CN113435637A - Garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM - Google Patents
Garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM Download PDFInfo
- Publication number
- CN113435637A CN113435637A CN202110676566.6A CN202110676566A CN113435637A CN 113435637 A CN113435637 A CN 113435637A CN 202110676566 A CN202110676566 A CN 202110676566A CN 113435637 A CN113435637 A CN 113435637A
- Authority
- CN
- China
- Prior art keywords
- garbage
- transfer station
- obtaining
- personnel
- garbage transfer
- 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.)
- Granted
Links
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 385
- 238000012546 transfer Methods 0.000 title claims abstract description 181
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 238000011156 evaluation Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 11
- 230000033001 locomotion Effects 0.000 claims description 34
- 230000001133 acceleration Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000002699 waste material Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000000126 substance Substances 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/043—Optimisation of two dimensional placement, e.g. cutting of clothes or wood
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/30—Administration of product recycling or disposal
-
- 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
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W90/00—Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field, in particular to a garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM. The method comprises the following steps: and obtaining the information of the garbage transfer station through a CIM (common information model), and obtaining a garbage transportation terminal and a garbage generation area. And taking the sum of the distances from the position of the candidate garbage transfer station to the garbage transportation terminal and the garbage generation area as a transportation index. And setting a service neighborhood by taking the position of the garbage transfer station as an origin, and adjusting the size of the service neighborhood according to the garbage output in the service neighborhood to obtain the intersection area of the service neighborhoods between the candidate garbage transfer station and the existing garbage transfer station. And obtaining the negative influence indexes of the scale and the human flow of the corresponding candidate garbage transfer station through the odor grade of the existing garbage transfer station. And obtaining the appropriateness of the position of the transfer station in the candidate garbage according to the service neighborhood intersection area, the transportation index and the negative influence index. The invention considers the influence of multiple aspects on the site selection of the transfer station in the candidate garbage, so that the site selection is more scientific and efficient.
Description
Technical Field
The invention relates to the technical field, in particular to a garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM.
Background
Garbage disposal is an essential part of modern cities, and garbage in a garbage generation area is collected, transported to a garbage transfer station, transferred and then sent to a final garbage disposal plant. The scientific garbage disposal flow has important significance for urban development and urban comfort.
The garbage transfer station is used as a transfer ground of the municipal garbage, is connected with a municipal garbage manufacturing site and a garbage final treatment site, and undertakes tasks such as garbage compression, garbage pretreatment and the like. The construction site of the garbage transfer station is very important for the treatment efficiency of the municipal garbage.
In the prior art, the evaluation method for site selection of the garbage transfer station is mostly determined according to manual investigation, and the investigation wastes time and labor. Service conflicts between the candidate garbage transfer station and the existing garbage transfer station are not considered. And the negative influence of the candidate garbage transfer station on the pedestrian is avoided.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM, and the adopted technical scheme is as follows:
the invention provides a garbage transfer station site selection evaluation method based on artificial intelligence and CIM, which comprises the following steps:
obtaining information of the garbage transfer station through a CIM (common information model); the garbage transfer station information comprises the existing garbage transfer station information and candidate garbage transfer station information;
obtaining a garbage transportation terminal and a garbage generation area through the CIM; taking the sum of the distances from the candidate garbage transfer station position to the garbage transportation terminal and the garbage generation area route as a transportation index;
setting a service neighborhood according to a preset neighborhood radius by taking the position of each garbage transfer station as an origin; adjusting the size of each service neighborhood according to the garbage yield in each service neighborhood; obtaining the intersection area of service neighborhoods between the candidate garbage transfer station and other garbage transfer stations;
acquiring a road image of the road with the similar distance from the existing garbage transfer station; acquiring movement information and personnel flow of personnel in the road image; the motion information comprises the acceleration and the posture of the person; obtaining a malodor grade according to the motion information; obtaining negative influence indexes corresponding to the personnel flow and the scale of the garbage transfer station according to the odor grade;
and obtaining the appropriateness of the position of the transfer station in the candidate garbage according to the service neighborhood intersection area, the transportation index and the negative influence index.
Further, the method for acquiring the garbage yield comprises the following steps:
acquiring a garbage generation area image in the service neighborhood;
segmenting a garbage image from the garbage generation area image; obtaining the scale of the garbage site where the garbage is located in the garbage image;
taking the area ratio of the garbage image to the garbage generation area image as a garbage ratio;
and obtaining the garbage yield according to the garbage ratio and the garbage site scale.
