JP2023023039A - Demand estimation system for article derived from waste - Google Patents

Abstract

To estimate the demand for an article derived from waste by automatically analyzing the waste.SOLUTION: An article demand estimation system comprises: a waste containing unit 7 that is for storing waste and has a container body that includes at least a bottom face 71 and a side face 72 erected from the bottom face 71, and imaging means that picks up an image of the inside of the container body; and an estimation device 2 that has information acquisition means that acquires the image of the waste stored in the container body picked up by the imaging means, and estimation means that uses three or more stages of degrees of relation between image information for reference related to the image of the waste and identification information on an article derived from the waste, and estimates the article derived from the waste based on the image information for reference according to image information acquired in an information acquisition step.SELECTED DRAWING: Figure 2

Description

The present invention relates to a demand estimation system for waste-derived goods.

Waste is deposited into a waste receptacle, commonly referred to as a trash can. These waste receptacles are installed everywhere, such as stations and convenience stores. Especially in stations, waste receptacles are often installed in close proximity to vending machines. As a result, a customer who has finished drinking beverages sealed in PET bottles or cans at the vending machine can put empty PET bottles, cans, etc. into the waste receptacle as they are.

By the way, a POS system installed in a convenience store or an automatic vending machine can extract the demand from the sales of each product. However, when the waste receptacle is not close to the sales floor, it is necessary to estimate the demand for goods at the sales floor from the type of waste stored in the waste receptacle. The current situation is that no technology has been devised to automatically estimate the

Accordingly, the present invention has been devised in view of the above-mentioned problems, and its object is to estimate the demand for goods derived from the waste by automatically analyzing the waste. To provide a demand estimation system for goods derived from possible waste.

A waste receptacle according to the present invention is a waste receptacle for containing waste, a container body including at least a bottom surface and side surfaces rising from the bottom surface, an imaging means for imaging the inside of the container body, 3: information acquisition means for acquiring image information of the waste contained in the container main body imaged by the imaging means; reference image information relating to the image of the waste; and identification information of the article derived from the waste. Estimation means for estimating articles derived from waste based on reference image information corresponding to the image information acquired in the information acquisition step using a degree of association of a level or higher, and an article estimated by the estimation means and transmitting means for transmitting information.

Even without special skills or experience, anyone can easily estimate the demand for goods derived from waste.

1 is a block diagram showing the overall configuration of a system to which the present invention is applied; FIG. It is a figure which shows the specific structural example of a search apparatus. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention.

A demand estimation system to which the present invention is applied will be described in detail below with reference to the drawings.

FIG. 1 is a block diagram showing the overall configuration of a demand estimation system 1 to which the present invention is applied. The identification information estimation system 1 includes an information acquisition section 9 , an estimation device 2 connected to the information acquisition section 9 , a database 3 connected to the estimation device 2 , and a waste container 7 .

The waste receptacle 7 is a so-called trash can, and stores waste (for example, PET bottles, bottles, cans, newspapers, burnable garbage, non-burnable garbage, recyclable garbage, etc.). Waste is usually thrown into the waste receptacle 7. For example, the waste receptacle 7 for PET bottles, bottles, and cans has a round hole corresponding to the diameter of the PET bottle, bottle, or the like. It is open and the waste is discharged through the round hole.

The information acquisition unit 9 is a device for a person using this system to input various commands and information. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an imaging device capable of capturing an image, such as a camera. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper document. Further, the information acquisition unit 9 may be integrated with the estimation device 2 to be described later. The information acquisition unit 9 outputs the detected information to the estimation device 2 . Further, the information acquisition unit 9 may be configured by means for specifying position information by scanning map information. Further, the information acquisition unit 9 may be configured with an illuminance sensor for measuring a temperature sensor, a humidity sensor, and a wind direction sensor. The information acquisition unit 9 may also be configured with a communication interface that acquires weather data from the Meteorological Agency or a private weather forecast company. The information acquisition unit 9 may be composed of a body sensor worn on the body to detect body data, and the body sensor detects, for example, body temperature, heart rate, blood pressure, number of steps, walking speed, and acceleration. It may be configured with a sensor for The information acquisition unit 9 may be configured as a device that acquires information such as drawings by scanning or reading from a database. The information acquisition unit 9 may be configured by an odor sensor that detects odors and scents in addition to these.

The information acquisition unit 9 is attached to the waste receptacle 7 and is capable of imaging the waste in the waste receptacle.

FIG. 2 shows a configuration example of the waste container 7 . The waste receptacle 7 has a container body consisting of a bottom surface 71, a side surface 72 rising from the bottom surface 71, a top plate 73 provided above the side surface 72, and a waste inlet 74 provided in the top plate 73. It has Incidentally, the configuration of the top plate 73 and the waste inlet 74 may be omitted. The waste material input port 74 is an opening for inputting cans, bottles, and PET bottles, for example. The diameter of the waste inlet 74 corresponds to the diameter of cans, bottles, and PET bottles.

