further, a target value of the second target influence factor corresponding to an intersection of the two curves (i.e., an optimal solution for intervention cost and noise complaint rate reduction) can be determined by using the variation curve of each noise complaint rate and a preset intervention cost curve, so that a correction suggestion (i.e., an output result) for reducing the noise complaint rate of the administrative area, that is, "the current initial value of the second target influence factor is adjusted to the target value", can be given.
It should be noted that the relevant representation of the intervention cost curve has been disclosed sufficiently to be limited by the trade secret not specifically described herein.
For example, according to the obtained XGboost regression prediction model, the living unit with the largest contribution degree to the model is adjusted to explore the corresponding change of the noise complaint rate. For example, by reducing the dwelling unit density in each street by 10%, 20%, 30%, respectively, as shown in Table 3, when the dwelling unit density in each street is reduced by 10%, the average noise complaint rate can be reduced by 36.56%, by 1086.3/km 2 Down to 689.1/km 2 And the noise complaint rate decreases by 40.80% and 46.19% after 20% or 30% reduction in the density of each street living unit. The above situation shows that the drop is not linear and an optimal solution is needed to consider intervention cost and reduce noise complaint rate.
TABLE 3 noise complaint rate changes
Therefore, according to the method proposed by the present study, the noise complaint rate per unit area can be effectively predicted. According to the prediction result, corresponding intervention measures can be implemented, such as reduction of living units, so that the noise complaint amount is reduced, harm of noise to people is reduced, and the living environment of the target city can be improved.
As shown in fig. 2 and 3, the present specification provides an apparatus for reducing a noise complaint rate. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. From a hardware aspect, as shown in fig. 2, for a hardware architecture diagram of an electronic device in which an apparatus for reducing a noise complaint rate provided in the embodiment of the present disclosure is located, in addition to the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 2, the electronic device in which the apparatus is located in the embodiment may generally include other hardware, such as a forwarding chip responsible for processing a packet, and the like. Taking a software implementation as an example, as shown in fig. 3, as a logical device, a CPU of the electronic device reads a corresponding computer program in the non-volatile memory into the memory for running.
As shown in fig. 3, the apparatus for reducing a noise complaint rate provided in this embodiment is applied to a detection node, where the detection node is deployed in an intranet environment, and the apparatus includes:
the obtaining module 300 is configured to obtain noise complaint data of a target city and influence factors thereof; the noise complaint data comprises a complaint number and a complaint administrative region, and the ratio of the complaint number to the area of the complaint administrative region is the noise complaint rate of the complaint administrative region;
a correlation analysis module 302, configured to perform correlation analysis on the noise complaint rate and the influence factor to determine a target influence factor to be applied from the influence factor;
a regression modeling module 304, configured to perform regression modeling on a preset machine learning model by using the noise complaint data and the target influence factor to obtain a prediction model for predicting the noise complaint rate of each complaint administrative area;
an interpretation module 306, configured to interpret the prediction model by using a preset model interpreter to determine a degree of contribution of each of the target influencing factors to a prediction capability of the prediction model;
a determining module 308, configured to determine, based on a degree of contribution of each of the target influencing factors to a prediction capability of the prediction model, an output result that reduces a noise complaint rate of the complaint administration area.
In this illustrative embodiment, the obtaining module 300 may be configured to perform step 100 of the above method embodiment, the association analysis module 302 may be configured to perform step 102 of the above method embodiment, the regression modeling module 304 may be configured to perform step 104 of the above method embodiment, the interpreting module 306 may be configured to perform step 106 of the above method embodiment, and the determining module 308 may be configured to perform step 108 of the above method embodiment.
In one embodiment of the present description, the association analysis includes Spearman correlation analysis and/or hierarchical clustering analysis.
In one embodiment of the present description, the machine learning model is an XGBoost model.
In one embodiment of the present description, the model interpreter is a SHAP.
In one embodiment of the present description, the influencing factors include traffic noise class factors, demographic class factors, land utilization class factors, and building morphology class factors.
In an embodiment of the present specification, the determining module is configured to perform the following operations:
determining a first target influence factor of which the contribution degree is greater than a preset contribution degree threshold value based on the contribution degree of each target influence factor to the prediction capability of the prediction model;
eliminating demographic factors from the first target influence factors to obtain second target influence factors;
and determining an output result for reducing the noise complaint rate based on the contribution degree of each second target influence factor to the prediction capability of the prediction model.
