Information processing device, information processing method, and information processing program

Abstract

Users should be able to easily determine the manufacturing date of the object. [Solution] The information processing device 100 comprises an acquisition unit 131, a prediction unit 132, a learning unit 133, and a provision unit 134. The acquisition unit 131 acquires an image of the product and textual information such as the product title and description. The prediction unit 132 predicts the manufacturing date of the target product based on the combination of the image of the product and the textual information such as the product title and description. The provision unit 134 provides information about the product in the order based on the predicted manufacturing date.

Description

[[Technical Field]]

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program. [[Background Art]]

[0002] In recent years, flea markets, auction services and the like via networks have been actively provided. In such services, for example, a seller who puts an item for sale adds image data, a product title, and a description to an introduction page of each product and uploads it onto a network (see, for example, Patent Document 1). [[Prior Art Literature]] [[Patent Literature]]

[0003] [[Patent Document 1]] Japanese Unexamined Patent Application Publication No. 2018-101339 [[Summary of the Invention]] [[Problem to be Solved by the Invention]]

[0004] By the way, among users of the above services, there are users searching for antique products. Such users check the manufacturing age of a product from, for example, image data, a product title, a description, or the like, but the manufacturing age is not always described in all product information, so there is room for improvement in terms of user convenience.

[0005] The present application has been made in view of the above problem, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of estimating the manufacturing age of an object. [[Means for Solving the Problem]]

[0006] The information processing device according to the present application is characterized by comprising: a prediction unit that estimates the manufacturing date of an object based on an image of the object and character information indicating the object; and a provision unit that provides information about the object in the order based on the estimated manufacturing date. [Effects of the Invention]

[0007] According to one embodiment, the user can easily determine the manufacturing date of the object. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is an explanatory diagram showing an overview of the information processing according to the embodiment. [Figure 2] Figure 2 shows an example of the configuration of an information processing system according to the embodiment. [Figure 3] Figure 3 shows an example of the configuration of an information processing device according to the embodiment. [Figure 4] Figure 4 shows an example of a score generated by a machine learning model in the information processing device according to the embodiment. [Figure 5] Figure 5 shows an example of a vectorized model in the base model. [Figure 6] Figure 6 shows an example of a vectorization model that estimates the manufacturing date from the product title. [Figure 7] Figure 7 shows an example of a vectorization model used to estimate the manufacturing date from a product image. [Figure 8] Figure 8 is a flowchart showing an example of a processing procedure according to the embodiment. [Figure 9] Figure 9 shows an example of the configuration of a user terminal according to this embodiment. [Figure 10] Figure 10 is a hardware configuration diagram showing an example of a computer that implements the functions of an information processing device. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing apparatus, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing apparatus, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in the following embodiments, and redundant descriptions are omitted.

[0010] [1. Overview of Information Processing Methods] First, with reference to Figure 1, an overview of the information processing according to the embodiment will be described. Figure 1 is an explanatory diagram showing an overview of the information processing according to the embodiment. Figure 1 shows an example of the operation of the information processing system 1, which includes the information processing device 100 according to the embodiment. Specifically, Figure 1 shows an example in which the information processing device 100 performs processing to estimate the manufacturing date of a product from information used to introduce each product on an e-commerce site where multiple sellers list the products they handle. As shown in Figure 1, the information processing system 1 according to the embodiment includes the information processing device 100 and user terminals 200A, 200B, ...

[0011] The information processing device 100 provides a service to user U that estimates the manufacturing date of a product listed as a commodity in e-commerce, for example, using a base model obtained by training a combination of an image of the product (product image) and textual information describing the product as training data. The textual information describing the product includes the product title and description attached to the product. In addition to message sending and receiving services, the services provided by the information processing device 100 may also include, for example, news provision services, auction services, weather forecast services, shopping services, financial transaction (stock trading, etc.) services, route search services, map provision services, travel services, restaurant introduction services, blog services, etc.

[0012] Furthermore, the information processing device 100 may also function as a web server providing websites related to various services. Alternatively, the information processing device 100 may be a device that distributes information to be displayed on applications related to various services installed on the user terminal 200 used by user U. Furthermore, the information processing device 100 may be a server that distributes the application data itself.

