Object sorting system, object sorting method, and object sorting program
The object classification system uses machine learning to accurately classify new objects and generate evaluation data, enhancing waste management by determining object types and guiding recycling processes.
Patent Information
- Application Number
- JP2024058037
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2024-03-29
- Publication Date
- 2024-12-09
- Estimated Expiration
- 2044-03-29
AI Technical Summary
Conventional object sorting systems struggle to accurately classify new types of objects due to pre-programmed information limitations, leading to inefficiencies in waste management and recycling processes.
An object classification system utilizing machine learning to learn the correspondence between image data and object type information, enabling high-accuracy classification of new objects, and generating evaluation data based on selling price ranges and identification codes.
Enables efficient management and analysis of waste through statistical information generation, improving waste separation work by determining object types and providing recycling guidance with high accuracy and efficiency.
Smart Images

Figure 0007596052000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an object sorting system that acquires a photograph of waste, determines the type of waste, and generates a recycling score and comments. [Background technology]
[0002] Conventionally, the waste recycling process has been unclear, and with the increase in illegal dumping and waste disposal costs, awareness of carbon neutrality is becoming more and more important. Therefore, a proper waste sorting system is required.
[0003] The waste sorting system and method disclosed in Patent Document 1 are provided with a waste transport means, a photograph acquisition means, a display means, a material information discrimination means, and a system control means. The type of waste can be determined based on the material information contained in the waste.
[0004] The waste history management system disclosed in Patent Document 2 discloses a method for efficiently managing and analyzing waste data, and by managing the waste history, it becomes possible to compare and analyze waste. [Prior art documents] [Patent documents]
[0005] [Patent Document 1] Patent No. 5969685 [Patent Document 2] JP 2023-171971 A Summary of the Invention [Problem to be solved by the invention]
[0006] In the conventional object sorting system, information indicating the type of object was pre-programmed into the program, so when a new type of object appeared, the type could not be recognized. The present invention aims to provide an object sorting system that can sort even new types of objects with high accuracy by learning in advance the correspondence between information indicating the type of object and learning image data through machine learning. [Means for solving the problem]
[0007] One embodiment of the present invention includes a photo acquisition unit that acquires a photo of a captured object, a calculation unit that calculates the degree to which the object contained in the photo indicates a type of waste through a learning model that has previously machine-learned the correspondence between learning image data and information indicating the type of object contained in the learning image data, and an output unit that outputs the degree together with the photo.
[0008] The above object classification system may further include a generation unit that generates degree-based evaluation data through a large-scale language model that has previously trained an input evaluation sentence text. The above-mentioned object sorting system may further include a price search unit that acquires images similar to the photograph as similar images and searches the Internet for the selling price ranges of the similar images, and a conversion unit that converts the amount indicating the selling price range into points. The generating unit may generate an identification code that identifies the identity of the owner of the object and associate the identification code with the photograph of the object.
[0009] This is an object sorting method that executes the following steps: a photo acquisition step in which a computer acquires a photo of the captured object; a calculation step in which a computer calculates the degree to which the object included in the photo indicates a type of waste through a learning model that has previously been machine-learned to learn the correspondence between learning image data and information indicating the type of object contained in the learning image data; and an output step in which a computer outputs the degree together with the photo.
[0010] This is an object sorting program that causes a computer to execute a photo acquisition function that acquires a photo of an imaged object, a calculation function that calculates the degree to which an object included in the photo indicates a type of waste through a learning model that has previously machine-learned the correspondence between learning image data and information indicating the type of object contained in the learning image data, and an output function that outputs the degree together with the photo. Effect of the Invention
[0011] According to one embodiment of the present invention, the object sorting system of the present invention generates an information set including a photograph of the object, the degree to which the photographed object indicates a type of waste, an evaluation based on that degree, a score obtained by searching the selling price range of second-hand goods similar to the object, etc. Therefore, the present invention makes it possible to manage and analyze statistical information on waste through a large language model (LLM) in the waste sorting work. [Brief description of the drawings]
[0012] [Figure 1] 1 is a diagram showing an outline of an object sorting system according to an embodiment of the present invention. [Diagram 2] 1 is a block diagram showing the configuration and functions of an object sorting system according to an embodiment of the present invention. FIG. [Diagram 3] 1 is an example of an object sorting system according to an embodiment of the present invention generating a match rate and comments. [Figure 4] This is an example of an object sorting system according to an embodiment of the present invention searching for the prices of similar items online and converting them into points. [Diagram 5] 1 is an example of a separation result generated by the object separation system according to an embodiment of the present invention. [Figure 6] FIG. 11 is a flowchart illustrating an example of an operation of the object sorting system according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0013] Hereinafter, an embodiment of the object sorting system 10 according to the present invention will be described with reference to the drawings. Note that the present invention is not limited to the embodiment. Also, in each drawing, some components that are not important for the explanation are omitted.
