Garbage production capacity prediction method and device, storage medium and program product

Abstract

The invention relates to the technical field of artificial intelligence, and particularly provides a garbage production capacity prediction method and device, a storage medium and a program product. According to the method, by constructing a road network Voronoi diagram of a garbage collection point, the total length of roads in the strength range of the garbage collection point can be calculated, and then the average garbage intensity coefficient is calculated by combining the total length, single-day garbage total amount data, single-day people flow total amount and per capita browsing time of a to-be-predicted area; and finally, based on the average garbage intensity coefficient, the tourist visiting speed, the number of tourists entering the to-be-predicted area at the prediction moment, the total length and the shortest distance between the garbage collection point and the entrance of the to-be-predicted area, the garbage production amount of the garbage collection point at the prediction moment is predicted. By adopting the scheme of the embodiment, the garbage production capacity of the garbage collection point of the to-be-predicted region at the prediction moment is predicted.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to a method, device, storage medium, and program product for predicting waste production. Background Technology

[0002] Tourism has become an indispensable part of the daily lives of Chinese people. Scenic spots are often overcrowded during holidays, and untimely garbage collection can greatly affect the tourist experience. Therefore, garbage collection and management is an important part of scenic spots, parks and other similar venues.

[0003] Common methods for predicting waste generation in existing technologies are as follows: One is the waste generation prediction method based on machine learning. This method mainly involves collecting data on the amount of urban domestic waste generated within a preset time period and N socio-economic factors to form a dataset. Machine learning is then used to obtain the best-performing model, which is then used to predict the amount of urban domestic waste generated under specific future scenarios.

[0004] Machine learning-based waste generation prediction methods are mainly applicable to large-scale urban areas with complex human activities. They require the collection of a large amount of socio-economic data for model training, and the predictions are based on the total amount of waste generated in the entire city, rather than the waste production of a single trash can. Therefore, these methods are not suitable for predicting the waste production of trash cans in scenic areas. Summary of the Invention

[0005] This disclosure is made in view of the above-mentioned problems. This disclosure provides a method, apparatus, storage medium, and program product for predicting waste production.

[0006] According to a first aspect of this disclosure, a method for predicting waste production is provided, comprising:

[0007] Obtain road vector data of the area to be predicted and data on the location of garbage collection points within the area to be predicted;

[0008] Using the location data of the collection points as the generating elements, a Venn diagram of the road network of the garbage collection points is constructed based on the road vector data and the location data of the collection points;

[0009] Based on the Vinograph of the road network, calculate the total length of the roads within the sphere of influence of the garbage collection point;

[0010] Based on the total length, the daily total amount of garbage in the area to be predicted, the daily total number of people, and the average browsing time per person in the area to be predicted, the average garbage intensity coefficient is calculated.

[0011] Based on the average waste intensity coefficient, the speed at which tourists visit the area to be predicted, the number of tourists entering the area to be predicted at the predicted time, the total length, and the shortest distance between the waste collection point and the entrance to the area to be predicted, the waste production of the waste collection point at the predicted time is predicted.

[0012] Furthermore, according to the waste production prediction method of the first aspect of this disclosure, based on the Venn diagram of the road network, the total length of roads within the sphere of influence of the waste collection point is calculated, including:

[0013] Based on the collected road images within the sphere of influence, the pedestrian density of the road segments in the road images is calculated;

[0014] Based on the pedestrian density, calculate the weight of the road class to which the road segment belongs;

[0015] Based on the weights and the geometric lengths of the graded roads obtained through the Venn diagram of the road network, the weighted lengths of the graded roads are calculated.

[0016] The total length of roads within the sphere of influence is obtained by summing the weighted lengths of all roads of the specified level.

[0017] Furthermore, according to the waste production prediction method of the first aspect of this disclosure, based on collected road images within the sphere of influence, the pedestrian density of road segments in the road images is calculated, including:

[0018] The number of tourists included in the road images within the sphere of influence collected at each collection time is counted; and the total geometric length of the collected roads is obtained by multiplying the geometric length of the road segments included in the road images by the number of collection times.

[0019] Sum the number of tourists to obtain the total number of tourists;

[0020] The population density is obtained by calculating the quotient of the total number of tourists and the total geometric length of the collected roads.

[0021] Furthermore, according to the waste production prediction method of the first aspect of this disclosure, based on the total length, the daily waste volume data of the area to be predicted, the daily pedestrian flow, and the average browsing time per person in the area to be predicted, an average waste intensity coefficient is calculated, including:

[0022] Calculate the product of the total length, the total daily visitor flow, and the average browsing time per person;

[0023] The average waste intensity coefficient is obtained by calculating the quotient of the product of the total daily waste volume and the average daily waste volume.