[0013] In this e-commerce site, multiple sellers list the products they handle. For example, an e-commerce site could be a shopping mall-like site where multiple sellers each have their own stores, or it could be an auction site where multiple sellers list products as they see fit. In such an e-commerce site, sellers typically create and assign product titles and descriptions to their products. Sellers also upload image data of the product along with the title and description. The e-commerce site generates product purchase pages based on the information uploaded by the sellers. A user U accesses the e-commerce site, refers to the product title and description on the purchase page, and makes a purchase. When user U searches for a product, the site finds the product U wants by determining whether the words in the product title and description assigned by the seller match the query entered by user U.

[0014] On such e-commerce sites, the creation of product information is left to the seller, which means that users are not always guaranteed to receive accurate product information. In other words, even if a seller arbitrarily assigns a product title and description, it may not include the year of manufacture, for example.

[0015] For example, for a user U searching for antique products, if the manufacturing year of the product is known, it becomes possible to provide functions such as filtering on the search result page (for example, by selecting the checkbox for "1950 to 1960", users can search for products from that period) and sorting on the search result page (products are sorted by manufacturing year based on the manufacturing year score described later, allowing users to browse products in chronological order like window shopping).

[0016] Therefore, the information processing apparatus 100 of the present embodiment estimates the manufacturing year of a product and assigns it as product information by the following method. Through such processing, the information processing apparatus 100 allows a user to easily grasp the manufacturing year of a product. This enables the information processing apparatus 100 to provide appropriate product information to the user U. Hereinafter, an example of the estimation processing performed by the information processing apparatus 100 will be described along the flow with reference to FIG. 1.

[0017] First, the information processing apparatus 100 acquires, from a user terminal 200 of the user U, character information as an image obtained by capturing an image of a target product (product image) and search information (product information) (step S1). Specifically, when the product to be processed is a desk 50, the information processing apparatus 100 acquires a product image P1 having the desk 50 as a subject (see FIG. 4).

[0018] Subsequently, the information processing apparatus 100 acquires character information associated with the product image P1. For example, this character information is assumed to be expressed as a product title "PB49 XConcept Tokyo Desk / XConcept Tokyo Modern / Hadano City, Kanagawa Prefecture".

[0019] Next, the information processing apparatus 100 calculates a score for each manufacturing year based on the product image and the character information (step S2). For example, the information processing apparatus 100 calculates the manufacturing year of the product based on the acquired product image and character information using a model trained with a combination of a product image and character information as learning data.

[0020] Here, we will briefly explain the model used by the information processing device 100. The model used by the information processing device 100 includes, for example, a base model obtained by training with a large number of product images and text information as training data. The base model is not specialized for a particular task, but can be used for various tasks.

[0021] The base model of this embodiment is a "clip-japanese-base" model that has the ability to simultaneously analyze images, text, and other elements and evaluate the relationships between these multiple modalities. CLIP (Contrastive Language-Image Pre-training) is a representative example of this, which trains a model using a large amount of images and text collected from the internet, improving zero-shot performance in many downstream tasks. CLIP has high versatility and extensibility and is used in a variety of situations, both in research and in actual services.

[0022] CLIP has two models: a "text vectorization model" and an "image vectorization model." These can measure semantic similarity by converting text and images into vectors and calculating the similarity of those vectors. For example, CLIP calculates the similarity between the vectorized product image P1 of Desk 50 (Q1) shown in Figure 4 and the vectorized text (R2, R3, R4) (e.g., Q2, Q3, Q4). As shown in Figure 5, the vectorized text "desk" (Q2) has the highest similarity (match) to the vectorized product image P1 of Desk 50. Vector similarity can be calculated not only for image-text pairs, but also for text-text pairs and image-image pairs.

[0023] In this embodiment, the information processing device 100 takes a product image P1 and text information as input and trains a machine learning model that outputs the manufacturing year. When taking text information as input and outputting the manufacturing year, as shown in Figure 6, the information processing device 100 vectorizes the product title "PB49 XConcept Tokyo Desk / XConcept Tokyo Modern / Hadano City, Kanagawa Prefecture". Next, the information processing device 100 vectorizes the strings "Product from the 1900s", "Product from the 1910s", ... "Product from the 2020s" for the era to be estimated. Then, the information processing device 100 calculates the similarity between the product title vector and the era string vector and converts it into a probability value to predict the likelihood of it being from that era.

[0024] On the other hand, when an image is used as input and the manufacturing date is output, the information processing device 100 vectorizes the product image P1, as shown in Figure 7. Next, the information processing device 100 vectorizes the strings "products from the 1900s," "products from the 1910s," ... "products from the 2020s" for the era to be estimated. Then, the information processing device 100 calculates the similarity between the product image vector and the era string vector and converts it into a probability value to predict the likely era.

[0025] Next, the information processing device 100 provides scores in order based on the predicted manufacturing year (step S3). For example, the information processing device 100 provides the user terminal 200 with information about the product shown in Figure 4. The product information includes, for example, the product title "PB49 XConcept Tokyo Desk / XConcept Tokyo Modern / Hadano City, Kanagawa Prefecture" and the product image P1. The product information may also include a description.

[0026] Furthermore, product information includes, for example, the manufacturing year, a score estimated from the product title, a score estimated from the image, and an overall estimated score. The manufacturing year is composed of, for example, the 1900s, 1910s, ..., 2020s. The score estimated from the product title is the score obtained when estimating the manufacturing year from textual information, and is the probability value described above. In Desk 50, the score estimated from the product title is highest for the 2020s. The score estimated from the image is the score obtained when estimating the manufacturing year from product image P1, and is the probability value described above. In Desk 50, the score estimated from the image is highest for the 1970s. The overall estimated score is a score based on the score obtained when estimating the manufacturing year from textual information and the score obtained when estimating the manufacturing year from product image P1, and is, for example, the average of the two scores. In this embodiment, the overall estimated score is highest for the 2020s. The estimated score is also used, for example, when a user U searching for products on the site uses sorting on the search results page.

[0027] Thus, according to the information processing device 100 of this embodiment, for example, a user looking for antique items can easily find out the approximate manufacturing date of items listed on an auction site whose manufacturing date is unknown, thereby improving user convenience.

[0028] [2. Example of an information processing system configuration] Next, the configuration of the information processing system according to the embodiment will be described using Figure 2. Figure 2 is a diagram showing an example of the configuration of the information processing system according to the embodiment. As shown in Figure 2, the information processing system 1 according to the embodiment has an information processing device 100, a user terminal 200, and a network N. These configurations will be briefly described below.

[0029] The information processing device 100 may be, for example, a personal computer (PC), a workstation (WS), or a computer equipped with server functions. The information processing device 100 performs processing based on information transmitted from a user terminal 200 via the network N.

[0030] The user terminal 200 is an information processing device used by the user. The user terminal 200 may be, for example, a smartphone, tablet, desktop PC, notebook PC, mobile phone, or PDA (Personal Digital Assistant). In the example shown in Figure 1, the user terminal 200 is a smartphone.

[0031] Network N connects the information processing device 100 and the user terminal 200 so that they can communicate with each other via wired or wireless connection. If Network N is wired, it may be implemented using Ethernet (registered trademark) as defined in IEEE 802.3. If Network N is wireless, it may be implemented using a wireless LAN (Local Area Network) as defined in IEEE 802.11.

[0032] [3. Example of Information Processing Device Configuration] Next, the configuration of the information processing device 100 according to the embodiment will be described using Figure 3. The information processing device 100 shown in Figure 3 has a communication unit 110, a storage unit 120, and a control unit 130.

[0033] (Regarding Communications Unit 110) The communication unit 110 is implemented, for example, by a NIC (Network Interface Card). The communication unit 110 is connected to the network N by wire or wireless connection and transmits and receives information with the user terminal 200, etc.

[0034] (Regarding memory unit 120) The memory unit 120 includes a main memory and an external memory. The main memory stores programs executed by the control unit 130, or data processed by the control unit 130. The main memory is implemented by semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs. The external memory stores data processed by the control unit 130. The external memory may be implemented by hard disks, SSDs (Solid State Drives), magnetic tapes, optical discs, etc.

[0035] The memory unit 120 stores, for example, information about products uploaded by sellers. The memory unit 120 also stores information about training for generating a model to be used in estimation processing. The memory unit 120 may also store the model itself that has been trained based on the training data. The information processing device 100 may also update the training data stored in the memory unit 120 as appropriate and continue training the generated model.

[0036] (Regarding the control unit 130) Returning to Figure 3, let's continue the explanation. The control unit 130 is a controller, and is realized by various programs (corresponding to an example of an information processing program) stored in the memory device inside the information processing device 100, such as a CPU (Central Processing Unit), MPU (Micro Processing Unit), ASIC (Application Specific Integrated Circuit), or FPGA (Field Programmable Gate Array), executing them using a memory area such as RAM as the working area. In the example shown in Figure 3, the control unit 130 has an acquisition unit 131, a prediction unit 132, a learning unit 133, and a provision unit 134.

[0037] (Regarding acquisition section 131) The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires an image of an object that is a product, and text information for searching for that object. Specifically, the acquisition unit 131 acquires an image of a product that has been listed as a product in e-commerce. The acquisition unit 131 also acquires text information associated with that product (for example, product title, description, etc.).

[0038] Furthermore, the acquisition unit 131 acquires text data associated with the object. For example, the acquisition unit 131 acquires words indicating the attributes of a predetermined object as text data associated with that object. More specifically, the acquisition unit 131 acquires words indicating the year of manufacture or the date of manufacture of the predetermined object as words indicating the attributes of that object.

[0039] For example, the acquisition unit 131 acquires text data such as the product title or a descriptive document associated with the product that explains the product. For example, if the product is a desk and it is difficult to identify the product from the image alone, the acquisition unit 131 performs morphological analysis on the product title and descriptive document to extract words that can serve as information to identify the product. Specifically, the acquisition unit 131 acquires words indicating at least the year and date of manufacture of the product. In this case, the prediction unit 132, which will be described later, estimates the manufacturing date based on the information obtained from the image and the information obtained from the words.

[0040] The acquisition unit 131 appropriately stores the acquired information in the storage unit 120. The acquisition unit 131 also appropriately acquires information to be used for processing from the storage unit 120.

[0041] (Regarding prediction unit 132) The prediction unit 132 uses a model trained on combinations of images and text information acquired by the acquisition unit 131 as training examples to predict the manufacturing date of an object whose manufacturing date has not been determined, based on an image of the object and text information used to search for the object.

[0042] Specifically, the prediction unit 132 estimates the manufacturing date of a product from an image of the product listed as a commodity in e-commerce. For example, when an image is uploaded from the user terminal 200, the prediction unit 132 inputs the uploaded image into its model and outputs the manufacturing date of the product shown in the image.

[0043] Furthermore, the prediction unit 132 estimates the manufacturing date of an object from the text information used to search for the object. For example, when text information such as the product title and description is uploaded from the user terminal 200, the prediction unit 132 inputs the uploaded text information into the model and outputs the manufacturing date of the product.

[0044] (Regarding Learning Section 133) The learning unit 133 trains on combinations of images and text information using training data, and generates a machine learning model that outputs the manufacturing date for input combinations of images and text information. Specifically, the learning unit 133 extracts products on the network N in which the manufacturing date is written in the product title or description and uses them as training data. Then, using the training data, the learning unit 133 generates a machine learning model that estimates the manufacturing date from the input combination of product title and image. In this case, the prediction unit 132 predicts the manufacturing date of newly listed products using the obtained machine learning model.

[0045] (Regarding Section 134) The information provider 134 provides information about an object to a user terminal 200 that has requested a prediction of the object's manufacturing date, in an order based on the estimated manufacturing date. For example, as shown in Figure 4, the information provider 134 provides various information such as the manufacturing date, which consists of the 1900s, 1910s, ..., 2020s; a score estimated from the product title; a score estimated from the image; and an overall estimated score. In the illustrated example, horizontal bar graphs corresponding to the score estimated from the product title, the score estimated from the image, and the overall estimated score have been added. This is because it can be difficult to grasp the magnitude of the score from the numerical value alone, so adding horizontal bar graphs makes it easier for the user to grasp the magnitude of the score. The information provider 134 also displays a list of products sorted by the predicted manufacturing date based on the score obtained by the model.

[0046] [4. Example of user terminal configuration] Next, the configuration of the user terminal 200 according to the embodiment will be described using Figure 9. Figure 9 is a diagram showing an example of the configuration of a user terminal according to the embodiment. As shown in Figure 9, the user terminal 200 has a communication unit 210, an input unit 220, an output unit 230, and a control unit 240.

[0047] The communication unit 210 is implemented by, for example, a NIC, a wireless LAN card, etc. The communication unit 210 is connected to the network N by wire or wireless connection and transmits and receives various types of information to and from the information processing device 100 via the network N.

[0048] The input unit 220 receives various operation information from the user. For example, the input unit 220 may accept various operations from the user via a touch panel on a display surface (e.g., the output unit 230). Alternatively, the input unit 220 may accept various operations from buttons on the user terminal 200, or from a keyboard or mouse connected to the user terminal 200.

[0049] The output unit 230 is a display screen for a tablet terminal, for example, which is implemented using a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. In other words, if the input unit 220 of the user terminal 200 is a touch panel, the output unit 230, which is the display screen, accepts user input and selections and also outputs to the user. The output unit 230 may also be a speaker, and may output sound through the speaker.

[0050] The control unit 240 is implemented, for example, by a CPU or MPU executing various programs stored in the user terminal 200 using RAM as a working area. Alternatively, the control unit 240 may be implemented by an integrated circuit such as an ASIC or FPGA.

[0051] As shown in Figure 9, the control unit 240 includes a supply unit 241 and a storage unit 242.

[0052] The information provision unit 241 provides various information via various applications installed on the user terminal 200. Specifically, it displays the information provided by the information provision unit 134 of the information processing device 100 on the output unit 230.

[0053] The memory unit 242 stores various types of information depending on the purpose. For example, the memory unit 242 stores image data of products and text data for searching for those products.

[0054] [5. Processing Procedure] Next, the processing procedure by the information processing device 100 according to the embodiment will be described using Figure 8. Figure 8 is a flowchart of an example of the processing procedure according to the embodiment. Note that the processing procedure shown below is repeatedly executed by the control unit 130 of the information processing device 100.

[0055] The control unit 130 of the information processing device 100 acquires an image of a product and text information indicating the product using the acquisition unit 131 (step S101). Next, the control unit 130 uses the prediction unit 132 to calculate a score for each manufacturing year of the product based on the acquired image and text information, using a model (step S102). Next, the control unit 130 uses the prediction unit 132 to calculate a score for each user based on the day of the week and time (step S103). Finally, the control unit 130 uses the provision unit 134 to deliver the information to each user at a timing based on the score (step S104), and then terminates the process.

[0056] [6. Hardware Configuration] The information processing device 100 according to the above embodiment is implemented, for example, by a computer 1000 having the configuration shown in Figure 10. The following explanation will use the information processing device 100 as an example. Figure 10 is a hardware configuration diagram showing an example of a computer 1000 that implements the functions of the information processing device 100.

[0057] Computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.

[0058] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as RAM, that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is implemented using ROM (Read Only Memory), HDD, flash memory, etc.

[0059] Output IF1060 is an interface for transmitting information to be output to output devices 1010, such as monitors and printers, and is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). Input IF1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, and scanners, and is implemented using, for example, USB.

[0060] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), tape media, magnetic recording media, or semiconductor memory. Furthermore, the input device 1020 may also be an external storage medium such as a USB memory stick.

[0061] Network IF1080 receives data from other devices via network N and sends it to the arithmetic unit 1030, and also transmits data generated by the arithmetic unit 1030 to other devices via network N.

[0062] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0063] For example, when the computer 1000 functions as an information processing device 100, the arithmetic unit 1030 of the computer 1000 performs the same functions as the control unit 130 by executing a program (for example, an information processing program) loaded onto the primary storage device 1040. In other words, the arithmetic unit 1030 performs processing by the information processing device 100 according to this embodiment in cooperation with the program (for example, an information processing program) loaded onto the primary storage device 1040.

[0064] The information processing device 100 may use either the manufacturing date estimation machine learning model or the base model described above to predict the manufacturing date, or it may use both. Furthermore, while the target product is a manufactured item, it may also be a refurbished product. In this case, the refurbished product may be used to perform the prediction using the learning model.

[0065] Furthermore, the information processing device 100 outputs scores estimated from the product title and scores estimated from the image, in order of manufacturing year. If the year with the highest score estimated from the product title and the year with the highest score estimated from the image are the same, then that manufacturing year is the most reliable as the manufacturing year of the product. On the other hand, if for some reason the year with the highest score estimated from the product title and the year with the highest score estimated from the image are not the same, and there is a large relative difference, then the reliability of the predicted manufacturing year may not be high. In this case, the information processing device 100 may be configured to notify the user U of an alert or the like.

[0066] Furthermore, while the information processing device 100 predicts the manufacturing date of a product, it is not limited to this; it may also be configured to predict the version of the product, or to predict both the manufacturing date and the version.

[0067] [7. Structure and Effects] As described above, the information processing device 100 according to this embodiment comprises an acquisition unit 131, a prediction unit 132, a learning unit 133, and a provision unit 134. The acquisition unit 131 acquires an image of the product and textual information such as the product title and description that indicates the product. The prediction unit 132 predicts the manufacturing date of the target product based on the combination of the image of the product and the textual information such as the product title and description that indicates the product. The provision unit 134 provides information about the product in an order based on the predicted manufacturing date. As a result, the information processing device 100 allows, for example, a user U searching for antique items to easily grasp the manufacturing date of items listed on auction sites, etc.

[0068] Furthermore, the information processing device 100 uses a prediction unit 132 to predict the manufacturing date of a product, employing a model trained on combinations of product images and their corresponding text information as training data. This allows the information processing device 100 to improve the reliability of its predicted manufacturing date. The providing unit 134 then provides a list of products sorted by the predicted manufacturing date based on the score obtained by the model. This makes it easier for the user U to understand the predicted manufacturing date.

[0069] Furthermore, the information processing device 100's learning unit 133 trains on training data consisting of image and text information combinations, and generates a machine learning model that outputs the manufacturing date for each input image and text information combination. This allows the information processing device 100 to efficiently generate a highly accurate model.

[0070] Furthermore, the information processing device 100 predicts the manufacturing date of a product using a base model obtained by the prediction unit 132, which learns a large amount of image and text information as training data from among the learning models. This makes it possible for the information processing device 100 to use a relatively low-cost and accurate model.

[0071] [8. Other] Although embodiments of the present invention have been described above, the present invention is not limited by the content of these embodiments. Furthermore, the aforementioned components include those that can be easily conceived by those skilled in the art, those that are substantially the same, and those that fall within the so-called equivalent range. Moreover, the aforementioned components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the gist of the embodiments described above.

[0072] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0073] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0074] For example, the information processing device 100 described above may be implemented using multiple server computers, and depending on the function, it may be implemented by calling external platforms, etc., via APIs (Application Programming Interfaces) or network computing, allowing for flexible configuration changes.

[0075] Furthermore, each of the processes described in the embodiments above can be combined as appropriate, as long as the processing content does not contradict each other.

[0076] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the control unit 130 can be replaced with a control means or a control circuit. [Explanation of Symbols]

[0077] 1. Information Processing System 100 Information Processing Devices 110 Communications Department 120 Storage section 130 Control Unit 131 Acquisition Department 132 Prediction Section 133 Learning Department 134 Provision Department 200 user terminals

Claims

1. A prediction unit predicts the manufacturing date of an object based on a combination of an image of the object and textual information indicating the object. A providing unit that provides information about the object in order based on the predicted manufacturing date, An information processing device characterized by comprising:

2. The prediction unit, Using a model trained with the combination of the aforementioned image and the aforementioned text information as training data, the manufacturing date of the object is predicted. The aforementioned supply unit is, For each predicted manufacturing year, the objects are sorted and displayed in a list based on the score obtained by the model. The information processing apparatus according to claim 1.

3. The system further comprises a learning unit that trains on the aforementioned training data and generates a machine learning model that outputs the manufacturing year for each combination of the input image and the text information. The information processing apparatus according to claim 2.

4. The prediction unit, The manufacturing date of the object is predicted using a base model obtained by training with a large number of combinations of the image and the text information from the aforementioned models. The information processing apparatus according to claim 2.

5. An information processing method performed by an information processing device, A prediction step that predicts the manufacturing date of an object based on a combination of an image of the object and textual information indicating the object, A providing step of providing information about the object in order based on the predicted manufacturing date, An information processing method characterized by including

6. A prediction procedure for predicting the manufacturing date of an object based on a combination of an image of the object and textual information indicating the object, A provision procedure for providing information about the object in order based on the predicted manufacturing date, An information processing program that causes a computer to execute something.

Images