When the information acquisition unit 9 is composed of a camera, for example, like the information acquisition unit 9a, it is provided at a position where the waste thrown into the waste material inlet 74 can be photographed. It may be configured such that image information can be acquired by capturing an image of the waste each time. Further, like the information acquisition unit 9b, it may be provided at a position where the inside of the container body can be imaged, and configured to be able to image the waste thrown into the waste container 7 and acquire the image information.

The waste receptacle 7 may include a communication unit (not shown) for wireless or wired communication of the estimation result to the outside. In such a case, it is also possible to immediately transmit the estimation result to an external system wirelessly.

The database 3 accumulates various information necessary for estimating identification information. The information necessary for estimating identification information includes information such as reference image information of the appearance of waste in the past, and identification information of items derived from waste for which judgments have actually been made. dataset is stored.

The estimating device 2 is composed of an electronic device such as a personal computer (PC), for example, but in addition to the PC, it is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc. It may be one that is made into. A user can obtain a search solution by this estimation device 2 .

FIG. 3 shows a specific configuration example of the estimation device 2. As shown in FIG. The estimating device 2 performs wired or wireless communication with a control unit 24 for controlling the entire estimating device 2 and an operating unit 25 for inputting various control commands via operation buttons, a keyboard, or the like. A communication unit 26 for searching, an estimating unit 27 for making various judgments, and a storage unit 28, represented by a hard disk, for storing a program for performing a search to be executed are connected to the internal bus 21, respectively. . Further, the internal bus 21 is connected with a display unit 23 as a monitor for actually displaying information.

The control unit 24 is a so-called central control unit for controlling each component implemented in the estimating device 2 by transmitting control signals via the internal bus 21 . In addition, the control unit 24 transmits commands for various controls through the internal bus 21 according to operations through the operation unit 25 .

The operation unit 25 is embodied by a keyboard or a touch panel, and a user inputs an execution command for executing a program. The operation unit 25 notifies the control unit 24 when the execution command is input by the user. Upon receiving this notification, the control unit 24 cooperates with each component including the estimation unit 27 to execute desired processing operations. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The estimation unit 27 estimates a search solution. The estimation unit 27 reads various information stored in the storage unit 28 and various information stored in the database 3 as necessary information in executing the estimation operation. This estimation unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

The display unit 23 is composed of a graphic controller that creates a display image based on control by the control unit 24 . The display unit 23 is implemented by, for example, a liquid crystal display (LCD).

When the storage unit 28 is configured with a hard disk, predetermined information is written to each address based on the control by the control unit 24, and this information is read as necessary. The storage unit 28 also stores a program for executing the present invention. This program is read and executed by the control unit 24 .

By the way, the present invention is not limited to the case where the search device 2 performs various determinations, controls, proposals, and estimations based on the data set recorded in the database 3, and is, for example, a terminal device of the system. It may be composed of artificial intelligence installed in an edge device.

In such a case, for example, an edge device provided in the waste container 7 may perform the estimation process.

The operation of the identification information estimation system 1 configured as described above will be described.

The identification information estimating system 1 estimates the demand for goods at the sales floor from the type of waste stored in the waste container 7 when the waste container 7 and the sales floor are not close to each other. However, the identification information estimating system 1 can be used even when the waste receptacle 7 and the sales floor are close to each other, such as when the waste receptacle 7 is installed next to the vending machine. Of course, it may be a person who estimates the demand for goods.

The identification information estimation system 1 is based on the assumption that, for example, as shown in FIG. 4, three or more degrees of association between reference image information and article identification information are set in advance. The reference image information is obtained from image information obtained by imaging the waste, and can be obtained by analyzing the image information. This image may be a moving image as well as a still image. Also, although this image is composed of visible light, it may be composed of a so-called spectrum image in which the display color is switched according to the spectrum instead of the image. This reference image information may specify the appearance of the waste based on any of the size, shape, and color of the waste by analyzing the captured image of the waste. Further, this reference image information may be composed of an ultrasonic image of the waste material. The appearance of these wastes may be determined based on previously learned features. At this time, using artificial intelligence, image data such as the size, shape, and color of the waste and the type of waste (for example, PET bottles, bottles, cans, newspapers, burnable garbage, non-burnable garbage, recyclable garbage, etc.) are collected. ) and the content of the waste itself (for example, the product name of the beverage in the case of PET bottles, the product name of the confectionery in the case of confectionery containers, etc.). When the reference image information is actually acquired, the waste may be determined by comparing it with the learned image data.