Further, the adjusting the size of the service neighborhood according to the garbage yield in the service neighborhood comprises:
when the difference value between the garbage yield and the garbage transfer station scale is larger than a preset first threshold value, reducing the size of the service neighborhood according to a preset adjustment step length;
when the difference value between the size of the garbage transfer station and the garbage yield is larger than the first threshold value, increasing the size of the service neighborhood according to the adjustment step length;
when the absolute value of the difference value between the garbage yield and the garbage transfer station size is smaller than or equal to the first threshold value, the size of the service neighborhood is unchanged.
Further, the obtaining the odor grade of the existing garbage transfer station according to the motion information further comprises:
obtaining an initial malodor grade corresponding to each person according to the movement information; the initial malodor level with the largest number of people is taken as the malodor level.
Further, the obtaining of the motion information and the person flow rate of the person in the road image includes:
sending the road image into a pre-trained personnel detection network, and outputting personnel key point information;
acquiring the personnel posture and the personnel flow through the personnel key point information;
overlapping the personnel key points on a time sequence to obtain a personnel moving track; and obtaining the acceleration of the person according to the movement track of the person.
The invention also provides a garbage transfer station site selection evaluation system based on artificial intelligence and CIM, which comprises:
the garbage transfer station information acquisition module is used for acquiring garbage transfer station information through a CIM (common information model); the garbage transfer station information comprises the existing garbage transfer station information and candidate garbage transfer station information;
the transportation index acquisition module is used for acquiring a garbage transportation terminal and a garbage generation area through the CIM; taking the sum of the distances from the candidate garbage transfer station position to the garbage transportation terminal and the garbage generation area route as a transportation index;
the service neighborhood intersection area acquisition module is used for setting a service neighborhood by taking the position of each garbage transfer station as an origin according to a preset neighborhood radius; adjusting the size of each service neighborhood according to the garbage yield in each service neighborhood; obtaining the intersection area of service neighborhoods between the candidate garbage transfer station and other garbage transfer stations;
the negative influence index acquisition module is used for acquiring a road image of a road with a similar distance from the existing garbage transfer station; acquiring movement information and personnel flow of personnel in the road image; the motion information comprises the acceleration and the posture of the person; obtaining a malodor grade according to the motion information; obtaining negative influence indexes corresponding to the personnel flow and the scale of the garbage transfer station according to the odor grade;
and the appropriateness obtaining module is used for obtaining the appropriateness of the position of the transfer station in the candidate garbage according to the service neighborhood intersection area, the transportation index and the negative influence index.
Further, the service neighborhood intersection area acquisition module further comprises a garbage yield acquisition module;
the garbage yield acquisition module is used for acquiring images of garbage generation areas in the service neighborhood; segmenting a garbage image from the garbage generation area image; obtaining the scale of the garbage site where the garbage is located in the garbage image; taking the area ratio of the garbage image to the garbage generation area image as a garbage ratio; and obtaining the garbage yield according to the garbage ratio and the garbage site scale.
Further, the service neighborhood intersection area obtaining module further comprises a service neighborhood size adjusting module;
the service neighborhood size adjusting module is used for reducing the size of the service neighborhood according to a preset adjusting step length when the difference value between the garbage output and the garbage transfer station size is larger than a preset first threshold value; when the difference value between the size of the garbage transfer station and the garbage yield is larger than the first threshold value, increasing the size of the service neighborhood according to the adjustment step length; when the absolute value of the difference value between the garbage yield and the garbage transfer station size is smaller than or equal to the first threshold value, the size of the service neighborhood is unchanged.
Further, the negative influence index obtaining module further comprises a malodor grade screening module;
the odor grade screening module is used for obtaining an initial odor grade corresponding to each person according to the motion information; the initial malodor level with the largest number of people is taken as the malodor level.
Further, the negative influence index acquisition module further comprises a road image processing module;
the road image processing module is used for sending the road image into a pre-trained personnel detection network and outputting personnel key point information; acquiring the personnel posture and the personnel flow through the personnel key point information; overlapping the personnel key points on a time sequence to obtain a personnel moving track; and obtaining the acceleration of the person according to the movement track of the person.
The invention has the following beneficial effects:
1. according to the embodiment of the invention, the optimal position of the candidate garbage transfer station is selected by calculating the appropriate combination of the positions of the candidate garbage transfer stations through the service neighborhood intersection area, the transportation index and the negative influence index, so that the urban garbage treatment efficiency is improved.