[0024] Furthermore, according to the waste production prediction method of the first aspect of this disclosure, based on the average waste intensity coefficient, the speed at which tourists visit the area to be predicted, the number of tourists entering the area to be predicted at the predicted time, the total length, and the shortest distance between the waste collection point and the entrance to the area to be predicted, the waste production of the waste collection point at the predicted time is predicted, including:

[0025] If the shortest distance is greater than or equal to the tourist tour distance calculated based on the predicted time, the open tour time of the area to be predicted, and the tour speed, the waste production of the waste collection point is determined to be 0.

[0026] If the shortest distance is less than the tourist tour distance, the product of the average waste intensity coefficient, the total length, and the number of tourists is integrated from the opening time to the predicted time to obtain the waste production of the waste collection point at the predicted time.

[0027] Furthermore, according to the waste production prediction method of the first aspect of this disclosure, the weight of the road's class based on the pedestrian density is calculated, including:

[0028] Obtain the maximum and minimum pedestrian density for all road sections within the defined area of ​​influence;

[0029] Based on the maximum and minimum values, multiple pedestrian density intervals are obtained, and a weight is assigned to each pedestrian density interval;

[0030] From the plurality of pedestrian density intervals, a target pedestrian density interval including the pedestrian density is determined;

[0031] The weight corresponding to the target pedestrian density range is used as the weight of the road's classification level.

[0032] According to a second aspect of this disclosure, a waste production prediction device is provided, comprising:

[0033] The acquisition module is used to acquire road vector data of the area to be predicted and collection point location data of garbage collection points located within the area to be predicted;

[0034] The construction module is used to construct a road network Venn diagram of the garbage collection points based on the road vector data and the collection point location data, using the collection point location data as the generation element.

[0035] The first calculation module is used to calculate the total length of roads within the sphere of influence of the garbage collection point based on the road network Veno diagram;

[0036] The second calculation module is used to calculate the average garbage intensity coefficient based on the total length, the daily garbage volume data of the area to be predicted, the daily pedestrian flow, and the average browsing time per person in the area to be predicted.

[0037] The prediction module is used to predict the amount of waste produced by the waste collection point at the predicted time, based on the average waste intensity coefficient, the speed at which tourists visit the area to be predicted, the number of tourists entering the area to be predicted at the predicted time, the total length, and the shortest distance between the waste collection point and the entrance of the area to be predicted.

[0038] According to a third aspect of this disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the steps of the method described in the first aspect.

[0039] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided that stores a computer program / instructions thereon, which, when executed by a processor, implement the steps of the method described in the first aspect.

[0040] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the steps of the method described in the first aspect.

[0041] As will be described in detail below, by constructing a Venn diagram of the road network of garbage collection points, the total length of roads within the strength range of the garbage collection points can be calculated. Then, combining this total length, daily garbage volume data, daily pedestrian flow data, and the average browsing time per person in the area to be predicted, an average garbage intensity coefficient is calculated. Finally, based on the average garbage intensity coefficient, the visitor's browsing speed, the number of visitors entering the area to be predicted at the predicted time, the total length, and the shortest distance between the garbage collection point and the entrance to the area to be predicted, the garbage production volume of the garbage collection point at the predicted time is predicted. The solution in this embodiment achieves the prediction of the garbage production volume of the garbage collection points in the area to be predicted at the predicted time.

[0042] It should be understood that both the foregoing general description and the following detailed description are exemplary and intended to provide further illustration of the claimed technology. Attached Figure Description

[0043] The above and other objects, features, and advantages of this disclosure will become more apparent from the more detailed description of the embodiments thereof in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0044] Figure 1 This is a flowchart illustrating a waste production prediction method according to an embodiment of the present disclosure.

[0045] Figure 2 This is a schematic diagram of a road network of trash cans in a scenic area, illustrating an embodiment of the present disclosure.

[0046] Figure 3 This is a schematic diagram illustrating the function of the number of tourists entering the scenic area per unit time according to an embodiment of this disclosure.

[0047] Figure 4 This is a schematic diagram illustrating the storage of the weighted length of roads in the attribute table of trash can location data according to an embodiment of this disclosure.

[0048] Figure 5 This is a schematic diagram illustrating a waste production prediction device according to an embodiment of the present disclosure.

[0049] Figure 6 This is a hardware block diagram illustrating an electronic device according to an embodiment of the present disclosure.

[0050] Figure 7 This is a schematic diagram illustrating a computer-readable storage medium according to an embodiment of the present disclosure. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0052] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0053] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0054] As mentioned earlier, the waste production prediction methods in related technologies are mainly applicable to large-scale urban areas with complex human activities. They require the collection of a large amount of socio-economic data for model training, and the predictions made are for the total amount of waste generated in the entire city, rather than the waste production of a single trash can. Therefore, these methods are not suitable for predicting the waste production of trash cans in scenic areas.