[0014] <Summary> 1, an object sorting system 10 according to the present invention is connected to a user terminal 20 via the Internet NW. The user terminal of this embodiment may be an electronic device such as a personal computer (hereinafter referred to as a PC), but the functions may be realized by any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc., other than a PC.
[0015] According to FIG. 2, the object sorting system 10 may be configured with a photo acquisition unit 101, a calculation unit 102, a generation unit 103, a price search unit 104, a conversion unit 105, and an output unit 106, but is not limited thereto, as long as the function of the object sorting system 10 is realized. The photo acquisition unit 101 of the present invention is configured to acquire a photo of the object. As an example, when there is only one object in the bounding box, the bounding box for acquiring the photo of the object sorting system 10 may surround the object to acquire the photo. When there are multiple objects in the bounding box, each bounding box may surround the object and acquire the object image. In addition, a photo of the object captured by the photo acquisition unit 101 is acquired, and the degree to which the object included in the photo indicates a type of waste is calculated through a learning model that has previously machine-learned the correspondence between the learning image data and the information indicating the type of object included in the learning image data. Then, the product genre is determined using a database that sets the correspondence between the product name and the product genre, and the degree, the product genre, and the photo are output together.
[0016] According to the present invention, it is possible to calculate the degree to which an object included in a photograph indicates a type of waste through a learning model that has previously machine-learned the correspondence between learning image data and information indicating the type of object included in the learning image data. Also, by focusing additional learning on feature amounts that are particularly in need of additional learning, additional learning can be efficiently carried out.
[0017] The photo acquisition unit 101 may include an area division unit that performs processing to extract an object area from the evaluation target image, and a processing feature extraction unit that extracts features from the divided object area. The object classification system 10 can then perform processing to determine a learning model from the learning image data. With the above-described configuration, the photo acquisition unit 101 according to the present invention is characterized not only by high accuracy, but also by high speed and energy saving.
[0018] The calculation unit 102 can calculate a matching rate indicating whether or not the object in the photograph matches a predetermined waste type. As an example, the object sorting system 10 can calculate the degree of similarity with a predetermined type (hereinafter referred to as a matching rate) after recognizing the object in the photograph. The predetermined type may include types as waste (e.g., circular economy, rare metal collection, upcycling, composting, reuse, etc.). Among them, a method for recognizing an object in a photograph may be a publicly known technology. In addition, a matching rate indicating a correspondence between a waste type and an object may be calculated in a learning model. In this case, the learned model may be one that has learned a correspondence between a feature amount generated based on the color of each pixel constituting a certain area in an image and whether or not the target waste is captured in that area. This correspondence is set in advance based on a sales performance database, and it is possible to determine whether the captured photograph is waste.
[0019] Based on the degree calculated by the calculation unit 102, the generation unit 103 can generate information about the recycling of the object (hereinafter referred to as evaluation data), an identification code for identifying the identity of the owner of the object, a QR code (registered trademark), etc. The evaluation data provides recycling guidance information to the user based on the matching rate. As an example, if a certain laptop computer has the highest matching rate with a predetermined type B (e.g., a reused item), the generation unit 103 may generate advice based on the matching rate, such as "This laptop computer can be recycled as a reused item, and the laptop computer screen can be used for other purposes."
[0020] For example, when the generation unit 103 connects to the Internet using a QR code (registered trademark) or the like as an information recording means (for example, when the current information is not directly recorded in the means attached to the QR code (registered trademark)), the generation unit 103 can use a processing device (CPU, etc.) and a storage device such as a publicly known computer, server device, and mobile terminal as the recording and updating means.