In such a case, a predictive model machine-learned using image information and the appearance of waste in terms of size, shape, or color as teacher data is used, and the input is the image information and the output is the appearance. Appearance may be specified based on the result of the determination.

A data set consisting of such reference image information and identification information of articles derived from waste is obtained and learned. The articles derived from the waste mentioned here are the articles before becoming the waste. Goods are consumed by customers and generated as waste. By identifying what the goods are before they are turned into waste, the demand for the goods can be identified.

In the example of FIG. 4, it is assumed that the input data are reference image information P01 to P03, for example. The reference image information P01 to P03 as such input data are linked to the identification information of articles derived from waste as output. In this output, identification information of articles derived from waste is displayed as an output solution.

The reference image information is associated with the identification information A to D of the article derived from the waste as the output solution through three or more degrees of association. For example, the identification information A may be composed of a rough type such as a PET bottle, the identification information B an empty can, etc. More specifically, the identification information C may be a PET bottle product 〇〇, The identification information D may be down to a specific product level, such as PET bottle product ▽▼. The image information for reference is arranged on the left side through the degree of association, and the identification information of the article derived from each waste is arranged on the right side through the degree of association. The degree of relevance indicates the degree to which the reference image information arranged on the left has a high degree of relevance with the identification information of the article derived from which waste. In other words, the degree of association is an index indicating whether each piece of reference image information is likely to be associated with the identification information of an article derived from what kind of waste. It indicates the accuracy in selecting the identification information of the product derived from the product. In the example of FIG. 4, w13 to w19 are shown as association degrees. These w13 to w19 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the more each combination as an intermediate node is related to the identification information of the article derived from the waste as output. Conversely, the closer to 1 point, the lower the degree of correlation between each combination as an intermediate node and the price as an output.

The estimating device 2 acquires in advance the degrees of association w13 to w19 of three or more stages shown in FIG. In other words, the estimating device 2 accumulates a past data set to determine which of the reference image information and the identification information of the article derived from the waste in that case was adopted and evaluated in determining the actual search solution. By analyzing these, the degree of association shown in FIG. 4 is created.

For example, it is assumed that the reference image information is α. It is assumed that the identification information A of the article derived from the waste is highly evaluated as the identification information of the article derived from the waste for such reference image information. By collecting and analyzing such data sets, the degree of association with the reference image information is strengthened.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of reference image information P01, analysis is performed from various data as a result of evaluation of identification information of articles derived from past waste. In the case of the reference image information P01, if there are many cases of the identification information A of the article derived from the waste, the degree of association leading to the evaluation of the identification information of the article derived from the waste is set higher. When there are many cases of identification information B of articles derived from waste, the degree of association leading to evaluation of the identification information of articles derived from this waste is set higher. For example, in the example of the reference image information P01, the identification information A of the article derived from the waste and the identification information C of the article derived from the waste are linked. The degree of relevance of w13 connected to the identification information A is set to 7 points, and the degree of relevance of w14 connected to the identification information C of the article derived from the waste is set to 2 points.

In addition, as shown in FIG. 5, this degree of association may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data through a data set of images of the appearance of the waste to be evaluated in the past and the identification information of items derived from the actually estimated and evaluated waste, In determining the identification information of the articles derived from the waste, the above-described learned data is used to search for the identification information of the articles derived from the waste. In such a case, new image information is actually acquired in the region to be determined. Image information to be newly acquired is input by the information acquisition unit 9 described above. Image information is obtained by imaging the waste whose identification information is to be determined. This determination method may be performed by the same method as for the reference image information described above.

Based on the image information newly acquired in this way, the identification information of the article derived from the waste is determined. In such a case, reference is made to the degrees of association shown in FIG. 4 (Table 1) that have been acquired in advance. For example, when the newly acquired image information is the same as or similar to P02, the identification information B of the article derived from the waste through the degree of association is w15, and the identification of the article derived from the waste Information C is associated with a degree of association w16. In such a case, the identification information B of the article derived from the waste with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the identification information C of the article derived from the waste whose degree of association is low but whose association itself is recognized is selected as the optimum solution. good too. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

In this way, from the newly acquired image information, the identification information of the most suitable waste-derived article can be searched, displayed and transmitted. By looking at this search result, the management side can estimate the demand for waste-derived goods based on the identification information of the searched waste-derived goods. Moreover, since the identification information can be predicted through imaging without touching the waste, the hands will not get dirty by touching the waste.

In order to estimate the demand for each item from the identification information of the searched items, for example, the number and frequency of identified items are obtained for each item, or the ratio of the number of identified items and frequency among items is obtained and obtained. You may make it connect a result and a demand. The obtained result and the demand may be linked based on a pre-created template in which the number, frequency, and ratio of identified articles are linked to the demand.