[0055] To alleviate the technical problems existing in related technologies, this application provides a method, device, storage medium, and program product for predicting waste production. The method constructs a Venn diagram of the road network of waste collection points, calculates the total length of roads within the strength range of each waste collection point, and then combines this total length, daily waste volume data, daily pedestrian flow data, and average browsing time per person in the area to be predicted to calculate an average waste intensity coefficient. Finally, based on the average waste intensity coefficient, the visiting speed of tourists, the number of tourists entering the area to be predicted at the predicted time, the total length, and the shortest distance between the waste collection point and the entrance to the area to be predicted, the waste production of the waste collection point at the predicted time is predicted. This embodiment achieves the prediction of the waste production of waste collection points in the area to be predicted at the predicted time.

[0056] To facilitate understanding of this embodiment, a detailed description of the waste production prediction method disclosed in this disclosure embodiment will be provided first. The execution subject of the waste production prediction method provided in this disclosure embodiment is generally an electronic device with a certain computing power, such as a terminal device, a server, or other processing device. In some possible implementations, the waste production prediction method can be implemented by a processor calling computer-readable instructions stored in memory.

[0057] See Figure 1 The diagram shows a flowchart of a waste production prediction method provided in this embodiment of the present disclosure. The method includes the following steps:

[0058] Step 101: Obtain road vector data of the area to be predicted and collection point location data of garbage collection points located within the area to be predicted.

[0059] In this application, the area to be predicted includes, but is not limited to, parks, scenic areas, etc., and the garbage collection points include, but are not limited to, garbage bins, garbage stations, etc. The road vector data of the area to be predicted includes, but is not limited to, the latitude and longitude information of the area to be predicted. Similarly, the location data of the garbage collection points includes, but is not limited to, the latitude and longitude information of the garbage collection points.

[0060] Step 102: Using the collection point location data as the generation element, construct a Venn diagram of the road network of garbage collection points based on road vector data and collection point location data.

[0061] Using the location data of each garbage collection point as the originating element, the road network of the area to be predicted is expanded along the road network until the boundary of other garbage collection points is encountered, thus obtaining the Voronoi diagram of the road network for a single garbage collection point. Taking a scenic area as an example, when constructing the Voronoi diagram of the road network for a garbage bin within the scenic area, the garbage bin location data is used as the originating element, and the road network of the scenic area is expanded along the road network until the boundary of other garbage bins is encountered, thus obtaining the Voronoi diagram of the road network for a single garbage bin.

[0062] As an example, the following is given: Figure 2 The diagram shown is a Venn diagram illustrating the road network of trash cans within the scenic area. Figure 2 As shown, Figure 2 The three squares in the diagram represent three trash cans placed within the scenic area. The roads of the same color connected to each trash can form the road network of that trash can, as shown in the Voronoi diagram.

[0063] Step 103: Based on the road network Veno graph, calculate the total length of roads within the sphere of influence of the garbage collection point.

[0064] The sphere of influence of a garbage collection point includes all roads in the Voronoi diagram of its road network. After constructing the Voronoi diagram of the road network, the length of each road segment within each road network segment can be calculated. The length of a road can be calculated segmentally based on the coordinates of the road vector data, or it can be directly obtained from the GIS software.

[0065] Because the number of tourists carried by roads of different grades varies greatly, the amount of garbage generated will also vary greatly. Therefore, different weights need to be set for different roads in order to calculate the amount of garbage.

[0066] In an optional embodiment, step 103 may include the following steps:

[0067] Based on the collected road images within the sphere of influence, calculate the pedestrian density of road segments in the road images;

[0068] The weight of the road segment's class is calculated based on pedestrian density;

[0069] The weighted length of the graded roads is calculated based on the weights and the geometric lengths of the graded roads obtained through the Vinograph of the road network.

[0070] The total length of roads within the territory is obtained by summing the weighted lengths of all levels of roads within the territory.

[0071] In this embodiment, the grade of each road in the area to be predicted is pre-set. Taking a scenic area as an example, the highest grade can be set for main roads that are accessible for cycling and walking, followed by gravel roads that are only accessible for walking, and so on. For road segments in the road image, image recognition and comparison can be used to detect which road segment in the area to be detected belongs to, and then the road to which the road segment belongs is determined as the road grade. It should be understood that the weight of a road segment is the weight of the road grade to which the road segment belongs.

[0072] The weighted length of a graded road is the product of its geometric length and its weight.

[0073] In one alternative embodiment, the pedestrian density of a road segment in a road image can be calculated by counting the number of tourists in the road image.

[0074] In practice, calculating the pedestrian density of road segments within the acquired road images that are within the sphere of influence can include the following steps:

[0075] The number of tourists included in the road images within the area of ​​influence collected at each collection time is counted; and the total geometric length of the collected roads is obtained by multiplying the geometric length of the road segments included in the road images by the number of collection times.

[0076] Sum the number of tourists to get the total number of tourists;

[0077] The population density is obtained by calculating the quotient of the total number of tourists and the total geometric length of the collected roads.