[0021] The price search unit 104 can recognize an object included in a photograph by the object sorting system 10 and search for the price of a used item similar to the object. As an example, a certain discarded refrigerator is sold at a plurality of secondhand stores for 1000 yen, 2000 yen, and 3000 yen, and the price search unit 104 may generate a price range by collecting the prices of the secondhand stores. In this case, the price search unit 104 may set the price range to 1000 to 3000, or may calculate the median number, average value, or the like of the price as the search price. In addition to automatically searching for the price, the user may manually input the price of the used item to the price search unit 104 since the actual price of the used item varies depending on the condition of the item and the market situation.
[0022] The price search unit 104 searches for records in which the average value of the feature included in the specified search criteria is equal to or greater than a predetermined value among the image records in the feature table, and stores the results in the search result table of the search result database. In the object sorting system 10 according to this embodiment, color information, shape information, and the like are used as feature values. Also, only the product name, the price excluding tax, the price including tax, and the area of the barcode may be extracted and output from an EC site or the like. Also, like the target image and the non-target image, the reference image does not have to be composed of only one image, and may be a data set composed of multiple images.
[0023] The conversion unit 105 can convert the price into points based on the price range, or the median or average price of the price search unit 104. The conversion result is the same as the price search result, and the price may be converted into points based on the median or average price.
[0024] The output unit 106 can output information such as the object photograph, each identification code, and score to a user terminal. The output may be displayed on a smartphone app or via a medium such as a photograph. In addition, the output recycling evaluation sheet for the object can be identified by each identification code, so that anyone can check it.
[0025] The object sorting system 10 according to this embodiment is equipped with a generation AI including an LLM, and the prompts of the generation AI may be a single process, or may be divided into multiple steps depending on the functions of the object sorting system 10. The prompts in this embodiment are divided into (1) sorting of objects, (2) investigating the used sales price range by searching for similar images, and (3) preventing tampering, but are not limited to these and may include steps such as editing EXIF (Exchangeable image file format) and visualizing the recycling process.
[0026] <Sorting of objects> The object sorting system 10 according to this embodiment can be equipped with a model for image recognition. Specifically, the learning model required for image recognition according to this embodiment is a model that has been machine-learned in advance to determine the correspondence between training image data and information indicating the type of object contained in the training image data, and the type of object contained in a photograph may be identified via the learning model after training.
[0027] In addition, the image identification technology is not limited to these, and an object contained in a photograph may be identified through an image detection model. As an example, the image area of an object extracted from an infrared image taken in the infrared wavelength band is associated with information indicating whether or not the object captured in this image area contains wavelength variations, and the learning data is generated in advance by a so-called supervised machine learning method.
[0028] The object sorting system 10 according to this embodiment can determine whether an object is waste from a photograph and output the result. In addition, the method of acquiring the purpose can be a method of acquiring the purpose by having the camera transmit it, or a method of having the user input it using the input / output unit of a computer, etc.
[0029] The object sorting system 10 according to the present invention calculates the degree to which an object included in a photograph indicates a type of waste through a learning model that has previously learned by machine learning the correspondence between learning image data and information indicating the type of object included in the learning image data. The object sorting system 10 can use a reference image (reference image created by the method of the embodiment) obtained by converting a provisionally captured image, or a reference image (reference image created by the method of the embodiment) obtained by converting a provisional reference image. The user can select either one.
[0030] On the other hand, the object sorting system 10 according to the present embodiment performs machine learning in advance to learn the correspondence between information indicating the type of the identified object and information indicating the type of the predetermined waste, and calculates the degree to which the object included in the photograph indicates the type of waste. The method of analyzing the type of the object is not limited, and information indicating the characteristics of the object in the photograph may be extracted and compared with information indicating the type of the predetermined waste to determine whether or not they match. As an example, the object sorting system 10 extracts information such as the color, material, and shape of the object included in the photograph in advance, assigns a value to it, and makes it photograph data. On the other hand, the object sorting system 10 assigns a predetermined value to the information indicating the type of the predetermined waste, and makes it predetermined type data. After that, the calculation unit 102 compares the photograph data with the predetermined type data, and if it falls within a certain range, it can be determined that the object is highly related to the predetermined type. According to this form, the waste sorting work can be made more efficient.