In particular, like the information acquisition unit 9a, it is provided at a position where the waste thrown into the waste inlet 74 can be photographed, and the waste thrown into the waste inlet 74 is imaged each time, thereby obtaining reference image information, Obtaining the image information makes it possible to search for identification information from images that focus on the input waste itself. In addition, like the information acquisition unit 9b, it is provided at a position where the inside of the container body can be imaged, and by capturing an image of the waste thrown into the waste container 7, image information for reference and image information can be obtained. , it becomes possible to search for the identification information of the item from the plurality of wastes in the container.

In FIG. 4, as an alternative to the reference image information, three or more degrees of association between the reference sensing information and the identification information of the article derived from the waste may be learned in advance. The reference sensing information is information obtained from known sensors that detect objects. For example, sensing information can be obtained by providing a sensor at a position capable of sensing the waste thrown into the waste inlet 74 and sensing the waste thrown into the waste inlet 74 each time. For example, by arranging and setting the sensors, it is possible to create a state in which the sensor responds or does not respond according to the size of the waste, so it is possible to identify the size of the waste itself through the sensor. becomes.

The reference sensing information obtained in this way and the identification information of the article described above are mutually learned through three or more stages of association, and when searching for a solution, by inputting the sensing information, a search solution can be obtained. , it is possible to similarly search for the identification information of the article.

In the example of FIG. 6, it is assumed that a combination of the reference image information and the reference audio information when the waste is contained in the container body is formed. The reference voice information is composed of data obtained by recording the voice when the waste is placed in the container body, and performing frequency analysis as necessary. The time of accommodation may be the stage when the waste is thrown in, but is not limited to this, and the voice may be recorded in the state of being accommodated later.

The identification information of the articles derived from the waste is the reference image information, and the sound when thrown is different depending on the bottle or can. Therefore, this reference voice information is also added as an explanatory variable.

In the example of FIG. 6, the input data are, for example, reference image information P01 to P03 and reference audio information P14 to P17. The intermediate node shown in FIG. 6 is a combination of the reference image information as input data and the reference audio information. Each intermediate node is also connected to an output. In this output, identification information of articles derived from waste is displayed as an output solution.

Each combination (intermediate node) of the reference image information and the reference audio information is associated with the identification information of the article derived from the waste as the output solution through three or more levels of association. . The image information for reference and the audio information for reference are arranged on the left side through this degree of association, and the identification information of articles derived from waste is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference image information and the reference audio information arranged on the left side are highly relevant to the identification information of the article derived from the waste. In other words, the degree of association is an index indicating whether each reference image information and reference audio information is highly likely to be associated with identification information of an article derived from waste. It indicates the accuracy in selecting the identification information of the article most likely derived from the waste from the reference audio information. Therefore, by combining the reference image information and the reference audio information, the identification information of the article derived from the optimum waste is searched.

In the example of FIG. 6, w13 to w22 are shown as association degrees. These w13 to w22 are shown in 10 stages as shown in Table 1. The closer to 10 points, the higher the degree of correlation between each combination as an intermediate node and the output. The closer it is, the lower the degree of correlation between each combination as an intermediate node and the output.

The estimating device 2 acquires in advance the degrees of association w13 to w22 of three or more stages shown in FIG. In other words, the estimating device 2 determines which of the reference image information, the reference audio information, and the identification information of the article derived from the waste in that case is suitable for determining the actual search solution. By accumulating data and analyzing the data, the degree of association shown in FIG. 6 is created.

For example, it is assumed that reference image information in an actual case in the past is α. It is also assumed that the reference audio information is audio that has a peak in a certain frequency band. In such a case, the identification information of the article derived from the waste, which indicates the actual amount of the identification information of the article derived from the waste, is learned as a data set and defined in the form of the degree of association described above.

This analysis may be performed by artificial intelligence. In such a case, for example, when the reference image information P01 is the reference audio information P16, the identification information of the article derived from the waste is analyzed from the past data. If there are many cases where the identification information of goods derived from waste is A, the degree of association leading to this identification information A is set higher, and there are many cases of identification information B of goods derived from waste. If there are few cases of the identification information A of the article derived from the waste, the degree of association leading to the identification information B of the article derived from the waste is increased, and the degree of association leading to the identification information A of the article derived from the waste is lowered. set. For example, in the example of the intermediate node 61a, it is linked to the output of the identification information A and the identification information B of the item derived from the waste, but from the previous case, the association of w13 leading to the identification information A of the item derived from the waste 7 points, and the association degree of w14 connected to the identification information B of the article derived from the waste is set to 2 points.

Further, the degree of association shown in FIG. 6 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

In the example of the degree of association shown in FIG. 6, the node 61b is a node of a combination of the audio information for reference P14 with respect to the image information for reference P01. , the association degree of the identification information E of the article derived from the waste is w16. The node 61c is a node of a combination of the reference position information P15 and P17 with respect to the reference image information P02. The association degree of the identification information D is w18.