[0078] The formula for calculating crowd density is as follows:

[0079]

[0080] Among them, p1, p2…p n Let P be the number of tourists included in the road images captured at different times, l be the geometric length of the road segment included in the road image, n be the number of times captured, and P be the number of tourists included in the road images. i This represents the pedestrian density of a road segment in the road image.

[0081] In one alternative embodiment, pedestrian density intervals can be divided based on the weights of all road segments within the territory, and the weights of graded roads can be determined by combining the pedestrian density intervals.

[0082] In practice, calculating the weight of a road's classification based on pedestrian density can include the following steps:

[0083] Obtain the maximum and minimum pedestrian density for all road sections within the territory's influence;

[0084] Based on the maximum and minimum values, multiple pedestrian density intervals are obtained, and a weight is assigned to each pedestrian density interval.

[0085] From multiple pedestrian density ranges, determine the target pedestrian density range that includes pedestrian density;

[0086] The weight corresponding to the target pedestrian density range is used as the weight of the road's classification level.

[0087] As an example, the following diagram illustrates the division of pedestrian density zones and the assignment of weights to these zones:

[0088] Let P be the maximum pedestrian density of the road segment obtained within the sphere of influence. max The minimum pedestrian density is P min The road classification is divided into five levels, and a corresponding weight value W is assigned to roads of different levels. i ,Right now

[0089] W i =0.2;

[0090] W i =0.4;

[0091] W i =0.6;

[0092] W i =0.8;

[0093] W i =1.

[0094] Step 104: Calculate the average garbage intensity coefficient based on the total length, the daily garbage volume of the area to be predicted, the daily pedestrian flow, and the average browsing time per person in the area to be predicted.

[0095] In the application, when calculating the average visit time per person in the area to be predicted, multiple camera images of tourists' faces are randomly captured in the area. Then, AI is used to search the camera recordings using image search to obtain the earliest and latest times of each tourist's appearance in the scenic area. Subtracting these times from each tourist's appearance time gives the visit time for each tourist. Finally, the average visit time of the scenic area is calculated by averaging the visit times of multiple tourists.

[0096] It should be understood that the daily total amount of garbage and the daily total number of people in the area to be predicted can be obtained directly from the management of the area.

[0097] It should be understood that the daily total garbage data and the daily total pedestrian flow data can be the total garbage data and the total pedestrian flow data of a certain historical day, or they can be the average of the total garbage data and the average of the total pedestrian flow data within a preset historical time range.

[0098] In an optional embodiment, step 104 may specifically include the following steps:

[0099] Calculate the product of total length, total daily visitor volume, and average browsing time per person;

[0100] The average waste intensity coefficient is obtained by calculating the quotient of the product of the total daily waste volume and the average waste intensity coefficient.

[0101] When expressed as a formula, the formula for calculating the average waste intensity coefficient can be:

[0102]

[0103] Where C is the average waste intensity coefficient, G t For daily waste volume data, P t ∑V represents the total daily pedestrian flow. i denoted as the total length, and T represents the average browsing time per person.

[0104] The average waste intensity coefficient C can be understood as the amount of waste generated by each tourist per unit time along a weighted length of road in the area to be predicted. For example, the amount of waste G generated by a scenic area in one day. t For a volume of 100m³, the total pedestrian flow is P. t For 10,000 visitors, the weighted total length of the scenic area roads is ∑V i The route is 10km long, and the average tour time is 1 hour. The average waste intensity coefficient C is calculated to be 0.001m / person / hour / km, which means that each tourist generates 0.001 cubic meters, or 1 liter, of waste per hour on every 1 kilometer of road.

[0105] It should be understood that if the management of the area to be predicted can provide data on waste volume and pedestrian flow over multiple days, multiple average waste intensity coefficients can be calculated and averaged to obtain the final average waste intensity coefficient.

[0106] Step 105: Based on the average waste intensity coefficient, the speed at which tourists visit the area to be predicted, the number of tourists entering the area to be predicted at the predicted time, the total length, and the shortest distance between the waste collection point and the entrance to the area to be predicted, predict the amount of waste produced at the waste collection point at the predicted time.

[0107] In application, the prediction time can be any time within the open time of the area to be predicted, and this embodiment does not impose specific limitations on it.

[0108] In an optional embodiment, step 105 may include the following steps:

[0109] If the shortest distance is greater than or equal to the tourist tour distance calculated based on the predicted time, the open tour time of the area to be predicted, and the tour speed, the waste production of the waste collection point is determined to be 0.

[0110] When the shortest distance is less than the tourist tour distance, the product of the average waste intensity coefficient, total length and number of tourists is integrated from the opening time to the predicted time to obtain the waste production at the waste collection point at the predicted time.