2. The embodiment of the invention constructs the service neighborhood of the garbage transfer station, and the service conflict degree between the garbage transfer stations is represented by the intersection area of the service neighborhood range of the candidate garbage transfer station and the service neighborhood range of the existing garbage transfer station, so that the waste of resources can be avoided, and the candidate garbage transfer station can be effectively and reasonably constructed.
3. According to the embodiment of the invention, the negative influence of the existing garbage transfer station on pedestrians is obtained by obtaining the road image of the road with the similar distance from the existing garbage transfer station, and the candidate garbage transfer station is evaluated by considering the negative influence index in the subsequent analysis, so that the site selection of the candidate garbage transfer station is more scientific and effective.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a garbage intermediate transfer station site selection evaluation method based on artificial intelligence and CIM according to an embodiment of the present invention;
fig. 2 is a block diagram of a garbage intermediate transit station site selection evaluation system based on artificial intelligence and CIM according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to a garbage transfer station selection evaluation method and system based on artificial intelligence and CIM according to the present invention, and the specific implementation, structure, features and effects thereof with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
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 invention belongs.
The following describes a specific scheme of a garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM in detail with reference to the accompanying drawings.
The application scenarios of the embodiment of the invention are as follows: and pre-selecting a plurality of candidate garbage transfer station addresses, and selecting the optimal address by analyzing the candidate garbage transfer station addresses.
Referring to fig. 1, a flowchart of a garbage intermediate station location evaluation method based on artificial intelligence and CIM according to an embodiment of the present invention is shown, where the method includes:
step S1: and obtaining the information of the garbage transfer station through a CIM (common information model), wherein the information of the garbage transfer station comprises the information of the existing garbage transfer station and the information of the candidate garbage transfer station.
The CIM model integrates multi-position and multi-scale information model data such as overground and underground, indoor and outdoor, current historical situation and the like of a city and city perception data on the basis of technologies such as a building information model, a geographic information system, an Internet of things and the like, and constructs a three-dimensional digital space city information organic complex. In the embodiment of the invention, in order to address the candidate garbage transfer station, the information of the candidate garbage transfer station needs to be analyzed according to the information of the existing garbage transfer station. And obtaining the information of the garbage transfer station through a CIM (common information model), wherein the information of the garbage transfer station comprises the information of the existing garbage transfer station and the information of the candidate garbage transfer station.
Step S2: and acquiring a garbage transportation terminal and a garbage generation area through a CIM model. And taking the sum of the distances from the position of the candidate garbage transfer station to the garbage transportation terminal and the garbage generation area as a transportation index.
The garbage transfer station is used as a central center of urban garbage treatment, and is required to receive garbage in a garbage generation area, treat the garbage and convey the garbage to garbage transport terminals such as a garbage landfill or a garbage incineration plant. Therefore, the length of the transit garbage transportation route in the candidate garbage needs to be considered in the address selection process.
And obtaining a garbage transportation terminal and a garbage generation area through a CIM (common information model), wherein a plurality of routes exist between the candidate garbage transfer station and the garbage transportation terminal and the garbage generation area, and the sum of distances of all the routes is used as a transportation index. Specifically, the road distance calculation formula is as follows:
wherein L is the distance of the road, n is the number of the roads, DiDistance of the ith route, σiIs the route weight of the ith route. In the embodiment of the invention, the routes are divided according to the distance, the nearest route is used as a main road, and the next nearest route is used as a secondary road and other roads. The route weight of the main road is 0.7, the route weight of the secondary road is 0.25, and the route weights of other roads are 0.05.
Step S3: and setting a service neighborhood by taking the position of the garbage transfer station as an origin, and adjusting the size of the service neighborhood according to the garbage output in the service neighborhood to obtain the intersection area of the service neighborhoods between the candidate garbage transfer station and the existing garbage transfer station.
The positions of all the trash transfer stations are obtained according to the trash transfer station information obtained in step S1. And setting a service neighborhood according to a preset neighborhood radius by taking the position of each garbage transfer station as an original point. The neighborhood radius is one hundred meters in embodiments of the invention. The service neighborhood set according to the neighborhood radius needs to adjust the size of the service neighborhood according to the garbage yield in the service neighborhood under the actual condition. And acquiring service neighborhoods of all the garbage transfer stations in the city, and further acquiring the intersection area of the service neighborhoods between the candidate garbage transfer stations and other garbage transfer stations.
The specific acquisition method of the garbage yield comprises the following steps:
there are various areas of waste generation in cities such as shopping malls, residential areas, etc. And acquiring images of the garbage generation area, which are acquired by monitoring near the garbage station, in the garbage generation area through a CIM (common information model). The garbage generation area image is image data of garbage accumulated in a garbage station before garbage cleaning in one day.