In an embodiment of the present specification, the determining module is configured to, when determining the output result for reducing the noise complaint rate based on the degree of contribution of each of the second target influence factors to the prediction capability of the prediction model, perform the following operations:
for each second target influence factor, performing:
adjusting the initial value of the current second target influence factor to predict by using the adjusted prediction model, so as to obtain a change curve of the current noise complaint rate of the complaint administrative area;
determining a target value of a current second target influence factor corresponding to the intersection point of the two curves based on a change curve of the current noise complaint rate of the complaint administrative region and a preset intervention measure cost curve;
and adjusting the initial value of the current second target influence factor to the target value to serve as an output result for reducing the noise complaint rate of the complaint administration area.
It is to be understood that the illustrated structure of the embodiment of the present specification does not constitute a specific limitation to a device for reducing the noise complaint rate. In other embodiments of the present description, an apparatus to reduce the rate of noise complaints can include more or fewer components than shown, or some components can be combined, or some components can be split, or a different arrangement of components can be used. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.
For the information interaction, execution process and other contents between the modules in the above-mentioned apparatus, because the same concept is based on as the method embodiment of this specification, specific contents can refer to the description in the method embodiment of this specification, and are not described herein again.
An embodiment of the present specification further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the method for reducing a noise complaint rate in any embodiment of the present specification is implemented.
The present specification also provides a computer readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the processor to perform a method for reducing a noise complaint rate in any one of the embodiments of the specification.
Specifically, a system or an apparatus equipped with a storage medium on which software program codes that realize the functions of any of the above-described embodiments are stored may be provided, and a computer (or a CPU or MPU) of the system or the apparatus is caused to read out and execute the program codes stored in the storage medium.
In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of this specification.
Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer by a communications network.
Further, it should be clear that the functions of any one of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform a part or all of the actual operations based on instructions of the program code.
Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then causes a CPU or the like mounted on the expansion board or the expansion module to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the above-described embodiments.
It is noted that, herein, relational terms such as first and second, and the like may be 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. Also, 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 a" \8230; "does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: ROM, RAM, magnetic or optical disks, etc. that can store program codes.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solutions of the present specification, and not to limit them; although the present description has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present specification.
Claims (9)
1. A method of reducing a rate of noise complaints, comprising:
acquiring noise complaint data and influence factors thereof of a target city; the noise complaint data comprises a complaint number and a complaint administration area, the ratio of the complaint number to the area of the complaint administration area is the noise complaint rate of the complaint administration area, the influence factors comprise traffic noise factors, demographic factors, land utilization factors and building form factors, the demographic factors comprise population under 18 years old, low income level population, medium income level population, high income level population and average education level, and the building form factors comprise housing units, building total units, estimated land prices, average room prices, building areas, floor numbers, building area ratios, building height ratios and total building area ratios;
performing correlation analysis on the noise complaint rate and the influence factors to determine target influence factors to be applied from the influence factors;
performing regression modeling on a preset machine learning model by using the noise complaint data and the target influence factors to obtain a prediction model for predicting the noise complaint rate of each complaint administrative region;
interpreting the prediction model by using a preset model interpretable device to determine the contribution degree of each target influence factor to the prediction capability of the prediction model;
and determining an output result for reducing the noise complaint rate of the complaint administrative area based on the contribution degree of each target influence factor to the prediction capability of the prediction model.
2. The method according to claim 1, wherein the association analysis comprises Spearman correlation analysis and/or hierarchical clustering analysis.
3. The method of claim 1, wherein the machine learning model is an XGBoost model.
4. The method of claim 1, wherein the model interpreter is a SHAP.
5. The method of claim 1, wherein determining an output that reduces a rate of noise complaints based on a degree to which each of the target influencing factors contributes to a predictive capability of the predictive model comprises:
determining a first target influence factor of which the contribution degree is greater than a preset contribution degree threshold value based on the contribution degree of each target influence factor to the prediction capability of the prediction model;
eliminating demographic factors from the first target influence factors to obtain second target influence factors;
and determining an output result for reducing the noise complaint rate based on the contribution degree of each second target influence factor to the prediction capability of the prediction model.
6. The method of claim 5, wherein determining an output that reduces the noise complaint rate based on the degree to which each of the second target influencing factors contributes to the predictive power of the predictive model comprises:
for each second target influence factor, performing:
adjusting the initial value of the current second target influence factor to predict by using the adjusted prediction model, thereby obtaining a change curve of the current noise complaint rate of the complaint administration area;
determining a target numerical value of a current second target influence factor corresponding to the intersection point of the two curves based on a change curve of the current noise complaint rate of the complaint administrative region and a preset intervention measure cost curve;
and adjusting the initial value of the current second target influence factor to the target value to serve as an output result for reducing the noise complaint rate of the complaint administrative area.