Such a degree of association becomes learned data in terms of artificial intelligence. After such learned data is created, the above-described learned data is used when discriminating the identification information of articles that are actually derived from this as waste. In such a case, image information and audio information are actually acquired. As for the voice information, the voice when the waste whose identification information is to be estimated is actually collected is acquired.

Based on the image information and audio information newly acquired in this way, the identification information of the article derived from the optimum waste is searched. In such a case, reference is made to the degrees of association shown in FIG. 6 (Table 1) that have been acquired in advance. For example, when the newly acquired image information is the same as or similar to P02 and the audio information is P17, the node 61d is associated via the degree of association, and this node In 61d, the identification information C of the article derived from the waste is associated with w19, and the identification information D of the article derived from the waste is associated with the association degree w20. In such a case, the identification information C of the article derived from the waste with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the identification information D of the article derived from the waste whose degree of association is low but whose association itself is recognized is selected as the optimum solution. good too. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

Table 2 below shows examples of degrees of association w1 to w12 extending from the input.

Intermediate nodes 61 may be selected based on degrees of association w1 to w12 extending from this input. In other words, the greater the degree of association w1 to w12, the heavier the weight in selecting the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weighting in selecting the intermediate nodes 61 may all be the same.

FIG. 7 shows a combination of the reference image information described above and the reference weight information related to the weight of the waste in the container main body instead of the reference audio information described above, and the number of items derived from the waste for the combination. An example is shown in which three or more levels of association with identification information are set.

The reference weight information relates to the weight of the waste, and may be composed of weight data measured by a weighing scale (not shown) provided at the bottom of the bottom surface 71 . It is already known that the weight of the waste is related to the identity of the items derived from the waste. For this reason, by combining this reference weight information to form a degree of association, the purpose is to improve the judgment accuracy of the identification information of the article derived from the waste.

In the example of FIG. 7, it is assumed that the input data are reference image information P01-P03 and reference weight information P18-21. An intermediate node shown in FIG. 7 is a combination of reference image information as such input data and reference weight information. Each intermediate node is also connected to an output. In this output, identification information of articles derived from waste is displayed as an output solution.

Each combination (intermediate node) of the reference image information and the reference weight information is associated with the identification information of the article derived from the waste as the output solution through three or more levels of association. . The image information for reference and the weight information for reference are arranged on the left side through this degree of association, and the identification information of articles derived from waste is arranged on the right side through the degree of association. The degree of relevance indicates the degree to which the reference image information and the reference weight information arranged on the left side are highly related to the identification information of the article derived from the waste. In other words, the degree of association is an index indicating whether each piece of reference image information and reference weight information is highly likely to be associated with identification information of an article derived from waste. and reference weight information to indicate the accuracy of selecting the most probable waste-derived article identification information.

The estimating device 2 acquires in advance the degrees of association w13 to w22 of three or more stages shown in FIG. That is, in determining the actual search solution, the estimation device 2 uses the reference image information, the reference weight information of the waste imaged when the reference image information is acquired, and the waste in that case. By accumulating past data as to which identification information of the article to be used was suitable, and analyzing the data, the degree of association shown in FIG. 7 is created.

This analysis may be performed by artificial intelligence. In such a case, for example, when the reference image information P01 is the reference weight information P20, the identification information of the article derived from the waste is analyzed from the past data. If there are many cases of identification information A of items derived from waste, set a higher degree of association that leads to identification information A of items derived from waste, and If there are many cases of B, and there are few cases where the identification information of the waste-derived goods is A, the degree of association that the identification information of the waste-derived goods leads to B is increased, and the waste-derived goods The degree of association in which the identification information of is connected to A is set low. For example, in the example of the intermediate node 61a, it is linked to the output of the identification information A of the waste-derived item and the identification information B of the waste-derived item. The degree of relevance of w13 connected to information A is set to 7 points, and the degree of relevance of w14 connected to identification information B of articles derived from waste is set to 2 points.

Also, the degree of association shown in FIG. 7 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

In the example of the degree of association shown in FIG. 7, the node 61b is a node of the combination of the reference image information P01 and the reference weight information P18, and the association degree of the identification information C of the article derived from the waste is w15, The association degree of the identification information E of the article derived from the waste is w16. A node 61c is a node of a combination of reference weight information P19 and P21 for reference image information P02. The association degree of the identification information D is w18.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data is used when actually searching for identification information of articles derived from waste. In such a case, the image information of the identification information of the article actually derived from the waste and the weight information are obtained. Here, the weight information is newly acquired when actually estimating the identification information of the article derived from the waste, but the acquisition method is the same as the reference weight information described above.