And segmenting the garbage image in the garbage generation area image. And obtaining the scale of the garbage station where the garbage is located in the garbage image. In the embodiment of the invention, the garbage segmentation network trained in advance is used for processing the garbage generation area image and outputting the garbage image. Training data for the garbage segmentation network generates region images for garbage containing garbage. And marking the garbage pixel points in the image of the garbage generation area to obtain marked data, wherein the mark of the garbage pixel points is 1, and the marks of the other garbage pixel points are 0. And training the garbage segmentation network by adopting a cross entropy loss function.
And obtaining the area of the garbage image through connected domain analysis, taking the area ratio of the garbage image to the image of the garbage generation area as a garbage ratio, and obtaining the garbage yield according to the garbage ratio and the scale of the garbage transfer station. Specifically, the garbage yield is obtained through a garbage yield formula:
wherein a is the garbage yield, V is the garbage transfer station scale, S is the garbage image area, and S is0The image area of the garbage generation area is shown, and epsilon is a garbage amount floating parameter. Epsilon can be set according to the actual garbage generation area. In the embodiment of the invention, the residential area is taken as the garbage generation area, and epsilon is set to be 2.
It should be noted that the service neighborhood includes a plurality of garbage generating areas, and the garbage yield of all the garbage generating areas is summed to obtain the garbage yield of the service neighborhood.
Adjusting the size of the service neighborhood according to the garbage yield in the service neighborhood specifically comprises:
when the difference value between the garbage yield and the garbage transfer station scale is larger than a preset first threshold value, reducing the size of a service neighborhood according to a preset adjustment step length;
when the difference value between the size of the garbage transfer station and the garbage yield is larger than the first threshold value, increasing the size of a service neighborhood according to the adjustment step length;
and when the absolute value of the difference value between the garbage yield and the garbage transfer station size is smaller than or equal to the first threshold, the size of the service neighborhood is not changed.
In an embodiment of the invention, the adjustment step size is set to ten meters.
The service neighborhood intersection area of the candidate garbage transfer station and other garbage transfer stations represents the conflict range of the two garbage transfer stations, and in the site selection process, the service neighborhood intersection area needs to be reduced as much as possible, so that resource waste is avoided.
Step S4: and obtaining the negative influence indexes of the scale and the human flow of the corresponding candidate garbage transfer station through the odor grade of the existing garbage transfer station.
The odor caused by garbage treatment of the garbage transfer station can affect the life of personnel, and the negative effects corresponding to the scale of the garbage transfer station and the flow of people at the position of the garbage transfer station need to be considered in the site selection process of the garbage transfer station.
And acquiring a road image of a road with a similar distance from the existing garbage transfer station. Motion information of the person in the road image is obtained. The motion information includes person acceleration and person posture. And obtaining negative influence indexes of corresponding personnel flow and the scale of the garbage transfer station according to the odor grade.
Specifically, obtaining the motion information of the person in the road image includes:
and (4) sending the road image into a pre-trained personnel detection network, and outputting personnel key point information. The personnel detection network in the embodiment of the invention specifically comprises:
1) road images containing personal information are used as training data. Marking the training data by taking the hand, elbow, shoulder central point and two-foot central point of the person as key points, and marking the hot spots by taking the key points as the center through Gaussian kernel convolution to obtain marked data. And (4) normalizing the training data and the labeling data.
2) The personnel detection network is of an encoding-decoding structure. The training data and the label data are sent as input data to an end-to-end training network in the network. And the personnel detection encoder performs characteristic extraction on the input data and outputs a characteristic diagram. The people detection decoder upsamples the feature map. The key points of the hands, the elbows and the shoulders are an output channel, the key points of the feet are an output channel, and large personnel key point heat maps such as original images are output. The person keypoint heat map includes person keypoint information.
3) Training by using a mean square error loss function.
And the personnel posture and the personnel flow can be obtained according to the personnel key point information. The odor generated by the garbage influences the passing personnel, and the passing of the person through the mouth and the nose can be covered when the person passes through the garbage transfer station, so that the included angle between the connecting line of the elbow key points and the connecting line of the elbow shoulder key points reflects the posture of the person in the embodiment of the invention.