[0111] Taking a scenic area as an example, the number of tourists entering the scenic area per unit time can be regarded as a function of time t, denoted as f(t). Assuming the opening time of the scenic area is t0, the amount of garbage in a certain trash can in the scenic area up to time t1 can be calculated as follows:

[0112]

[0113] Among them, G i To predict the amount of waste produced at a waste collection point at the predicted time, d min V represents the shortest distance from the trash can to the entrance of the scenic area, and d represents the speed of the visitor's tour. min ≥V*(t1-t0) indicates that the tourist has not yet visited the trash can, and the amount of trash at this time is 0; similarly, d min <V*(t1-t0) indicates that the tourist has reached the trash can. The amount of trash at this point can be calculated by integrating the function f(t) with reference to the above formula.

[0114] In practice, the function f(t) representing the number of tourists entering the scenic area per unit time can be approximated as a piecewise function, such as... Figure 3As shown, the opening hours of a scenic area are from 8:00, and tourists are not allowed to enter after 18:00 in the afternoon. By statistically counting the number of tourists in real time, the piecewise values of the number of tourists f(t) in the scenic area can be obtained. When 8:00 < t ≤ 9:00, the value of f(t) is 231 people per hour.

[0115] Of course, in order to obtain a more accurate prediction effect, the statistical calculation time of the passenger flow can also be shortened as much as possible, such as 1 minute. Scenic areas with conditions can even refresh the number of tourists once a second. In addition, when calculating, it should be noted that the time unit needs to be consistent with the unit of the average browsing time. For example, if the time unit of the average browsing time is hours, the unit of f(t) here should be: people per hour.

[0116] In the solution provided in this embodiment, by constructing the road network Voronoi diagram of the garbage collection points, the total length of the roads within the power range of the garbage collection points can be calculated. Then, combined with the total length, the daily total garbage volume data, the daily total pedestrian flow, and the average browsing time per capita in the area to be predicted, the average garbage intensity coefficient can be calculated. Finally, based on the average garbage intensity coefficient, the browsing speed of tourists, the number of tourists entering the area to be predicted at the prediction moment, the total length, and the shortest distance between the garbage collection point and the entrance of the area to be predicted, the garbage production volume of the garbage collection point at the prediction moment can be predicted. The solution of this embodiment realizes the prediction of the garbage production volume of the garbage collection point in the area to be predicted at the prediction moment.

[0117] Taking the area to be predicted as a scenic area as an example, the garbage production volume prediction method of this application will be introduced below.

[0118] The garbage in the scenic area mainly comes from human activities, and most of the human activities are carried out based on the roads in the scenic area. The trash cans (points) in the scenic area are usually arranged beside the roads. The method of the network Voronoi diagram is very suitable for spatially dividing the roads in the scenic area according to the positions of the trash cans, and then calculating the spatial range of the road network radiated by each trash can. The garbage generated by human behavior within this range will probably converge to the trash can point at its center; then, combined with the overall pedestrian flow parameters of the scenic area, the garbage volume of each trash can can be predicted.

[0119] The garbage production volume prediction method proposed in this embodiment specifically requires the following processes: 1) Basic data collection and preprocessing, including scenic area road data, trash can point data, and road weight setting; 2) Taking the trash can points in the scenic area as the generating elements, constructing the road network Voronoi diagram of each trash can; 3) Calculating the weighted road length within the power range of each trash can; 4) Calculating the average browsing time of tourists in the scenic area; 5) Calculating the average garbage intensity coefficient of the scenic area according to the historical daily total garbage volume and daily total pedestrian flow data of the scenic area; 6) Calculating the garbage volume value of each trash can on the same day according to the real-time pedestrian flow data.

[0120] in:

[0121] (1) Basic data collection and preprocessing

[0122] The vector format data of road network data and trash can location data in scenic areas are usually readily available and provided by the scenic area management. If the scenic area management cannot provide vector format data, the road data and trash can location data of the scenic area can be manually vectorized based on the scenic area's guide map. This process can be completed in professional GIS software.

[0123] (2) Constructing a Voronoi diagram of the road network

[0124] Using the location data of trash cans in the scenic area as the origin, the network is expanded along the road network of the scenic area until it encounters the boundary of the range of other trash cans, thus obtaining the network Voronoi diagram of a single trash can.

[0125] (3) Calculate the weighted road length within the influence range of the trash can.

[0126] After constructing the Voronoi diagram of the network, the geometric length of each road segment within the Voronoi diagram of each trash can network can be calculated. The geometric length of the road network can be calculated segment by segment based on the coordinate points of the road vector data, or it can be obtained directly from the GIS software.

[0127] Because the number of visitors on roads of different grades varies greatly, the amount of waste generated will also differ significantly. Therefore, different weights need to be assigned to different roads to calculate waste volume. The calculation of road weights is mainly based on visitor flow density, and the calculation method is described in detail below.

[0128] Select a camera on a certain road segment, and select different times t1, t2, t3...t within a day. n The captured images, through actual measurement, show the road length within the image's field of view as l. AI image recognition identifies the number of tourists in each image as p1, p2, p3...p... n The pedestrian density on this section of road is calculated by averaging the number of tourists and then dividing by the road length l.