7. An apparatus for reducing a rate of noise complaints, comprising:
the acquisition module is used for acquiring noise complaint data of a target city and influence factors thereof; the noise complaint data comprises complaint quantity and complaint administrative regions, the ratio of the complaint quantity to the area of the complaint administrative regions is the noise complaint rate of the complaint administrative regions, the influence factors comprise traffic noise factors, demographic factors, land utilization factors and building form factors, the demographic factors comprise population under 18 years old, population with low income level, population with medium income level, population with high income level and average education level, and the building form factors comprise housing units, building total units, estimated land price, average house price, building area, floor number, building area ratio, building height ratio and total building area ratio;
the correlation analysis module is used for performing correlation analysis on the noise complaint rate and the influence factors so as to determine target influence factors to be applied from the influence factors;
the regression modeling module is used for carrying out regression modeling on a preset machine learning model by utilizing the noise complaint data and the target influence factors so as to obtain a prediction model for predicting the noise complaint rate of each complaint administrative region;
the interpretation module is used for interpreting the prediction model by utilizing a preset model interpreter so as to determine the contribution degree of each target influence factor to the prediction capability of the prediction model;
and the determining module is used for determining an output result for reducing the noise complaint rate of the complaint administrative area based on the contribution degree of each target influence factor to the prediction capability of the prediction model.
8. An electronic device comprising a memory having stored therein a computer program and a processor that, when executing the computer program, implements the method of any of claims 1-6.
9. A computer-readable storage medium, on which a computer program is stored which, when executed in a computer, causes the computer to carry out the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211133752.6A CN115271544B (en) | 2022-09-19 | 2022-09-19 | Method and device for reducing noise complaint rate, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211133752.6A CN115271544B (en) | 2022-09-19 | 2022-09-19 | Method and device for reducing noise complaint rate, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115271544A CN115271544A (en) | 2022-11-01 |
| CN115271544B true CN115271544B (en) | 2022-12-09 |
Family
ID=83757385
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211133752.6A Active CN115271544B (en) | 2022-09-19 | 2022-09-19 | Method and device for reducing noise complaint rate, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115271544B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104598757B (en) * | 2015-02-12 | 2017-10-24 | 西南交通大学 | Orbital region traffic noise prediction method |
| CN113421422B (en) * | 2021-06-22 | 2022-04-12 | 吴桐雨 | Urban road noise prediction system based on Internet of things and cloud computing technology |
| CN113627692A (en) * | 2021-09-17 | 2021-11-09 | 平安银行股份有限公司 | Complaint amount prediction method, complaint amount prediction device, complaint amount prediction apparatus, and storage medium |
| CN114662772A (en) * | 2022-04-01 | 2022-06-24 | 北京零点远景网络科技有限公司 | Traffic noise early warning method, model training method, device, equipment and medium |
-
2022
- 2022-09-19 CN CN202211133752.6A patent/CN115271544B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115271544A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070141B (en) | Network intrusion detection method | |
| Goh et al. | Incorporating the rough sets theory into travel demand analysis | |
| Merkle et al. | Binary recursive partitioning: Background, methods, and application to psychology | |
| CN111738628A (en) | Risk group identification method and device | |
| CN113077097A (en) | Air quality prediction method based on deep space-time similarity | |
| CN112348519A (en) | Method and device for identifying fraudulent user and electronic equipment | |
| JP6265214B2 (en) | Information presentation method, apparatus, and program | |
| CN111160472B (en) | Method and device for predicting target characteristic of object, storage medium and electronic equipment | |
| Cui et al. | Learning global pairwise interactions with Bayesian neural networks | |
| CN112966189B (en) | Fund product recommendation system | |
| CN113205403A (en) | Method and device for calculating enterprise credit level, storage medium and terminal | |
| CN110728301A (en) | Credit scoring method, device, terminal and storage medium for individual user | |
| CN111861781A (en) | Feature optimization method and system in residential electricity consumption behavior clustering | |
| CN117078048A (en) | Digital twinning-based intelligent city resource management method and system | |
| CN116611546A (en) | Knowledge-graph-based landslide prediction method and system for target research area | |
| CN117291428B (en) | Enterprise management APP-based data background management system | |
| CN115271544B (en) | Method and device for reducing noise complaint rate, electronic equipment and storage medium | |
| KR102525491B1 (en) | Method of providing structure damage detection report | |
| CN110633890A (en) | Land utilization efficiency judgment method and system | |
| CN112861692B (en) | Method and device for constructing room classification model, and method and device for classifying rooms | |
| CN111882421B (en) | Information processing method, wind control method, device, equipment and storage medium | |
| Li et al. | Generalized building energy and carbon emissions benchmarking with post-prediction analysis | |
| CN113962508A (en) | Identification method and identification device for electricity object and electronic equipment | |
| CN115242482B (en) | Unauthorized access risk detection method and device, electronic equipment and readable storage medium | |
| CN110400160B (en) | Method and device for identifying competitive product user, electronic equipment and storage medium |
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 |