And overlapping the key points of the feet on a time sequence to obtain a moving track of the personnel. And obtaining the acceleration of the person according to the movement track of the person. The speed of pedestrians passing through the garbage transfer station is accelerated by the odor generated by the garbage transfer station, so that the larger the acceleration of the personnel is, the larger the change of the posture of the personnel is, the larger the odor level is. In the embodiment of the invention, superposition is performed on the basis of a forgetting algorithm at a time sequence of 0.2 second and one frame. The specific calculation method for forgetting algorithm superposition is as follows:
X＝αx+(1-α)x′
wherein X is a current frame result, X' is a superposition result of a previous frame, X is a superposition calculation result including the current frame, and (1- α) is a forgetting coefficient, and in the embodiment of the invention, the value of α is 0.05.
In the embodiment of the invention, the odor grade is divided into 3 grades, and when the posture and the acceleration of the personnel are not changed, the odor grade is 1; when the posture of the person changes and lasts for a period of time and the acceleration of the person is not changed, the odor grade is 2; when both the posture of the person and the acceleration of the person change, the malodor level is 3.
Because the affected reactions among the personnel passing through the garbage transfer station are different, the initial odor grade corresponding to each personnel is obtained according to the movement information, and the initial odor grade with the largest number of the personnel is used as the final odor grade.
And obtaining a corresponding odor grade according to the scale of the candidate garbage transfer station and the pedestrian flow of the position of the candidate garbage transfer station, and taking the odor grade as a negative influence index of the candidate garbage transfer station. In the embodiment of the invention, the candidate garbage transfer station and the pedestrian flow at the corresponding position are sent to the classification network trained in advance, and the corresponding negative influence index is output.
Step S5: and obtaining the appropriateness of the position of the transfer station in the candidate garbage according to the service neighborhood intersection area, the transportation index and the negative influence index.
Normalizing the transportation index, the service neighborhood intersection area and the negative influence index to obtain a characteristic index [ tau ] representing the candidate garbage transfer stationa，τb，τc]. In the embodiment of the invention, the fitness calculation formula is as follows:
wherein the content of the first and second substances,
to a suitable degree, τaFor transportation purposes, τbTo serve the neighborhood intersection area, τcAs an indication of negative influence, ω1、ω2、ω3For the weight of the corresponding characteristic index, the embodiment of the invention is set as follows: omega1＝0.25、ω2＝0.25、ω3＝0.5。
The positions of the candidate garbage transfer stations can be comprehensively evaluated through appropriate sizes, and the optimal candidate garbage transfer station can be found from the positions of the candidate garbage transfer stations.
In summary, in the embodiment of the present invention, the information of the garbage transfer station is obtained through the CIM model, and the garbage transportation destination and the garbage generation area are obtained. And taking the sum of the distances from the position of the candidate garbage transfer station to the garbage transportation terminal and the garbage generation area as a transportation index. And setting a service neighborhood by taking the position of the garbage transfer station as an origin, and adjusting the size of the service neighborhood according to the garbage output in the service neighborhood to obtain the intersection area of the service neighborhoods between the candidate garbage transfer station and the existing garbage transfer station. And obtaining the negative influence indexes of the scale and the human flow of the corresponding candidate garbage transfer station through the odor grade of the existing garbage transfer station. And obtaining the appropriateness of the position of the transfer station in the candidate garbage according to the service neighborhood intersection area, the transportation index and the negative influence index. The influence of multiple aspects on the station selection of the candidate garbage is considered, so that the site selection is more scientific and efficient.
Referring to fig. 2, a block diagram of a garbage intermediate station selection and location evaluation system based on artificial intelligence and CIM according to an embodiment of the present invention is shown. The system comprises:
and the garbage transfer station information obtaining module 101 is configured to obtain the garbage transfer station information through a CIM model. The garbage transfer station information comprises the existing garbage transfer station information and the candidate garbage transfer station information.
A transportation index obtaining module 102, configured to obtain a garbage transportation destination and a garbage generation area through a CIM model, and use a sum of distances from a candidate garbage transfer station to the garbage transportation destination and the garbage generation area as a transportation index;
and the service neighborhood intersection area acquisition module 103 is used for setting a service neighborhood according to a preset neighborhood radius by taking the position of each garbage transfer station as an origin, adjusting the size of the service neighborhood according to the garbage output in each service neighborhood, and acquiring a service neighborhood intersection plane between the candidate garbage transfer station and other garbage transfer stations.
And the negative influence index acquisition module 104 is used for acquiring a road image of a road close to the existing garbage transfer station. And obtaining the motion information and the personnel flow of the personnel in the road image. The motion information includes person acceleration and person posture. And obtaining the odor grade according to the motion information. And obtaining negative influence indexes of corresponding personnel flow and the scale of the garbage transfer station according to the odor grade.