[0129]

[0130] The pedestrian density of roads of different grades can be calculated using the above method, and the maximum average pedestrian density P can be obtained. max and minimum value P min The road classification is divided into five levels, and a corresponding weight value W is assigned to roads of different levels. i ,Right now:

[0131] W i =0.2;

[0132] W i =0.4;

[0133] W i =0.6;

[0134] W i =0.8;

[0135] W i =1.

[0136] Multiplying the geometric length of a road by its weight yields its weighted length, i.e.:

[0137] V i =ΣL i *W i ;

[0138] After the calculation is complete, the value can be directly saved to the attribute table of the trash can location data, such as... Figure 4 As shown.

[0139] (4) Calculate the average visit time of tourists

[0140] Randomly capture facial images of tourists from multiple scenic area cameras, and then use AI to search the camera footage to obtain the earliest and latest times each tourist appeared in the scenic area. Subtracting these times from the earliest and latest times will give you the total visit time for each tourist. Finally, take the average of the visit times for multiple tourists to calculate the average visit time in the scenic area.

[0141] (5) Calculate the average road litter intensity coefficient in the scenic area

[0142] By summing the weighted total road lengths for each trash can, we can obtain the total weighted road length ∑V for the entire scenic area. i Obtain the total amount of garbage in the scenic area on a specific day from the scenic area management. t and total flow of people P t And, based on the average tour time T calculated in step 4, the average garbage intensity coefficient C of the scenic area is calculated, that is:

[0143]

[0144] The average garbage intensity coefficient C can be understood as the amount of garbage generated by each tourist per unit time on a road with a unit weighted length in the scenic area. For example, the amount of garbage G generated in the scenic area in one day t is 100m 3 , the total number of visitors P t is 10,000 person-times, the total weighted length of the scenic area roads ∑V i is 10 km, and the average visiting time is 1 hour. The calculated average garbage intensity coefficient C is: 0.001 m / person / hour / km, that is, each tourist generates 0.001 cubic meters, which is 1 liter of garbage per hour on each 1-kilometer road.

[0145] If the scenic area management can provide the garbage volume and visitor flow data for multiple days, it can be calculated multiple times and the average value of C can be taken.

[0146] (6) Calculate the garbage volume of the trash can at time t1

[0147] The number of tourists entering the scenic area per unit time can be regarded as a function of time t, denoted as f(t). Then, according to the total weighted length of the roads ∑V of the trash can obtained in step 3 i and the average garbage intensity coefficient C obtained in step 5, assuming the opening time of the scenic area is t0, then the garbage volume of a certain trash can in the scenic area at time t1 can be calculated as:

[0148]

[0149] where G i is the garbage production at the garbage collection point at the prediction time, d min represents the shortest distance from this trash can to the scenic area entrance, V represents the visiting speed of tourists, and d min ≥V*(t1 - t0) means that the tourists have not visited this trash can yet, and the garbage volume at this time is 0; similarly, d min <V*(t1-t0) means that the tourists have visited this trash can, and the garbage volume at this time can be obtained by integrating the function f(t) according to the above formula.

[0150] In specific practice, the function f(t) of the number of tourists entering the scenic area per unit time can be approximately regarded as a piecewise function. For example Figure 3 As shown, the opening time of a certain scenic area is 8:00, and tourists are not allowed to enter after 18:00 in the afternoon. By statistically counting the number of tourists in real time, the piecewise values of the number of tourists f(t) in this scenic area can be obtained. When 8:00 < t ≤ 9:00, the value of f(t) is 231 people / hour.

[0151] Of course, to achieve more accurate predictions, the time for calculating visitor flow statistics can be shortened as much as possible, such as to 1 minute. Scenic spots with the necessary resources can even update visitor numbers every second. Additionally, it's important to ensure that the time unit matches the unit of the average browsing time. For example, if the average browsing time is in hours, then f(t) should be in people / hour.

[0152] It should be noted that steps 1-5 can be performed using professional GIS software and video AI analysis tools, and only need to be built once. The resulting data can be imported into a scenic area management platform, such as OnePark. In step 6, the formula calculates the amount of trash in each bin at a future time based on the actual visitor flow data collected by the scenic area (statistics are collected hourly, minutely, or secondly). The scenic area management platform can easily visualize the calculation results, for example, by displaying the predicted amount of trash in each bin on a map in real time, facilitating timely trash removal by the scenic area management.

[0153] Please refer to Figure 5 , Figure 5 This is a schematic diagram of the waste production prediction device provided in the embodiments of this application, as shown below. Figure 5 As shown, the device may include:

[0154] The acquisition module 51 is used to acquire road vector data of the area to be predicted and collection point location data of garbage collection points located within the area to be predicted;

[0155] Construction module 52 is used to construct a road network Venn diagram of the garbage collection points based on the road vector data and the collection point location data, using the collection point location data as the generation element.