[0031] According to the present invention, it is possible to determine whether an object is waste from a photograph taken. The present invention is also applicable to mobile information terminals such as mobile phones and tablet terminals.
[0032] In the present invention, a photograph of an object is acquired by a photograph acquisition unit 101, and the degree to which the object contained in the photograph indicates a type of waste is calculated through a learning model that has previously machine-learned the correspondence between learning image data and information indicating the type of object contained in the learning image data. At this time, more accurate judgment is possible by considering not only color tone but also feature quantities such as shape and size. In addition, special waste such as heterogeneous waste and bulky waste can also be appropriately identified. Based on the degree calculated in this way, the output unit can separate the object into types such as general waste and recyclable waste.
[0033] The images input to the object sorting system 10 according to the present invention may be given an identifier, which may be set in advance, such as an image, or may be set by a similar image search device, so that the images can be identified.
[0034] The object sorting system 10 according to this embodiment can determine whether an object is waste from a captured image. In addition, since any image processing is possible, more accurate determination is possible. As a method for selecting a representative image, for example, the first image received by the selection unit among the grouped images may be used, or any image among the grouped images may be used.
[0035] The object classification system 10 according to the present invention generates a multimodal model by training a fully connected layer so that classification information that is likely to be output based on the appearance features and classification text features of a training image approaches the classification information of the training image. This multimodal model receives the appearance features and classification text features of an input image, and is adjusted so that the output classification information approaches the correct classification information of the input image. Then, the correct classification information of the input image can be estimated using this multimodal model.
[0036] The object classification system 10 according to the present invention trains the attention mechanism of the appearance feature extraction model so that classification information that is likely to be output based on the internal state of the CNN unit obtained by inputting appearance information of the training image approaches the classification information of the training image. In this way, the image similarity estimation system according to the present invention can estimate the degree to which a photo containing the same type of object as the training image is similar to the training image by inputting the photo. The image similarity estimation system according to the present invention can be used in the object classification system.
[0037] 2, the object sorting system 10 may acquire a photo of an object 30, and then generate a list having a predetermined classification 301, a matching rate 302, and ratings and comments 303 based on the object 30 contained in the photo. The number and definition of the predetermined classifications 301 are not particularly limited, and a user may set the predetermined classifications by himself / herself, or may use classifications installed in the object sorting system 10.
[0038] Furthermore, the object sorting system 10 according to the present invention can extract one or more highly similar products in response to a similar image search request input by a user, by extracting a product area from a product image, calculating image features of each product, and calculating the similarity between each product, and can present the products to the user. The product recommendation system according to the present invention is expected to be used, for example, in online shopping sites on the Internet. The similar image search request input by the user is, for example, a photograph taken by the user. Since the product recommendation system according to the present invention can extract one or more highly similar products in response to a similar image search request input by a user, the user can significantly reduce the time and effort required to search for a product he or she wants.
[0039] In both the photo acquisition unit 101 and the price search unit 104, calculation of the feature vector of the search target image does not necessarily have to be performed by the similar image search device of the present invention, and similar image search can be performed using the feature vector of the search target image calculated by another device.
[0040] In the image retrieval method according to the present invention, an image is divided into regions having the same characteristics, and for each divided region, matching is performed at the pixel data level as a rough recognition using a reference template, and object candidates are extracted and the position of the object is detected. Then, in order to accurately detect the object from the object candidates, the object is accurately detected using feature quantities such as the object's shape and color. In this way, the image retrieval method according to the present invention is capable of high-precision and high-speed image retrieval.
[0041] In the object sorting system 10 according to this embodiment, the image generating device does not have to be a scanner, and may be a device capable of capturing images, such as a digital camera, a smartphone, or a tablet terminal.
[0042] Information on shooting conditions that can be acquired automatically, such as the camera model, may be acquired automatically and used to search for a reference image generation model. Also, the object to be inspected is not limited to food, but may be a package, an industrial product, or the like.