And the appropriateness obtaining module 105 is configured to obtain an appropriateness of the position of the relay station in the candidate garbage according to the service neighborhood intersection area, the transportation index and the negative influence index.
Preferably, the service neighborhood intersection area obtaining module 103 further includes a garbage yield obtaining module. The garbage yield acquisition module is used for acquiring images of garbage generation areas in the service neighborhood. And segmenting the garbage image in the garbage generation area image. And obtaining the scale of the garbage site where the garbage is located in the garbage image. And taking the area ratio of the garbage image and the garbage generation area image as a garbage ratio. And obtaining the garbage yield according to the garbage ratio and the garbage station scale.
Preferably, the service neighborhood intersection area obtaining module 103 further includes a service neighborhood size adjusting module. And the service neighborhood size adjusting module is used for reducing the size of the service neighborhood according to a preset adjusting step length when the difference value between the garbage output and the garbage transfer station size is larger than a preset first threshold value. And when the difference value between the size of the garbage transfer station and the garbage yield is larger than a first threshold value, increasing the size of the service neighborhood according to the adjustment step length. And when the absolute value of the difference value between the garbage yield and the garbage transfer station size is smaller than or equal to a first threshold value, the size of the service neighborhood is unchanged.
Preferably, the negative impact index obtaining module 104 further comprises a malodor level screening module. And the odor grade screening module is used for obtaining an initial odor grade corresponding to each person according to the movement information. The initial malodor level with the largest number of people is taken as the malodor level.
Preferably, the negative impact indicator obtaining module 104 further includes a road image processing module. And the road image processing module is used for sending the road image into a pre-trained personnel detection network and outputting personnel key point information. And acquiring the personnel posture and the personnel flow through the personnel key point information. And overlapping the personnel key points on a time sequence to obtain a personnel moving track. And obtaining the acceleration of the person according to the movement track of the person.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A garbage transfer station site selection evaluation method based on artificial intelligence and CIM is characterized by comprising the following steps:
obtaining information of the garbage transfer station through a CIM (common information model); the garbage transfer station information comprises the existing garbage transfer station information and candidate garbage transfer station information;
obtaining a garbage transportation terminal and a garbage generation area through the CIM; taking the sum of the distances from the candidate garbage transfer station position to the garbage transportation terminal and the garbage generation area route as a transportation index;
setting a service neighborhood according to a preset neighborhood radius by taking the position of each garbage transfer station as an origin; adjusting the size of each service neighborhood according to the garbage yield in each service neighborhood; obtaining the intersection area of service neighborhoods between the candidate garbage transfer station and other garbage transfer stations;
acquiring a road image of the road with the similar distance from the existing garbage transfer station; acquiring movement information and personnel flow of personnel in the road image; the motion information comprises the acceleration and the posture of the person; obtaining a malodor grade according to the motion information; obtaining negative influence indexes corresponding to the personnel flow and the scale of the garbage transfer station according to the odor grade;
and obtaining the appropriateness of the position of the transfer station in the candidate garbage according to the service neighborhood intersection area, the transportation index and the negative influence index.
2. The artificial intelligence and CIM-based site selection evaluation method for the garbage intermediate transfer station is characterized in that the garbage yield acquisition method comprises the following steps:
acquiring a garbage generation area image in the service neighborhood;
segmenting a garbage image from the garbage generation area image; obtaining the scale of the garbage site where the garbage is located in the garbage image;
taking the area ratio of the garbage image to the garbage generation area image as a garbage ratio;
and obtaining the garbage yield according to the garbage ratio and the garbage site scale.
3. The method of claim 1, wherein the adjusting the size of the service neighborhood according to the garbage yield in the service neighborhood comprises:
when the difference value between the garbage yield and the garbage transfer station scale is larger than a preset first threshold value, reducing the size of the service neighborhood according to a preset adjustment step length;
when the difference value between the size of the garbage transfer station and the garbage yield is larger than the first threshold value, increasing the size of the service neighborhood according to the adjustment step length;
when the absolute value of the difference value between the garbage yield and the garbage transfer station size is smaller than or equal to the first threshold value, the size of the service neighborhood is unchanged.
4. The artificial intelligence and CIM based site selection evaluation method for the garbage transfer station according to claim 1, wherein the obtaining the odor grade of the existing garbage transfer station according to the motion information further comprises:
obtaining an initial malodor grade corresponding to each person according to the movement information; the initial malodor level with the largest number of people is taken as the malodor level.