Based on the newly acquired image information and weight information in this way, the identification information of the article derived from the optimum waste is searched. In such a case, reference is made to the degrees of association shown in FIG. 7 (Table 1) that have been acquired in advance. For example, when the newly acquired image information is the same as or similar to P02 and the weight information is the same or similar to P21, the node 61d is associated via the degree of association. This node 61d is associated with the identification information C of the article derived from the waste at w19 and the identification information D of the article derived from the waste with the association degree w20. In such a case, the identification information C of the article derived from the waste with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the identification information D of the article derived from the waste whose degree of association is low but whose association itself is recognized is selected as the optimum solution. good too. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

As the reference information, reference time information may be applied. The reference time information is information about the time corresponding to the acquisition point of the reference image information. Three or more degrees of association between combinations having this reference time information and reference image information and the identification information of articles derived from waste are obtained in advance as learning data. During the search for a solution, time information relating to the time corresponding to the time when the waste to be estimated is imaged is acquired. Then, the solution search is performed while referring to the degree of association via the reference time information corresponding to this time information, as described above.

As the reference information, reference position information may be applied. The reference position information is information about the installation position of the waste container 7 . The reference positional information may consist of the address or address data where the waste receptacle 7 is actually installed, but is not limited to this. The installation position of the container 7 may be indicated. At this time, information on surrounding buildings, facilities, etc. may also be included in this reference position information. For example, if the waste receptacle 7 is installed in a building, condominium, hotel, station, ship, or the like, this reference position information may be composed of information that can identify these structures or ships. The waste receptacle 7 may be composed of rough positional information on the prefectural level, or may be composed of medium-sized positional information on the municipality level. Also, the position information may be composed of coordinate information indicated by GPS or the like.

Three or more degrees of association between a combination having the reference position information and the reference image information and the identification information of the article derived from the waste are acquired in advance as learning data. During the solution search, positional information regarding the installation position of the waste receptacle 7 in which the waste to be estimated is discarded is acquired. Then, it is the same as described above in that the solution search is performed while referring to the degree of association described above via the reference position information corresponding to this position information.

As the reference information, reference weather information may be applied. Reference weather information is information related to reference weather information at the time of acquisition of reference image information, including temperature, humidity, weather (sunny, cloudy, rain), movement of typhoons, wind direction, rainfall, etc. Contains data. The reference weather information may be obtained from data provided by the Japan Meteorological Agency or private weather forecasting companies. We added this as an explanatory variable because the type of beverage consumed, and thus the type of waste derived from it, differs depending on the weather, for example on hot and cold days. Three or more degrees of association between a combination of the reference weather information and the reference image information and the identification information of the article derived from the waste are acquired in advance as learning data. Then, during the search for a solution, weather information corresponding to the time when the waste to be estimated is imaged is acquired. Then, the reference weather information corresponding to this weather information is used to search for solutions while referring to the degree of association as described above.

As reference information, reference attribute information may be applied. The attribute information for reference is the consumer's age, sex, occupation, student, and student type determined from appearance. In actually creating learning data, consumers are photographed with a camera, and their features are extracted by analyzing the images. This feature extraction is obtained by image analysis of the image data as required. If necessary, deep learning technology may be used to automatically discriminate the consumer's age, gender, occupation, student, and student type based on the feature values of the analyzed image, and convert the information into data.

Three or more degrees of association between combinations having this reference attribute information and reference image information and the identification information of articles derived from waste are acquired in advance as learning data. Then, when searching for a solution, an image of the consumer who intends to dispose of the waste is captured, and the image is analyzed in the same manner as described above to extract the characteristics of the consumer. This feature extraction is obtained by image analysis of the image data as required. Using deep learning technology as necessary, attribute information is acquired by automatically distinguishing the consumer's age, gender, occupation, student, and student type based on the feature values of the analyzed image. The attribute information corresponds to the reference attribute information described above, and the acquisition method is also the same. Then, after referring to the association degree, the identification information is determined based on the newly acquired image information and attribute information.

It should be noted that face authentication of the consumer may be performed when acquiring the reference attribute information. This facial recognition can be used to identify the consumer, and to report if the consumer is disposed of in violation of the waste disposal rules.

Further, in the present invention, reference traffic information may be applied as the reference information. The reference traffic volume information referred to here is information relating to the traffic volume around the waste container 7 at the time when the reference image information was obtained. The term "surroundings of the waste container 7" as used herein may refer to the amount of traffic on the sidewalk or passage on which the waste container 7 is installed. The traffic volume is basically the traffic volume of people per unit time, but is not limited to this, and may be the traffic volume of vehicles. This reference traffic volume information may be manually counted traffic volume per unit time, but is not limited to this. You may make it Incidentally, this reference traffic information is not limited to the data at the time when the reference image information was obtained, and may be data used when learning data is actually created in relation to the degree of demand and identification information.