[0156] The first calculation module 53 is used to calculate the total length of roads within the sphere of influence of the garbage collection point based on the road network Venn diagram.

[0157] The second calculation module 54 is used to calculate the average garbage intensity coefficient based on the total length, the daily garbage volume data of the area to be predicted, the daily pedestrian flow, and the average browsing time per person in the area to be predicted.

[0158] The prediction module 55 is used to predict the amount of waste produced by the waste collection point at the predicted time based on the average waste intensity coefficient, the speed at which tourists visit the area to be predicted, the number of tourists entering the area to be predicted at the predicted time, the total length, and the shortest distance between the waste collection point and the entrance of the area to be predicted.

[0159] In one or more embodiments, the first computing module 53 is used for:

[0160] Based on the collected road images within the sphere of influence, the pedestrian density of the road segments in the road images is calculated;

[0161] Based on the pedestrian density, calculate the weight of the road class to which the road segment belongs;

[0162] Based on the weights and the geometric lengths of the graded roads obtained through the Venn diagram of the road network, the weighted lengths of the graded roads are calculated.

[0163] The total length of roads within the sphere of influence is obtained by summing the weighted lengths of all roads of the specified level.

[0164] In one or more embodiments, the first computing module 53 is used for:

[0165] The number of tourists included in the road images within the sphere of influence collected at each collection time is counted; and the total geometric length of the collected roads is obtained by multiplying the geometric length of the road segments included in the road images by the number of collection times.

[0166] Sum the number of tourists to obtain the total number of tourists;

[0167] The population density is obtained by calculating the quotient of the total number of tourists and the total geometric length of the collected roads.

[0168] In one or more embodiments, the second computing module 54 is used for:

[0169] Calculate the product of the total length, the total daily visitor flow, and the average browsing time per person;

[0170] The average waste intensity coefficient is obtained by calculating the quotient of the product of the total daily waste volume and the average daily waste volume.

[0171] In one or more embodiments, prediction module 55:

[0172] If the shortest distance is greater than or equal to the tourist tour distance calculated based on the predicted time, the open tour time of the area to be predicted, and the tour speed, the waste production of the waste collection point is determined to be 0.

[0173] If the shortest distance is less than the tourist tour distance, the product of the average waste intensity coefficient, the total length, and the number of tourists is integrated from the opening time to the predicted time to obtain the waste production of the waste collection point at the predicted time.

[0174] In one or more embodiments, the first computing module 53 is used for:

[0175] Obtain the maximum and minimum pedestrian density for all road sections within the defined area of ​​influence;

[0176] Based on the maximum and minimum values, multiple pedestrian density intervals are obtained, and a weight is assigned to each pedestrian density interval;

[0177] From the plurality of pedestrian density intervals, a target pedestrian density interval including the pedestrian density is determined;

[0178] The weight corresponding to the target pedestrian density range is used as the weight of the road's classification level.

[0179] The waste production prediction device and the waste production prediction method provided in this disclosure are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate or implement.

[0180] This disclosure also provides an electronic device for performing the above-described waste production prediction method. Please refer to... Figure 6 It illustrates a schematic diagram of an electronic device provided by some embodiments of this disclosure. For example... Figure 6 As shown, the electronic device 8 includes: a processor 800, a memory 801, a bus 802, and a communication interface 803. The processor 800, the communication interface 803, and the memory 801 are connected via the bus 802. The memory 801 stores a computer program that can run on the processor 800. When the processor 800 runs the computer program, it executes the waste production prediction method provided in any of the foregoing embodiments of this disclosure.

[0181] The memory 801 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this device network element and at least one other network element is achieved through at least one communication interface 803 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0182] Bus 802 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 801 is used to store programs. After receiving an execution instruction, the processor 800 executes the program. The waste production prediction method disclosed in any of the foregoing embodiments of this disclosure can be applied to the processor 800, or implemented by the processor 800.

[0183] The processor 800 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 800 or by instructions in software form. The processor 800 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 801. Processor 800 reads the information in memory 801 and, in conjunction with its hardware, completes the steps of the above method.

[0184] The electronic device provided in this disclosure and the waste production prediction method provided in this disclosure are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate, or implement.

[0185] This disclosure also provides a computer-readable storage medium corresponding to the waste production prediction method provided in the foregoing embodiments. Please refer to... Figure 7 The computer-readable storage medium shown is an optical disc 30, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it executes the waste production prediction method provided in any of the foregoing embodiments.

[0186] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0187] The computer-readable storage medium provided in the above embodiments of this disclosure and the waste production prediction method provided in the embodiments of this disclosure are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications stored therein.

[0188] It should be noted that:

[0189] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this disclosure may be practiced without these specific details. In some instances, well-known structures and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0190] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of this disclosure, various features of this disclosure are sometimes grouped together in a single embodiment, figure, or description thereof. However, this approach to disclosure should not be construed as reflecting a schematic diagram in which the claimed disclosure requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of this disclosure.

[0191] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of this disclosure and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0192] The above description is merely a preferred embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method of predicting a waste production amount, characterized by, The method comprises the following steps: acquiring road vector data of a to-be-predicted area and collection point location data of garbage collection points located in the to-be-predicted area; taking the collection point location data as a generating element, constructing a road network V-structure of the garbage collection points based on the road vector data and the collection point location data; calculating a total length of roads within a range of influence of the garbage collection points based on the road network V-structure; calculating an average garbage intensity coefficient based on the total length, total daily garbage amount data of the to-be-predicted area, total daily passenger flow amount, and per capita browsing time of the to-be-predicted area; predicting a garbage production amount of the garbage collection points at a prediction time based on the average garbage intensity coefficient, a browsing speed of tourists in the to-be-predicted area, a number of tourists entering the to-be-predicted area at the prediction time, the total length, and a shortest distance from the garbage collection points to an entrance of the to-be-predicted area.

2. The method of claim 1, wherein, The method for calculating a total length of roads within a range of influence of the garbage collection points based on the road network V-structure comprises the following steps: calculating a passenger flow density of a road segment in a road image within the range of influence based on the collected road image; calculating a weight of a grade road to which the road segment belongs based on the passenger flow density; calculating a weighted length of the grade road based on the weight and a geometric length of the grade road obtained through the road network V-structure; summing up the weighted lengths of all the grade roads within the range of influence to obtain the total length of the roads within the range of influence.

3. The method of claim 2, wherein, The method for calculating a passenger flow density of a road segment in a road image within the range of influence based on the collected road image comprises the following steps: counting a number of tourists in the road image within the range of influence collected at each collection time; and calculating a product of a geometric length of the road segment included in the road image and a number of the collection times to obtain a total road geometric length collected; summing up the number of tourists to obtain a total number of tourists; 4. The method of claim 1, wherein, calculating a quotient of the total number of tourists and the total road geometric length collected to obtain the passenger flow density. The method for calculating an average garbage intensity coefficient based on the total length, total daily garbage amount data of the to-be-predicted area, total daily passenger flow amount, and per capita browsing time of the to-be-predicted area comprises the following steps: calculating a product of the total length, the total daily passenger flow amount, and the per capita browsing time; 5. The method of claim 1, wherein, calculating a quotient value of the total daily garbage amount data and the product to obtain the average garbage intensity coefficient. The method for predicting a garbage production amount of the garbage collection points at a prediction time based on the average garbage intensity coefficient, a browsing speed of tourists in the to-be-predicted area, a number of tourists entering the to-be-predicted area at the prediction time, the total length, and a shortest distance from the garbage collection points to an entrance of the to-be-predicted area comprises the following steps: in a case where the shortest distance is greater than or equal to a tourist browsing distance calculated based on the prediction time, an open browsing time of the to-be-predicted area, and the browsing speed, determining that the garbage production amount of the garbage collection points is 0; In a case that the shortest distance is less than the tourist tour distance, a product of the average garbage intensity coefficient, the total length and the number of tourists is integrated from the open tour time to the predicted time to obtain a garbage production amount of the garbage collection point at the predicted time.

6. The method of claim 2, wherein, Based on the crowd density, a weight of a grade road to which the road belongs is calculated, including: Obtaining a maximum value and a minimum value of the crowd density of all road segments in the range of the force; Based on the maximum value and the minimum value, a plurality of crowd density intervals are divided, and a weight is set for each of the crowd density intervals; From the plurality of crowd density intervals, a target crowd density interval including the crowd density is determined; The weight corresponding to the target crowd density interval is taken as the weight of the grade road to which the road belongs.

7. A garbage production amount prediction device characterized by comprising: Including: An acquisition module is configured to acquire road vector data of a to-be-predicted area and collection point location data of a garbage collection point located in the to-be-predicted area; A construction module is configured to take the collection point location data as a generation element, and construct a road network graph of the garbage collection point based on the road vector data and the collection point location data; A first calculation module is configured to calculate a total length of roads within a range of the garbage collection point based on the road network graph; A second calculation module is configured to calculate an average garbage intensity coefficient based on the total length, single-day garbage total amount data of the to-be-predicted area, single-day crowd total amount and per capita browsing time of the to-be-predicted area; A prediction module is configured to predict a garbage production amount of the garbage collection point at a predicted time based on the average garbage intensity coefficient, a tour speed of tourists to the to-be-predicted area, a number of tourists entering the to-be-predicted area at the predicted time, the total length and a shortest distance from the garbage collection point to an entrance of the to-be-predicted area.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program, when executed by the processor, is arranged to perform the method of any one of claims 1 to 7. The processor executes the computer program to implement the steps of the method of any one of claims 1-6.

9. A computer readable storage medium having stored thereon computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the steps of the method of any one of claims 1-6.

10. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the steps of the method of any one of claims 1-6.

Images