5. The method for evaluating the site selection of the garbage intermediate transfer station based on artificial intelligence and CIM as claimed in claim 1, wherein the obtaining of the motion information and the personnel flow of the personnel in the road image comprises:
sending the road image into a pre-trained personnel detection network, and outputting personnel key point information;
acquiring the personnel posture and the personnel flow through the personnel key point information;
overlapping the personnel key points on a time sequence to obtain a personnel moving track; and obtaining the acceleration of the person according to the movement track of the person.
6. A garbage transfer station site selection evaluation system based on artificial intelligence and CIM is characterized by comprising:
the garbage transfer station information acquisition module is used for acquiring garbage transfer station information through a CIM (common information model); the garbage transfer station information comprises the existing garbage transfer station information and candidate garbage transfer station information;
the transportation index acquisition module is used for acquiring a garbage transportation terminal and a garbage generation area through the CIM; taking the sum of the distances from the candidate garbage transfer station position to the garbage transportation terminal and the garbage generation area route as a transportation index;
the service neighborhood intersection area acquisition module is used for setting a service neighborhood by taking the position of each garbage transfer station as an origin according to a preset neighborhood radius; adjusting the size of each service neighborhood according to the garbage yield in each service neighborhood; obtaining the intersection area of service neighborhoods between the candidate garbage transfer station and other garbage transfer stations;
the negative influence index acquisition module is used for acquiring a road image of a road with a similar distance from the existing garbage transfer station; acquiring movement information and personnel flow of personnel in the road image; the motion information comprises the acceleration and the posture of the person; obtaining a malodor grade according to the motion information; obtaining negative influence indexes corresponding to the personnel flow and the scale of the garbage transfer station according to the odor grade;
and the appropriateness obtaining module is used for obtaining the appropriateness of the position of the transfer station in the candidate garbage according to the service neighborhood intersection area, the transportation index and the negative influence index.
7. The system of claim 6, wherein the service neighborhood intersection area obtaining module further comprises a garbage yield obtaining module;
the garbage yield acquisition module is used for acquiring images of garbage generation areas in the service neighborhood; segmenting a garbage image from the garbage generation area image; obtaining the scale of the garbage site where the garbage is located in the garbage image; taking the area ratio of the garbage image to the garbage generation area image as a garbage ratio; and obtaining the garbage yield according to the garbage ratio and the garbage site scale.
8. The system of claim 6, wherein the service neighborhood intersection area obtaining module further comprises a service neighborhood size adjusting module;
the service neighborhood size adjusting module is used for reducing the size of the service neighborhood according to a preset adjusting step length when the difference value between the garbage output and the garbage transfer station size is larger than a preset first threshold value; when the difference value between the size of the garbage transfer station and the garbage yield is larger than the first threshold value, increasing the size of the service neighborhood according to the adjustment step length; when the absolute value of the difference value between the garbage yield and the garbage transfer station size is smaller than or equal to the first threshold value, the size of the service neighborhood is unchanged.
9. The system for site selection of the garbage transfer station based on artificial intelligence and CIM as claimed in claim 6, wherein the negative impact index obtaining module further comprises a malodor level screening module;
the odor grade screening module is used for obtaining an initial odor grade corresponding to each person according to the motion information; the initial malodor level with the largest number of people is taken as the malodor level.