In such a case, three or more degrees of association between a combination of reference image information and reference traffic information and identification information are acquired in advance. At the time of actual determination, traffic information at the time of image information acquisition is acquired. This traffic amount information corresponds to the reference traffic amount information described above, and the acquisition method is also the same. Then, after referring to the association degree, the identification information is similarly determined based on the newly acquired image information and the traffic information.

Further, the present invention is not limited to the above-described embodiment. For example, as shown in FIG. good too. In such a case, the solution search is performed based on three or more degrees of association between the reference information and the identification information according to the newly acquired information. All of the reference information described above can be applied to the basic reference information.

In these cases, similarly, when information corresponding to reference information used as learning data is input, solution search is performed based on the above-described method.

The search solution obtained through the degree of association may be further modified or weighted based on other reference information.

The other reference information referred to here corresponds to any reference information other than the basic reference information when any of the reference information described above is used as the basic reference information.

For example, it is assumed that in some reference information F, which is one of the other reference information, the identification information B has been discriminated many times in the past. It is set in advance so that when information corresponding to such reference information F is newly acquired, processing for increasing weighting is performed on identification information B, in other words, processing for connecting to identification information B is performed. Keep

For example, the other reference information G is an analysis result that suggests a search solution C as identification information, and the reference information F is an analysis result that suggests a search solution D as identification information. Assume that there is After the setting with the reference information in this way, when the actually acquired information is the same as or similar to the reference information G, the process of increasing the weight of the identification information C is performed. On the other hand, when the actually acquired information is the same as or similar to the reference information F, the weighting of the identification information D is increased. In other words, the degree of association itself leading to the identification information may be controlled based on the reference information FH. Alternatively, after determining the identification information based only on the degree of association described above, the obtained search solution may be modified based on the reference information FH. In the latter case, how and with what weight the identification information as the search solution is modified based on the reference information FH is to reflect what is designed on the system side each time.

The reference information is not limited to any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the discrimination type as a search solution obtained through the degree of association may be corrected to a higher value for a case that leads to the degree of demand suggested by the reference information.

Similarly, as shown in FIG. 9, even in the case of forming the degree of association with identification information for a combination of reference information that is the keynote and other reference information, the reference information that is the keynote is Any reference information mentioned above is applicable. Other reference information includes any reference information other than the underlying reference information.

At this time, if the basic reference information is the reference weight information, the other reference information includes any other reference information.

In such a case as well, identification information can be estimated by searching for solutions in the same way. At this time, as shown in FIG. 8 described above, the search solution obtained through the degree of association is corrected through further reference information (reference information F, G, H, etc.) to correct the identification information. can be

Further, as shown in FIG. 10, the degree of association may be formed between only the reference information that is the keynote and the identification information. Any of the reference information described above can be applied to this underlying reference information. Description of the solution search method of FIG. 10 is omitted below by citing the description of FIGS.

It should be noted that the present invention is not limited to the above-described embodiments. As a search solution, instead of the article identification information, the storage saturation of the container body in the waste container 7 may be estimated. As a result of the accumulation of waste in the waste receptacle 7, it is no longer possible to dispose of waste once it becomes saturated. In such a case, it is necessary to empty the waste receptacle 7 so that new waste can be disposed of. The accommodation saturation is the degree of accumulation and saturation of waste in the container body of the waste container 7 . This capacity saturation may be quantified through volume or weight. When quantified through volume, the volume fill factor of the waste in the container body may be expressed as a percentage. This volume filling rate may be determined by human eyes, or may be obtained by measuring the actual height of the waste with a tape measure.

By learning the accommodation saturation obtained in this way together with each reference information described above, the degree of association shown in FIGS. 11 and 12 is formed. Then, when searching for a solution, the accommodation saturation can be estimated by referring to the degree of association in the same manner as described above.

When the accommodation saturation is estimated, the estimation result may be notified to an external system via wireless communication and transmitted.

When estimating the accommodation saturation degree, when acquiring sensing information, a sensor is installed in the container body and is set so as to be able to sense already-thrown-in waste. At this time, by installing sensors over a plurality of locations in the height direction, it is possible to sense the situation in which the waste is accumulated and the height is piled up one by one.

Further, according to the present invention, the appropriateness of disposal of waste may be determined based on the identification information of the article. Originally, there are cases where non-burnable garbage, bottles, cans, and the like are discarded in the waste container 7, which is capable of discarding only burnable garbage. In such a case, by obtaining the content of the waste through the identification information, it is possible to issue a warning when waste that should not be disposed of is actually disposed of, or to notify the external system of that fact. .

1 identification information estimation system 2 estimation device 21 internal bus 23 display unit 24 control unit 25 operation unit 26 communication unit 27 estimation unit 28 storage unit 61 node

Claims (11)

For a waste container for containing waste,
a container body including at least a bottom surface and side surfaces rising from the bottom surface;
imaging means for imaging the inside of the container body;
an information acquiring means for acquiring image information of the waste contained in the container main body imaged by the imaging means;
Based on the reference image information corresponding to the image information acquired in the information acquisition step, using three or more degrees of association between the reference image information related to the image of the waste and the identification information of the article derived from the waste , an estimating means for estimating waste-derived items;
and transmission means for transmitting information about the article estimated by the estimation means. For a waste container for containing waste,
a container body including at least a bottom surface, a side surface rising from the bottom surface, a top plate provided on the top of the side surface, and a waste inlet provided on the top plate;
an information acquisition means provided at a position capable of sensing the waste thrown into the waste inlet and acquiring sensing information by sensing the waste thrown into the waste inlet each time;
Based on the reference sensing information according to the sensing information acquired in the information acquisition step, using three or more levels of association between the reference sensing information obtained by sensing the waste and the identification information of the article derived from the waste , an estimating means for estimating waste-derived items;
and transmission means for transmitting information about the article estimated by the estimation means. A waste receptacle for containing waste, which has a container body including at least a bottom surface and a side surface rising from the bottom surface, and imaging means for imaging the inside of the container body;
Three stages: information acquisition means for acquiring the image of the waste contained in the container body imaged by the imaging means; reference image information relating to the image of the waste; and identification information of the article derived from the waste. and an estimating device for estimating articles derived from waste based on the reference image information corresponding to the image information acquired in the information acquisition step using the above degree of association. A system for estimating the demand for goods derived from waste products. The container body includes a top plate provided on the upper part of the side surface and a waste inlet provided on the top plate,
The imaging means is provided at a position where the waste thrown into the waste inlet can be photographed, and acquires the image information by taking an image of the waste thrown into the waste inlet each time. 4. A system for estimating demand for articles derived from waste according to claim 3. The information acquisition means acquires voice information when the waste is accommodated in the container body,
The estimating means has three or more levels of association between a combination having the reference image information and the reference audio information when the waste is contained in the container main body, and the identification information of the article derived from the waste. and further based on the reference audio information corresponding to the audio information acquired in the information acquisition step, to estimate the article derived from the waste according to claim 3. Demand estimation system. The information acquisition means acquires weight information related to the weight of the waste in the container body,
The estimating means uses a combination of the reference image information and the reference weight information related to the weight of the waste in the container body and the identification information of the article derived from the waste at three or more levels of association. and further, based on the reference weight information corresponding to the weight information acquired in the information acquisition step, the demand estimation for the waste-derived goods according to claim 3. system. The information acquisition means acquires time information corresponding to the point in time when the waste is imaged by the imaging means,
The estimating means has three or more levels of association between a combination having the reference image information and the reference time information corresponding to the acquisition point of the reference image information and the identification information of the article derived from the waste. and further based on the reference weight information corresponding to the weight information acquired in the information acquisition step, the article derived from the waste is estimated. Demand estimation system. The information acquisition means acquires position information regarding the installation position of the waste container,
The estimating means includes a combination of the reference image information and the reference position information relating to the installation position of the waste receptacle that acquired the reference image information, and the identification information of the article derived from the waste. 4. The waste according to claim 3, wherein the article derived from the waste is estimated based on the reference position information corresponding to the position information obtained in the information obtaining step, using the degree of association of a level or higher. Demand estimation system for goods derived from. The information acquisition means acquires weather information at the time the image of the waste is captured by the imaging means,
The estimating means uses a combination of the reference image information and the reference weather information at the time of acquisition of the reference image information and the identification information of the article derived from the waste at three or more levels of association. and further, based on the reference weather information corresponding to the weather information acquired in the information acquisition step, the demand estimation for the waste-derived goods according to claim 3. system. The waste derived waste according to any one of claims 3 to 9, wherein the estimation means uses the degree of association corresponding to a weighting coefficient of each output of a neural network node in artificial intelligence. Demand estimation system for goods. a container body including at least a bottom surface, a side surface rising from the bottom surface, a top plate provided on the top of the side surface, and a waste inlet provided on the top plate;
an information acquisition means provided at a position capable of sensing the waste thrown into the waste inlet and acquiring sensing information by sensing the waste thrown into the waste inlet each time; Using three or more levels of association between the sensed reference sensing information and the identification information of the article derived from the waste, based on the reference sensing information corresponding to the sensing information acquired in the information acquisition step, waste and an estimating device having estimating means for estimating goods derived from waste.

Images