[0043] <Investigation of second-hand sales price ranges using similar image search> In addition, the price search unit 104 according to the present embodiment may register in advance, as attribute information, in the product item database, identification information of the combined product items associated as identical or similar, image feature data extracted from the image data of the sold product items, sales information such as the price and brand of the sold product items, and use information of each sold product, and store the information in a database mounted on the object sorting system 10. Then, the image photographed by the user terminal is collated with the product item database, and based on the collation result, combined product items related to the product item photographed by the user are presented. The product item database according to the present embodiment is not limited to domestic online shops, and may search for prices of overseas online shops, EC sites, and physical stores. In the case of a foreign store, the price search unit 104 may convert the foreign price into Japanese yen.
[0044] In addition, the object sorting system 10 according to the present embodiment is connected to the Internet NW, and may search for products identical or similar to the object included in the photo from each used goods sales site. When an identical or similar product is searched for, attribute information such as a photo, price, and seller of the identical or similar product may be extracted and displayed on the user terminal 20. When performing a price search, a similar image search may be performed using a classifier that classifies used goods. As shown in FIG. 4, when a photo including an object 40 is input to the object sorting system 10, the object sorting system 10 searches for used or new products similar to the object 40, and may generate information such as photos and prices of the used or new products as a price list 401. In this case, the information included in the price list 401 is not limited, and the price search unit 104 may add information such as URL information of an online store selling the used product and product description to the price list 401. These pieces of information may be stored as category information in a database mounted on the object sorting system 10.
[0045] The generation of the classifier does not necessarily have to be performed by the similar image search device of the present invention, and similar image search can be performed using a classifier generated by another device. It is also possible to automatically determine the type of photographed object and provide an appropriate processing method.
[0046] The category information is not only an image feature amount, but is also used in the similarity calculation in the similar image search means, and the similarity between the images to be compared is calculated by a weighted average with the similarity of the color, shape, and texture. The category information may be stored in a database as text information. As an example, the object sorting system 10 is connected to each EC site, and the database installed therein stores product information, and may store information stored in the storage unit, information input by the user, search results, and the like. When the user sets the search conditions by himself / herself, the object sorting system 10 may be provided with a condition setting unit. In this case, the search results are narrowed down based on the conditions set by the user.
[0047] In addition, in the present invention, the IDs of the major category, the IDs of the medium category, and the IDs of the small category may be registered separated by underscores. For example, if the object to be recycled is a daily necessity such as a pin, a lunch box case, or plastic packaging, the object may be assigned a major category ID since it is common. Conversely, if the object to be recycled is a valuable item having multiple parts such as a personal computer, tablet, or coffee maker, each part may be assigned a small category ID since the recycling method for each part differs depending on the material.
[0048] Also, after acquiring the price of each used or new item, the conversion unit 105 may convert the price into a predetermined point value according to a certain ratio. For example, the price search unit 104 may analyze information on the listing of each item and assign points equal to the price of each used or new item to the object in an equal ratio to the price. According to the latter half of FIG. 4, the conversion unit 105 may enter the name 402 of the store selling the object, and then generate a list of information such as the price 403, photo 404, and points 405 of an item similar to the object in the store.
[0049] When searching for used or new items similar to the target object, a learning model may be used to calculate the confidence level of the result. As an example, if the confidence level of the judgment result by the trained model is 95% or higher, the target object included in the photo is determined to be highly related to the used or new item and to match, and the price of the used or new item is acquired. If the confidence level is less than 95%, the target object included in the photo is determined to be low related to the used or new item and to not match, and the price of the used or new item does not need to be acquired.
[0050] <Prevention of tampering> The object sorting system 10 according to the present embodiment may use Advanced Data Analysis to embed personal information of the object owner in an uploaded image by steganography. Steganography is a type of information hiding, and is a technology for embedding certain information in other information. As an example, the generation unit 103 of the object sorting system 10 according to the present embodiment may generate a first identification code for reading personal information of the object owner, and may also generate a second identification code for reading information about the object. The first identification code and the second identification code are not limited to QR Code (registered trademark), and may include information identification codes such as barcodes.
[0051] According to FIG. 5, the object classification system 10 according to the present embodiment may generate an information list showing the analysis result of the object included in the photograph. The information list may have a photograph of the object, a first identification code for reading the personal information of the owner, and a second identification code for reading the information about the object. Among them, the first identification code of the owner may simultaneously include information that can identify the identity of the owner. The information for identifying the identity of the owner may be input by the owner in advance into the database installed in the object classification system 10, or may be collected from publicly available information on the Internet and stored in the database. When the user reads the first identification code, the identification code can be input on the screen presented when the user reads the first identification code. By comparing the identification code input by the user with the information capable of identifying the identity of the user stored in the database installed in the object classification system 10, if they match exactly, it can be determined that the user is the owner of the object. As an example, if the owner of the object is a school, the school may input the school code into the object classification system 10 in advance before obtaining the photograph of the object. After generating the recycling information of the object, the school can perform identity authentication by reading the first identification code and inputting the school code. If the school codes match, it may be determined that the owner of the object included in the photograph is the school.
[0052] After the user determines that he / she is the owner of the object included in the photograph, the user may read the second identification code and check the recycling information of the object. As an example, after the user reads the second identification code, product information, a proposal for the optimal recycling method, the estimated point number retrieved from similar images for the second-hand sales price, the school code, EXIF information, etc. may be displayed on the user terminal 20.
[0053] <EXIF Editing> The object sorting system 10 according to the present embodiment may add tags to the metadata of a photo in cooperation with another system. In general, when information such as photo data can be exchanged, there is a high possibility that information contained in the photo data will be leaked due to EXIF information. In this case, the object sorting system 10 displays EXIF information such as the date of photo shooting, tags, ratings, size, title, creator, and shooting location on the user terminal 20, and the user may re-edit each of the above-mentioned information on the user terminal 20, or the object sorting system 10 may encrypt each of the above-mentioned information. In addition, the re-editing of the EXIF information may be performed using an EXIF editing tool.
[0054] <Process Management> Furthermore, the object sorting system 10 according to this embodiment may generate a status management screen and a reference dashboard to visualize the process of collection by factories, reuse (upcycling) in schools, and the like. As an example, for a certain waste, information such as the object itself, the date of disposal, the time when the recycler picks up the waste, and the recycling result of the waste may be displayed on the user terminal 20. The user can grasp the recycling information and recycling process of the waste in real time.
[0055] It is assumed that the information processing device for the object sorting system 10 according to the present invention performs a learning process to generate a learning model, but this is not limited to this. A device other than the information processing device may generate the learning model, and the information processing device may acquire information on the learned learning model from this device, store it in the learning model memory section of the memory section, and use it for anomaly detection processing.
[0056] The photo acquisition unit 101 and price search unit 104 according to the present invention include an image acquisition module, an image display module, an area division module, an evaluation value calculation module, and an evaluation model determination module. The image acquisition module acquires the image to be evaluated. The image display module displays the image to be evaluated. The area division module divides the image to be evaluated into areas. The evaluation value calculation module calculates the feature amount of each area and calculates an evaluation value for each area. The evaluation model determination module calculates an evaluation value for the entire image to be evaluated from the evaluation values of each area.
[0057] Furthermore, the implementation form of the program is not limited to an application program such as an object code compiled by a compiler or a program code executed by an interpreter, but may be in the form of a program module built into an operating system, etc. The code module may be stored in any type of computer-readable medium or other computer storage device.
[0058] The object sorting system 10 according to the present embodiment can determine whether an object is waste from a photograph and propose an appropriate processing method. In addition, more accurate sorting is possible because the accuracy is improved by machine learning. The present invention can automatically determine the type of waste from a photograph. In addition, even if the direction of reclassification based on the reference data table is different, precise reclassification is possible.
[0059] <Operation> From now, referring to FIG. 6, the operation of the object sorting system 10 according to this embodiment will be described. As shown in FIG. 5, the photo acquisition unit 101 acquires a photo of an object (S501), and then calculates the degree of correspondence between the item included in the photo and information indicating a predetermined type (S502). In this case, since multiple matching rates are calculated for a certain object, the object sorting system 10 can generate an evaluation sentence based on the matching rates (S503). After that, the price search unit 104 searches for products similar to the object via the Internet (S504) and calculates the value of the object. Next, the conversion unit 105 assigns a score to the object according to its value based on the value of the object (S505). Then, the object sorting system 10 generates a list of information including the object photo, the identification code, and the comment sentence as output information (S506). Finally, the object sorting system 10 transmits the listed information to the user terminal 20 and displays it on the display unit of the user terminal (S507).
[0060] The object sorting system 10 according to the present invention is configured with electronic devices such as a personal computer, but may be embodied in any other electronic devices such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc., other than a PC. The present invention makes it possible to determine whether an object is waste from a photograph taken. In addition, an AI edge device may be installed in the user terminal 20 itself. The AI edge device is the AI part of an IoT device equipped with artificial intelligence (AI).
[0061] Some of the functions of the CPU may be realized by a circuit executed by program code such as a DSP, or by a hardware configuration such as a gate circuit generated based on a programming language written in Verilog, or by a hardware circuit.
[0062] The program may be stored in advance in a storage device (a storage device with a non-transient storage medium) such as an HDD (Hard Disk Drive) or a flash memory, or may be stored in a removable storage medium (a non-transient storage medium) such as a DVD or a CD-ROM, and may be installed by inserting the storage medium into a drive device. The program may be for realizing part of the above-mentioned functions, or may be capable of realizing the above-mentioned functions in combination with a program already recorded in the computer system, or may be realized using a programmable logic device such as an FPGA (Field Programmable Gate Array).
[0063] The object sorting system 10 according to the present embodiment can determine whether an object is waste from a captured image, thereby improving the efficiency of waste recycling work. In addition, the use of artificial intelligence technology such as LLM makes it possible to obtain recycling comments that serve as reference for each object, which is expected to lead to more efficient recycling work. [Explanation of symbols]
[0064] 10. Object sorting system 20 User terminal 30 Examples of Objects 101 Photo Acquisition Department 102 Calculation section 103 Generation part 104 Price Search Section 105 Conversion Department 106 Output section
Claims
1. a photo acquisition unit for acquiring a photo of an imaged object; a calculation unit that calculates the degree to which the object included in the photograph indicates a type of waste through a learning model that has previously been machine-learned to learn a correspondence relationship between learning image data and information indicating a type of object included in the learning image data; an output unit that outputs the degree together with the photograph; a price search unit that acquires an image similar to the photograph as a similar image and searches the Internet for a sales price range of an object included in the similar image; A conversion unit that converts the amount indicating the sales price range into points. Object sorting system.
2. The object sorting system includes: A generation unit that generates evaluation data based on the degree through a large-scale language model that has previously trained an input evaluation sentence text.
2. The object sorting system according to claim 1 .
3. The generation unit is An identification code that identifies the identity of the owner of the object is generated and linked to the photograph of the object.
3. The object sorting system according to claim 2.
4. The computer A photo acquisition step of acquiring a photo of the captured object; a calculation step of calculating a degree to which the object included in the photograph indicates a type of waste through a learning model that has previously been machine-learned to learn a correspondence relationship between learning image data and information indicating a type of object included in the learning image data; an output step of outputting the degree together with the photograph; a price search step of acquiring an image similar to the photograph as a similar image, and searching the Internet for a sales price range of an object included in the similar image; A conversion step of converting the amount indicating the sales price range into points. Method of separating objects.
5. On the computer, A photo acquisition function for acquiring a photo of the captured object; A calculation function that calculates the degree to which the object included in the photograph indicates a type of waste through a learning model that has previously been machine-learned to learn the correspondence between learning image data and information indicating the type of object included in the learning image data; and an output function for outputting the degree together with the photograph; a price search function for acquiring an image similar to the photograph as a similar image and searching the Internet for a sales price range of an object included in the similar image; A conversion function for converting the amount indicating the selling price range into points; Object sorting program.
Citation Information
Patent Citations
High heat-insulating furnace
JP1984069685A
Waste disposal history managing system, waste disposal history managing method and waste disposal history managing program
JP2023081501A
Waste disposal history managing system, waste disposal history managing method and waste disposal history managing program
JP2023171971A
Cited By
Sorting processing support system, sorting processing support method, program, and storage medium
WO2026176664A1