10. The system for evaluating the site selection of the garbage transfer station based on artificial intelligence and CIM as claimed in claim 6, wherein the negative impact index obtaining module further comprises a road image processing module;
the road image processing module is used for sending the road image into a pre-trained personnel detection network and outputting personnel key point information; acquiring the personnel posture and the personnel flow through the personnel key point information; overlapping the personnel key points on a time sequence to obtain a personnel moving track; and obtaining the acceleration of the person according to the movement track of the person.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110676566.6A CN113435637B (en) | 2021-06-16 | 2021-06-16 | Garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110676566.6A CN113435637B (en) | 2021-06-16 | 2021-06-16 | Garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113435637A true CN113435637A (en) | 2021-09-24 |
| CN113435637B CN113435637B (en) | 2022-12-30 |
Family
ID=77756558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110676566.6A Active CN113435637B (en) | 2021-06-16 | 2021-06-16 | Garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113435637B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115271190A (en) * | 2022-07-19 | 2022-11-01 | 中环洁环境有限公司 | Method and device for distributing centralized garbage recycling points |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107274017A (en) * | 2017-06-13 | 2017-10-20 | 武汉大学 | The facility Optimization Method for Location-Selection of resident's activity time and space idea in a kind of consideration city |
| CN111598359A (en) * | 2020-06-04 | 2020-08-28 | 上海燕汐软件信息科技有限公司 | Logistics station site selection method and system |
| CN111611949A (en) * | 2020-05-25 | 2020-09-01 | 陈金山 | Intelligent urban water area garbage density detection method based on CIM and block chain |
| CN112862176A (en) * | 2021-02-01 | 2021-05-28 | 上海元卓信息科技有限公司 | Public service facility site selection method and device |
-
2021
- 2021-06-16 CN CN202110676566.6A patent/CN113435637B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107274017A (en) * | 2017-06-13 | 2017-10-20 | 武汉大学 | The facility Optimization Method for Location-Selection of resident's activity time and space idea in a kind of consideration city |
| CN111611949A (en) * | 2020-05-25 | 2020-09-01 | 陈金山 | Intelligent urban water area garbage density detection method based on CIM and block chain |
| CN111598359A (en) * | 2020-06-04 | 2020-08-28 | 上海燕汐软件信息科技有限公司 | Logistics station site selection method and system |
| CN112862176A (en) * | 2021-02-01 | 2021-05-28 | 上海元卓信息科技有限公司 | Public service facility site selection method and device |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115271190A (en) * | 2022-07-19 | 2022-11-01 | 中环洁环境有限公司 | Method and device for distributing centralized garbage recycling points |
| CN115271190B (en) * | 2022-07-19 | 2023-05-19 | 中环洁环境有限公司 | Method and device for arranging garbage centralized recovery points |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113435637B (en) | 2022-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Transit ridership estimation with network Kriging: A case study of Second Avenue Subway, NYC | |
| CN108629978A (en) | A kind of traffic trajectory predictions method based on higher-dimension road network and Recognition with Recurrent Neural Network | |
| Veloso et al. | Sensing urban mobility with taxi flow | |
| Schneider et al. | Method to adjust Institute of Transportation Engineers vehicle trip-generation estimates in smart-growth areas | |
| Su et al. | Transboundary air pollution and environmental justice: Vancouver and Seattle compared | |
| CN105493109A (en) | Air quality inference using multiple data sources | |
| CN111653096A (en) | Urban trip mode identification method based on mobile phone signaling data | |
| Yudhistira et al. | Transportation network and changes in urban structure: Evidence from the Jakarta Metropolitan Area | |
| CN110400462B (en) | Track traffic passenger flow monitoring and early warning method and system based on fuzzy theory | |
| Yamamoto et al. | Structured random walk parameter for heterogeneity in trip distance on modeling pedestrian route choice behavior at downtown area | |
| Lee et al. | Automatic physical activity and in‐vehicle status classification based on GPS and accelerometer data: A hierarchical classification approach using machine learning techniques | |
| CN108549976A (en) | Smart travel big data analysis method | |
| CN113435637B (en) | Garbage transfer station site selection evaluation method and system based on artificial intelligence and CIM | |
| Halim et al. | On finding optimum commuting path in a road network: a computational approach for smart city traveling | |
| Zalzal et al. | Assessing the transferability of landuse regression models for ultrafine particles across two Canadian cities | |
| Wang et al. | Hybrid model for prediction of carbon monoxide and fine particulate matter concentrations near a road intersection | |
| CN113159371B (en) | Unknown target feature modeling and demand prediction method based on cross-modal data fusion | |
| Arnesen et al. | A forward Markov model for predicting bicycle speed | |
| Cohen et al. | Pedestrian Traffic flow prediction based on ANN model and OSM data | |
| Panovski et al. | Real-time public transportation prediction with machine learning algorithms | |
| Ku et al. | Assessment of the resilience of pedestrian roads based on image deep learning models | |
| Hannan et al. | Feature extraction using Hough transform for solid waste bin level detection and classification | |
| Talaat et al. | Mobile monitoring and spatial prediction of black carbon in Cairo, Egypt | |
| CN115761519A (en) | Index prediction method, index prediction device, index prediction apparatus, storage medium, and program product | |
| Kar et al. | Intelligent traffic prediction by combining weather and road traffic condition information: a deep learning-based approach |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221205 Address after: 518000 21C, North Block, Baihui Building, No. 3019, Sungang East Road, Songyuan Community, Guiyuan Street, Luohu District, Shenzhen, Guangdong Applicant after: Shenzhen yunzhiping Information Technology Co.,Ltd. Address before: 523000 Room 501, No. 2, Guancheng section, Dongcheng West Road, Guancheng street, Dongguan City, Guangdong Province Applicant before: Guangdong shikelang Environmental Protection Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |