Information processing apparatus, information processing method, and program

Abstract

To achieve an information processing apparatus that can suitably perform color mixing prediction related to plastic material including waste plastic.SOLUTION: An information processing apparatus comprises: acquisition means that acquires any one of color information and pigment information and the feature quantity of waste plastic; and prediction means that predicts the other information of the color information and the pigment information from the information acquired by the acquisition means, by using a prediction model having learned the relationship among the pigment information, feature quantity of waste plastic, and color information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] A technique for predicting color toning of plastic materials is known. For example, Patent Document 1 describes: A technique for predicting color data of a coating film based on color matching has been disclosed for a resin-containing coating material. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-188046 Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology described in Patent Document 1, unlike virgin materials, the simple rule of pigment data addition does not hold for plastic materials containing waste plastics, making it difficult to predict color tones for plastic materials containing waste plastics.

[0005] The present disclosure has been made in consideration of the above-mentioned problems, and one exemplary purpose thereof is to provide a technology for suitably predicting color toning for plastic materials including waste plastics. [Means for solving the problem]

[0006] An information processing device according to an exemplary aspect of the present disclosure includes an acquisition means for acquiring either color information or pigment information and characteristic quantities of waste plastic, and a prediction means for predicting the other of the color information and the pigment information from the information acquired by the acquisition means using a prediction model that has learned the mutual correlation between the pigment information, the characteristic quantities of waste plastic, and the color information.

[0007] An information processing device according to an exemplary aspect of the present disclosure includes an acquisition means for acquiring either color information or pigment information, and characteristic quantities of waste plastic, and a learning means for learning a predictive model that predicts the correlation between the pigment information, characteristic quantities of waste plastic, and color information by referring to the information acquired by the acquisition means.

[0008] An information processing method according to an exemplary aspect of the present disclosure includes acquiring either color information or pigment information and characteristic quantities of waste plastic, and predicting the other of the color information and the pigment information from the acquired information using a prediction model that has learned the mutual relationships between the pigment information, the characteristic quantities of waste plastic, and the color information.

[0009] An information processing method according to an exemplary aspect of the present disclosure includes acquiring either color information or pigment information, and characteristic quantities of waste plastic, and training a predictive model that predicts the correlation between the pigment information, characteristic quantities of waste plastic, and color information, by referring to the acquired information.

[0010] A program according to an exemplary aspect of the present disclosure is a program that causes a computer to function as an information processing device, and the program causes the computer to execute an acquisition process that acquires either color information or pigment information and characteristic quantities of waste plastic, and a prediction process that predicts the other of the color information and the pigment information from the information acquired by the acquisition process using a prediction model that has learned the mutual relationships between the pigment information, the characteristic quantities of waste plastic, and the color information.

[0011] A program according to an exemplary aspect of the present disclosure is a program that causes a computer to function as an information processing device, and the program causes the computer to execute an acquisition process that acquires either color information or pigment information and characteristic quantities of waste plastic, and a learning process that learns a predictive model that predicts the correlation between the pigment information, characteristic quantities of waste plastic, and color information by referring to the information acquired by the acquisition process. [Effects of the Invention]

[0012] According to one exemplary aspect of the present disclosure, an exemplary effect is achieved in that a technology can be provided that can suitably predict color toning for plastic materials including waste plastics. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 2] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 3] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 4] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 5] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 6] FIG. 1 is a diagram for explaining information processing according to the present disclosure. [Figure 7] FIG. 1 is a diagram for explaining information processing according to the present disclosure. [Figure 8] FIG. 1 is a diagram for explaining information processing according to the present disclosure. [Figure 9] FIG. 1 is a diagram for explaining information processing according to the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating a display example by an information processing device according to the present disclosure. [Figure 11] FIG. 1 is a diagram for explaining information processing according to the present disclosure. [Figure 12] FIG. 1 is a diagram for explaining information processing according to the present disclosure. [Figure 13] FIG. 1 is a diagram for explaining information processing according to the present disclosure. [Figure 14] FIG. 10 is a diagram illustrating a display example by an information processing device according to the present disclosure. [Figure 15] FIG. 1 is a diagram for explaining information processing according to the present disclosure. [Figure 16]1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 17] FIG. 1 is a block diagram illustrating a configuration of a computer that functions as an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0014] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technologies (part or all of the products or methods) employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0015] First Exemplary Embodiment A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is the basic form of each exemplary embodiment described later. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technology shown in the drawings referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0016] (Configuration of information processing device 1) The configuration of an information processing device 1 according to this exemplary embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing device 1. As shown in Fig. 1, the information processing device 1 includes an acquisition unit 11 and a prediction unit 12.

[0017] (Acquisition part 11) The acquisition unit 11 acquires either color information or pigment information, and feature quantities of the waste plastic. Here, the color information acquired by the acquisition unit 11 is, for example, target color information indicating a target color. Also, the pigment information acquired by the acquisition unit 11 is, for example, pigment composition candidate information indicating usable pigment compositions.

[0018] In addition, the “feature amount of waste plastic” acquired by the acquisition unit 11 is, for example, - It may be numerical information showing the characteristics of waste plastics, Non-numerical information such as classification information and qualitative information on waste plastics may be presented quantitatively using numerical values ​​so that it can be referenced by machine learning models (one example is the predictive model described below).

[0019] In addition, in this specification, the term "waste plastic" does not exclude virgin materials. In other words, in this specification, "waste plastic" means: It may consist solely of discarded plastics, It may be a mixture of discarded plastic and virgin plastic material.

[0020] It should be noted that the information acquired by the acquisition unit 11 is, for example, information that is referenced in the inference phase, but this term does not limit the present exemplary embodiment.

[0021] (Prediction Section 12) The prediction unit 12 predicts the other of the color information and the pigment information from the information acquired by the acquisition unit 11 using a trained prediction model. Here, the prediction model is, for example, a prediction model that has learned the correlation between pigment information, feature quantities of waste plastic, and color information. To give a more specific example, the prediction unit 12 uses the following as the prediction model: (Prediction model 1) A prediction model that predicts color information indicating the color that will be obtained when a pigment indicated by the pigment information is applied to the waste plastic, based on pigment information and the feature quantities of the waste plastic. (Prediction model 2) A prediction model that predicts pigment information indicating pigments that will cause waste plastic to turn into the color indicated by the color information based on color information and the feature quantities of the waste plastic. The prediction unit 12 may use any one of the prediction models. (Prediction process 1) A process of predicting color information indicating a color corresponding to the pigment information acquired by the acquisition unit 11 from the pigment information and the feature amount of the waste plastic. (Prediction process 2) A process of predicting pigment information indicating a pigment corresponding to the color information from the color information acquired by the acquisition unit 11 and the feature amount of the waste plastic. At least one of the following is executed.

[0022] Here, any combination of the above-described prediction models 1 and 2 and prediction processes 1 and 2 may be adopted. To give a specific example, the prediction unit 12 may perform any of the following four types of prediction processes.

[0023] (Example 1-1: 1 prediction model x 1 prediction process) The pigment information and the feature amount of the waste plastic acquired by the acquisition unit 11 are A prediction model (prediction model 1 above) that predicts color information indicating the color that will be obtained when the pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic. A process of predicting color information indicating a color corresponding to the pigment information acquired by the acquisition unit 11 by inputting the information into (Example 1-2: Prediction model 1 x prediction process 2) By referring to the color information acquired by the acquisition unit 11 and the feature amount of the waste plastic, A prediction model (prediction model 1 above) that predicts color information indicating the color that will be obtained when the pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic. A process of predicting pigment information indicating a pigment corresponding to the color information acquired by the acquisition unit 11 using the In this case, as an example, the prediction unit 12 inputs each of multiple candidate pigment information into the prediction model 1, predicts the color corresponding to each candidate, and performs a search process so that the color approaches the color indicated by the color information acquired by the acquisition unit 11, thereby performing a process to predict pigment information indicating the pigment corresponding to the color information acquired by the acquisition unit 11.

[0024] (Example 2-1: 2 prediction models x 1 prediction process) By referring to the pigment information and the feature amount of the waste plastic acquired by the acquisition unit 11, A prediction model that predicts pigment information indicating the pigment that will cause the waste plastic to turn into the color indicated by the color information and the feature amount of the waste plastic (prediction model 2 above) A process of predicting color information indicating a color corresponding to the pigment information acquired by the acquisition unit 11 using the In this case, as an example, the prediction unit 12 predicts pigment information corresponding to each candidate by inputting each of multiple candidate color information into the prediction model 1, and performs a search process so that the pigment information approaches the pigment information acquired by the acquisition unit 11, thereby performing a process to predict color information indicating the color corresponding to the pigment information acquired by the acquisition unit 11.

[0025] (Example 2-2: Prediction model 2 x prediction process 2) The color information and the feature amount of the waste plastic acquired by the acquisition unit 11 are A prediction model that predicts pigment information indicating the pigment that will cause the waste plastic to turn into the color indicated by the color information and the feature amount of the waste plastic (prediction model 2 above) A process of predicting pigment information indicating a pigment corresponding to the color information acquired by the acquisition unit 11 by inputting the information into The specific configuration of the prediction model used by the prediction unit 12 does not limit this exemplary embodiment, but may be, for example, a deep learning model having multiple layers or other models. Furthermore, the prediction model may be trained by supervised learning, or may be trained by unsupervised learning or semi-supervised learning.

[0026] The prediction result by the prediction unit 12 is, for example, - Presented to the user via an output unit (not shown) The color information is provided to an external manufacturing device via a communication unit (not shown) and is used to adjust the color of plastic materials, including waste plastics.

[0027] (Effects of information processing device 1) As described above, in the information processing device 1, Acquire either color information or pigment information and the feature amount of the waste plastic, Using a prediction model that has learned the correlation between pigment information, waste plastic feature values, and color information, predicting the other of the color information and the pigment information from the acquired information. The following configuration is adopted.

[0028] In this way, the information processing device 1 predicts either color information or pigment information from the other by referring to the feature amounts of the waste plastic, and therefore can suitably predict color matching for plastic materials including waste plastic.

[0029] (Flow of information processing method S1) Next, the flow of the information processing method S1 according to this exemplary embodiment will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the information processing method S1. As shown in Fig. 2, the information processing method S1 includes an acquisition process (acquisition step) S11 and a prediction process (prediction step) S12.

[0030] (Step S11) In step S11, the acquisition unit 11 acquires either color information or pigment information, and the feature amount of the waste plastic. A more specific description of the acquisition unit 11 has been given above, so a description thereof will be omitted here.

[0031] (Step S12) In step S12, the prediction unit 12 predicts the other of the color information and the pigment information from the acquired information using a prediction model that has learned the correlation between the pigment information, the feature values ​​of the waste plastic, and the color information. The prediction unit 12 has been described in more detail above, so a detailed description thereof will be omitted here.

[0032] (Effect of information processing method S1) As described above, in the information processing method S1, Acquire either color information or pigment information and the feature amount of the waste plastic, Using a prediction model that has learned the correlation between pigment information, waste plastic feature values, and color information, predicting the other of the color information and the pigment information from the acquired information. According to the above configuration, the same effects as those of the information processing device 1 are achieved.

[0033] (Configuration of information processing device 2) Next, the configuration of the information processing device 2 according to this exemplary embodiment will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of the information processing device 2. As shown in Fig. 3, the information processing device 2 includes an acquisition unit 21 and a learning unit 22.

[0034] (Acquisition part 21) The acquisition unit 21 acquires either color information or pigment information, and the feature amount of the waste plastic.

[0035] Here, the color information, pigment information, and feature quantities of waste plastics are substantially the same as those explained in the information processing device 1, and therefore redundant explanations will be omitted. However, although each piece of information acquired by the acquisition unit 21 is, for example, information referenced in the learning phase, this wording does not limit this exemplary embodiment.

[0036] (Study Section 22) The learning unit 22 learns a prediction model that predicts the correlation between pigment information, feature amounts of waste plastic, and color information, by referring to the information acquired by the acquisition unit 21.

[0037] As an example, the learning unit 22 (Prediction model 1) A prediction model that predicts color information indicating the color that will be obtained when a pigment indicated by the pigment information is applied to the waste plastic, based on pigment information and the feature quantities of the waste plastic. (Prediction model 2) A prediction model that predicts pigment information indicating pigments that will cause waste plastic to turn into the color indicated by the color information based on color information and the feature quantities of the waste plastic. The learning unit 22 may learn at least one of the above models. The learning unit 22 may also be configured to acquire ground-truth labels via the acquisition unit 21, and learn the prediction model by supervised learning with reference to the acquired ground-truth labels. As an example, the learning unit 22 may perform the learning process exemplified below.

[0038] (Learning process 1) As an example, the learning unit 22 inputs the learning data acquired by the acquisition unit 21 to a prediction model (prediction model 1) that predicts color information indicating the color obtained when a pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic. Pigment Information Feature quantities of waste plastic The training data includes The actual color (correct label) obtained when the pigment indicated by the pigment information is applied to the waste plastic. Then, the learning unit 22 updates one or more parameters of the prediction model 1 so that the color indicated by the prediction result output by the prediction model 1 to which the learning data has been input approaches the color indicated by the correct label.

[0039] (Learning process 2) As another example, the learning unit 22 inputs the learning data acquired by the acquisition unit 21 to a prediction model (prediction model 2) that predicts pigment information indicating pigments that will cause the waste plastic to have the color indicated by the color information based on color information and the feature amount of the waste plastic. Color information Feature quantities of waste plastic The training data includes Pigment information (correct label) indicating the actual pigment that will cause the waste plastic to have the color indicated by the color information Then, the learning unit 22 updates one or more parameters of the prediction model 2 so that the pigment information indicated by the prediction result output by the prediction model 2 to which the learning data has been input approaches the pigment information indicated by the correct label.

[0040] The specific configuration of the predictive model trained by the learning unit 22 does not limit this exemplary embodiment, but may be, for example, a deep learning model having multiple layers or other models. Furthermore, the predictive model may be trained by supervised learning, or may be trained by unsupervised learning or semi-supervised learning.

[0041] The prediction model learned by the learning unit 22 is stored in a storage unit (not shown) and is referred to in the inference phase. For example, the prediction model learned by the learning unit 22 is used in prediction processing by the prediction unit 12 included in the information processing device 1 described above.

[0042] (Effects of information processing device 2) As described above, in the information processing device 2, Acquire either color information or pigment information and the feature amount of the waste plastic, A prediction model that predicts the correlation between pigment information, waste plastic feature values, and color information is trained by referring to the acquired information. The following configuration is adopted.

[0043] In this way, the information processing device 2 learns a prediction model that predicts the correlation between pigment information, feature amounts of waste plastic, and color information by referring to the feature amounts of waste plastic, so it is possible to generate a prediction model that can suitably perform predictions regarding the color matching of plastic materials containing waste plastic. Therefore, with the above configuration, it is possible to suitably perform color matching predictions regarding plastic materials containing waste plastic.

[0044] (Flow of information processing method S2) Next, the flow of the information processing method S2 according to this exemplary embodiment will be described with reference to Fig. 4. Fig. 4 is a flow diagram showing the flow of the information processing method S2. As shown in Fig. 4, the information processing method S2 includes an acquisition process (acquisition step) S21 and a learning process (learning step) S22.

[0045] (Step S21) In step S21, the acquisition unit 21 acquires either color information or pigment information, and the feature amount of the waste plastic. A more specific description of the acquisition unit 21 has been given above, so a description thereof will be omitted here.

[0046] (Step S22) In step S22, the learning unit 22 learns a prediction model that predicts the correlation between the pigment information, the feature amount of the waste plastic, and the color information, by referring to the acquired information. The learning unit 22 has been described in more detail above, so a detailed description thereof will be omitted here.

[0047] (Effect of information processing method S2) As described above, in the information processing method S2, Acquire either color information or pigment information and the feature amount of the waste plastic, A prediction model that predicts the correlation between pigment information, waste plastic feature values, and color information is trained by referring to the acquired information. The above configuration provides the same effects as the information processing device 2.

[0048] Second Exemplary Embodiment A second exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs. Furthermore, each technology shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs.

[0049] (Configuration of information processing system 1A) The configuration of an information processing system 1A according to this exemplary embodiment will be described with reference to Fig. 5. Fig. 5 is a block diagram showing the configuration of the information processing system 1A. As shown in Fig. 5, the information processing system 1A includes an information processing device 100A and a server device 50 connected to the information processing device 100A via a network N. Here, the specific configuration of the network N does not limit this exemplary embodiment, but as an example, a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination of these networks can be used.

[0050] (Server device 50) As shown in FIG. 5 , the server device 50 includes a control unit 51, a database 52, and a communication unit 53. The communication unit 53 communicates with devices external to the server device 50. As an example, the communication unit 53 communicates with an information processing device 100A included in the information processing system 1A or other external devices (not shown) connected via the network N. The communication unit 53 transmits data supplied from the control unit 51 to the information processing device 100A, and supplies data received from the information processing device 100A to the control unit 51. Note that the data transmitted and received between the communication unit 53 and the information processing device 100A may include at least any one of waste plastic information WPI, waste plastic feature amount WPF, pigment information PI, and color information CI.

[0051] (Database 52) For example, waste plastic-related information WPRI, which is information related to waste plastic, is stored in the database 52. For example, the waste plastic-related information WPRI is information that can be generated by the control unit 10 included in the information processing device 100A and recorded in a database such as the database 52.

[0052] For example, the waste plastic-related information WPRI may include the contribution of the waste plastic feature WPF when the prediction unit 12 predicts the pigment information PI or the color information CI. For example, the contribution of the waste plastic feature WPF indicates the degree to which each of the multiple waste plastic feature WPF contributed when the prediction unit 12 predicted the pigment information PI or the color information CI. Here, the contribution of the waste plastic feature WPF may be expressed, for example, as a percentage of the total contribution, or as a real number ranging from 0 to 1, or as a value ranging from 0% to 100%. For example, the contribution of the waste plastic feature WPF may be calculated using a known technique from the prediction result PRED by the prediction unit 12. With the above-described configuration, for example, a user can suitably identify a waste plastic feature WPF that is more effective in reproducing certain pigment information PI or certain color information CI. As a specific example, when developing a product using waste plastic, a user can refer to the waste plastic-related information WPRI to suitably identify the waste plastic feature quantities that have a greater impact on the color development of the product.

[0053] Furthermore, as part of environmental protection efforts, there is a need to identify the amount of waste plastic used in products that use waste plastic in order to manage plastic emissions throughout the entire supply chain. For example, the waste plastic-related information WPRI may include information associating the waste plastic feature values ​​WPF input to the prediction model PM with the color information CI output from the prediction model PM at that time. In this case, a user may, for example, refer to the waste plastic-related information WPRI to identify the amount of each waste plastic material used in the product from the color information CI indicating the color of the product that uses waste plastic. Here, the amount of each waste plastic material used may be identified, for example, from information such as the mixing rate of a specific waste plastic material included in the waste plastic feature values ​​WPF. For example, the waste plastic-related information WPRI may also include information associating the waste plastic feature values ​​WPF input to the prediction model PM with the pigment information PI output from the prediction model PM at that time. In this case, a user may, for example, refer to the waste plastic-related information WPRI to identify the amount of each waste plastic material used in the product from the pigment information PI indicating the pigment composition of the product that uses waste plastic.

[0054] (control unit 51) The control unit 51 updates the waste plastic related information WPRI stored in the database 52.

[0055] As an example, the control unit 51 adds or updates information in the database 52 that associates the waste plastic feature WPF received from the information processing device 100A and input to the prediction model PM with the color information CI or pigment information PI output from the prediction model PM at this time.

[0056] Also, as an example, the control unit 51 may calculate the contribution rate of the waste plastic feature amount WPF from the prediction result PRED by the prediction unit 12. Then, as an example, the control unit 51 adds or updates, in the database 52, information that associates the calculated contribution rate of the waste plastic feature amount WPF with the prediction result PRED.

[0057] In this exemplary embodiment, the server device 50 is illustrated as a device separate from the information processing device 100A, but this does not limit the exemplary embodiment. The functions of the control device 51 of the server device 50 or the database update unit and contribution calculation unit in the control device 51 may be configured to be provided in the control device of the information processing device 100A. Similarly, the waste plastic-related information WPRI stored in the database 52 of the server device 50 may be stored in a memory unit of the information processing device 100A, and the waste plastic-related information WPRI may be updated by the information processing device 100A itself.

[0058] (Configuration of information processing device 100A) The configuration of an information processing device 100A according to this exemplary embodiment will be described with reference to Fig. 5. As shown in Fig. 5, the information processing device 100A includes a control unit 10, a storage unit 20, a communication unit 30, and an input / output unit 40.

[0059] (Communication unit 30) The communication unit 30 communicates with devices external to the information processing device 100A. As an example, the communication unit 30 communicates with a server device 50. The communication unit 30 transmits data supplied from the control unit 10 to the server device 50, and supplies data received from the server device 50 to the control unit 10.

[0060] (Input / output section 40) The input / output unit 40 is configured to include at least one of input / output devices such as a keyboard, a mouse, a display, a printer, and a touch panel. Alternatively, the input / output unit 40 may be configured to have input / output devices such as a keyboard, a mouse, a display, a printer, and a touch panel connected to it. In this configuration, the input / output unit 40 accepts various types of information input to the information processing device 100A from the connected input devices. Furthermore, the input / output unit 40 outputs various types of information to connected output devices under the control of the control unit 10. An example of the input / output unit 40 is an interface such as a USB (Universal Serial Bus).

[0061] (Storage unit 20) The storage unit 20 stores various data referenced by the control unit 10 and various data generated by the control unit 10. As an example, the storage unit 20 stores: ·Waste Plastic Information WPI Waste plastic feature vector WPF Pigment Information PI Color information CI ·Reference information RI Prediction result PRED Predictive Model PM is stored.

[0062] (Waste Plastic Information WPI) Here, the waste plastic information WPI is information about waste plastics that are the target of color matching. For example, the waste plastic information WPI includes the following: Information on the main raw materials of the target waste plastics Information on contaminants in the target waste plastics Information on whether the target waste plastic is made of a single material -Information about the color of the target waste plastic - Information showing the degree of pigment contamination in the target waste plastic (level of contamination) Information about the texture of the target waste plastic Information on the degree of cleaning of the target waste plastics Information on the traceability of the target waste plastics - Product name of the product containing the target waste plastic or classification information obtained by referencing the product category Whether the target waste plastic falls under the category of waste plastic material for which pigments are empirically ineffective Here, the "information regarding the texture of the material" may include at least one of the following: -Image of the target waste plastic - Information obtained by analyzing the captured image of the target waste plastic Here, the "information obtained by image analysis of the captured image" may be any of the following: - The result of classifying the captured image into one of multiple categories based on a rule base in the image analysis of the captured image. In the image analysis, the feature vector obtained by embedding the captured image into the feature space The image analysis and the derivation of the results may be performed by a feature generation unit 111, which will be described later.

[0063] In addition, the above "information about the texture of the material" includes Characteristics classified using onomatopoeia (sensual expressions, sensory expressions) such as smooth, rough, or silky may be included.

[0064] In addition, the "information regarding the above traceability" is as follows: Information on whether the waste plastic in question is classified as industrial waste or general waste may be included.

[0065] (Waste plastic feature value WPF) The waste plastic feature value WPF includes feature values ​​related to the waste plastic to be toned. As an example, the waste plastic feature value WPF may be generated by a feature value generation unit 111, which will be described later, but this is not intended to limit the present exemplary embodiment.

[0066] The waste plastic feature amount WPF may also be expressed as information obtained by processing the waste plastic information WPI so that it can be input to the prediction model PM used by the prediction unit 12. The waste plastic feature amount WPF will be described in detail later.

[0067] (Pigment Information PI) Pigment information PI includes: Pigment information referenced in the learning process by the learning unit 22 Pigment information referenced in the prediction process by the prediction unit 12 Here, at least a portion of the pigment information referenced in the learning process and at least a portion of the pigment information referenced in the prediction process may or may not overlap with each other. Note that the pigment information PI may also be referred to as pigment composition information or pigment composition.

[0068] As another example, the pigment information PI may include information about dyes.

[0069] (Color Information CI) Color information CI includes: Color information referenced in the learning process by the learning unit 22 Color information referenced in the prediction process by the prediction unit 12 Here, at least a portion of the color information referenced in the learning process and at least a portion of the color information referenced in the prediction process may or may not overlap with each other. Note that the color information CI may also be referred to as generated color information or generated color.

[0070] (Reference information RI) The reference information RI is, for example, information referenced by the feature generating unit 111 described later, and may include information on each color obtained by applying each of a plurality of types of pigments to each of a plurality of types of waste plastic. Information showing the effectiveness (efficacy, color development) of one or more pigments for one or more types of waste plastics For example, a Reference Information RI might include: - For waste plastics of type P1, the color development by pigment D1 is about 0.8 compared to virgin material, but the color development by pigment D2 is about 1.2 compared to virgin material. For this reason, the reference information RI may be referred to as effective color information. However, this name does not limit this exemplary embodiment. A more specific description of the reference information RI will be given later.

[0071] (Prediction result PRED) The prediction result PRED is information indicating the prediction result by the prediction unit 12. Specific examples of information included in the prediction result will be described later.

[0072] (Prediction Model PM) The prediction model PM is a prediction model that is learned by the learning unit 22 and used by the prediction unit 12. The prediction model PM is A prediction model (prediction model PM1) that predicts color information that indicates the color that will be obtained when the pigment indicated in the pigment information is applied to the waste plastic, based on the pigment information and the feature values ​​of the waste plastic. A prediction model (Prediction Model PM2) that predicts pigment information indicating the pigments that will cause the waste plastic to turn into the color indicated by the color information and the feature values ​​of the waste plastic, based on the color information and the feature values ​​of the waste plastic. The prediction model PM may have a configuration including at least one of the above. The prediction model PM has a plurality of model parameters, and at least one of the plurality of model parameters is updated by a learning process by the learning unit 22. Note that the specific configuration of the prediction model PM does not limit this exemplary embodiment, and as an example, the prediction model PM may be a deep learning model having a plurality of layers, or other models. Furthermore, the prediction model may be a model trained by supervised learning, or may be a model trained by unsupervised learning or semi-supervised learning.

[0073] (Control unit 10) 5, the control unit 10 includes an acquisition unit 11, a prediction unit 12, an output unit 13, a registration unit 14, and a learning unit 22. Here, the acquisition unit 11 also has the same functions as the acquisition unit 11 included in the information processing device 1 described in exemplary embodiment 1 and the acquisition unit 21 included in the information processing device 2 described in exemplary embodiment 1, and therefore the acquisition unit 11 may also be referred to as the acquisition unit 11(21).

[0074] (Acquisition part 11) The acquisition unit 11 acquires either color information or pigment information, and feature quantities of the waste plastic, similarly to the acquisition unit 11 according to the first exemplary embodiment. Here, the color information acquired by the acquisition unit 11 may be, for example, target color information indicating a target color. Furthermore, the pigment information acquired by the acquisition unit 11 may be, for example, pigment composition candidate information indicating usable pigment compositions. For example, this information is referenced in the prediction process by the prediction unit 12. Furthermore, the pigment information acquired by the acquisition unit 11 may include, for example, information on dyes.

[0075] Similarly to the acquisition unit 21 according to the first exemplary embodiment, the acquisition unit 11 may be configured to acquire either color information or pigment information, and feature quantities of waste plastic, as information to be referenced in the learning phase. For this reason, the acquisition unit 11 may also be referred to as the acquisition unit 11(21). The acquisition unit 11 may also be configured to further acquire ground-truth labels to be referenced in the learning phase. The acquisition unit 11 may also include a feature generation unit 111, as shown in FIG. 5.

[0076] The data acquired by the acquisition unit 11 may be, for example: Numerical data, and Recognition results of image data including at least one of color information, pigment information, and images of waste plastic At least one of the above may be used.

[0077] As another example, the data acquired by the acquiring unit 11 may be input by a user via the input / output unit 40. As another example, the acquiring unit 11 may acquire data stored in a database.

[0078] (Feature generation unit 111) The feature generation unit 111 generates a waste plastic feature WPF for the target waste plastic by referring to the waste plastic information WPI for the target waste plastic acquired by the acquisition unit 11. The feature generation process by the feature generation unit 111 includes, for example, any of the following processes.

[0079] (Process 1-1) Processing to include the numerical information contained in the waste plastic information WPI as numerical information in the waste plastic feature quantity WPF (Process 1-2) This process converts non-numerical information such as classification information and qualitative information contained in the waste plastic information WPI into numerical information or one-hot vectors, and includes them in the waste plastic feature quantity WPF.

[0080] (Process 2-1) Based on physicochemical assumptions, the process produces the following: A process to generate waste plastic feature quantities by applying linear operations (in other words, generating linear terms) to the numerical information included in the waste plastic information WPI or the numerical information generated by the above process 1-2. A process of generating waste plastic feature quantities by applying a nonlinear operation (in other words, generating a nonlinear term) to the numerical information included in the waste plastic information WPI or the numerical information generated by the above process 1-2 (here, the nonlinear operation includes: A process of generating cross-variable terms by multiplying multiple different types of variables (numerical information) Processing to generate nonlinear terms using quadratic or higher power functions, logarithmic functions, exponential functions, etc. etc.) - Processing to generate nonlinear terms using the qualitative information (qualitative data) contained in the waste plastic information WPI as arguments (qualitative data can be useful additional information when adjusting changes in color mixing) A process to generate a term that depends on the mixing rate of a specific waste plastic material in the target waste plastic (for example, if the specific waste plastic material in question worsens the effect of the color, a process to generate a term such as min(0.5, exp(-P)) using the mixing rate P of the specific waste plastic material in the target waste plastic) The above phrase "based on physicochemical assumptions" refers to, for example, using a function based on physicochemical laws or empirical rules as a function including the linear or nonlinear term when generating the linear or nonlinear term. However, this example does not limit the present exemplary embodiment. (Process 2-2) A process that generates each item listed in Process 2-2 above without making any physicochemical assumptions.

[0081] (Process 3) A process of generating a correction term to be referenced when deriving color information or pigment information in the prediction process by the prediction unit 12 or the learning process by the learning unit 22 (for example, A process for generating correction terms that are referenced when calculating color information in the prediction process or learning process, and that are used to correct the effect of color (the mixing of colors) on target waste plastics that contain specific waste plastic materials.

[0082] (Prediction Section 12) The prediction unit 12, like the prediction unit 12 according to the first exemplary embodiment, uses a trained prediction model to predict the other of the color information and the pigment information from the information acquired by the acquisition unit 11. Here, the prediction model is, for example, a prediction model that has learned the correlation between pigment information, feature quantities of waste plastic, and color information. To give a more specific example, the prediction unit 12 uses, as the prediction model, (Prediction model 1) A prediction model that predicts color information indicating the color that will be obtained when a pigment indicated by the pigment information is applied to the waste plastic, based on pigment information and the feature quantities of the waste plastic. (Prediction model 2) A prediction model that predicts pigment information indicating pigments that will cause waste plastic to turn into the color indicated by the color information based on color information and the feature quantities of the waste plastic. The prediction unit 12 may use any one of the prediction models. (Prediction process 1) A process of predicting color information indicating a color corresponding to the pigment information acquired by the acquisition unit 11 from the pigment information and the feature amount of the waste plastic. (Prediction process 2) A process of predicting pigment information indicating a pigment corresponding to the color information from the color information acquired by the acquisition unit 11 and the feature amount of the waste plastic. At least one of the following is executed.

[0083] Here, any combination of the above-described prediction models 1 and 2 and prediction processes 1 and 2 may be adopted. To give a specific example, the prediction unit 12 may perform any of the following four types of prediction processes.

[0084] (Example 1-1: 1 prediction model x 1 prediction process) The pigment information and the feature amount of the waste plastic acquired by the acquisition unit 11 are A prediction model (prediction model 1 above) that predicts color information indicating the color that will be obtained when the pigment indicated in the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic. A process of predicting color information indicating a color corresponding to the pigment information acquired by the acquisition unit 11 by inputting the information into (Example 1-2: Prediction model 1 x prediction process 2) By referring to the color information acquired by the acquisition unit 11 and the feature amount of the waste plastic, A prediction model (prediction model 1 above) that predicts color information indicating the color that will be obtained when the pigment indicated in the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic. A process of predicting pigment information indicating a pigment corresponding to the color information acquired by the acquisition unit 11 using the In this case, as an example, the prediction unit 12 inputs each of multiple candidate pigment information into the prediction model 1, predicts the color corresponding to each candidate, and performs a search process so that the color approaches the color indicated by the color information acquired by the acquisition unit 11, thereby performing a process to predict pigment information indicating the pigment corresponding to the color information acquired by the acquisition unit 11.

[0085] (Example 2-1: 2 prediction models x 1 prediction process) By referring to the pigment information and the feature amount of the waste plastic acquired by the acquisition unit 11, A prediction model that predicts pigment information indicating the pigment that will cause the waste plastic to turn into the color indicated by the color information and the feature values ​​of the waste plastic (prediction model 2 above) A process of predicting color information indicating a color corresponding to the pigment information acquired by the acquisition unit 11 using the In this case, as an example, the prediction unit 12 predicts pigment information corresponding to each candidate by inputting each of multiple candidate color information into the prediction model 1, and performs a search process so that the pigment information approaches the pigment information acquired by the acquisition unit 11, thereby performing a process to predict color information indicating the color corresponding to the pigment information acquired by the acquisition unit 11.

[0086] (Example 2-2: Prediction model 2 x prediction process 2) The color information and the feature amount of the waste plastic acquired by the acquisition unit 11 are A prediction model that predicts pigment information indicating the pigment that will cause the waste plastic to turn into the color indicated by the color information and the feature amount of the waste plastic (prediction model 2 above) A process of predicting pigment information indicating a pigment corresponding to the color information acquired by the acquisition unit 11 by inputting the information into The specific configuration of the prediction model used by the prediction unit 12 does not limit this exemplary embodiment, but may be, for example, a deep learning model having multiple layers or other models. Furthermore, the prediction model may be trained by supervised learning, or may be trained by unsupervised learning or semi-supervised learning.

[0087] Further, as an example, the prediction unit 12 The color obtained when the pigment indicated in the pigment information is applied to virgin plastic or a mixed plastic containing virgin plastic and waste plastic, and A pigment that makes virgin plastic or a mixed plastic containing virgin plastic and waste plastic the color indicated by the color information. Here, the mixed plastic may be, for example, a mixture of virgin plastic and waste plastic in any ratio.

[0088] The prediction result by the prediction unit 12 is, for example, - Presented to the user via the output unit 13, The color information is provided to an external manufacturing device via the communication unit 30 and is used to adjust the color of plastic materials including waste plastics.

[0089] (Output section 13) The output unit 13 outputs the prediction result by the prediction unit 12. As an example, the output unit 13 may visually present presentation information including the prediction result by the prediction unit 12 to the user.

[0090] (Registration Section 14) The registration unit 14 registers information including at least one of the prediction result by the prediction unit 12 and information referenced by the prediction unit 12 in a database.

[0091] Specific examples of prediction results by the prediction unit 12 include: Color information CI indicating the color corresponding to the pigment information PI acquired by the acquisition unit 11 Pigment information PI indicating the pigment corresponding to the color information CI acquired by the acquisition unit 11 Examples include:

[0092] Specific examples of information that the prediction unit 12 refers to include: Pigment information PI showing candidate pigments Color information CI showing the target color Waste plastic feature vector WPF Examples include:

[0093] (Study Section 22) The learning unit 22 learns a prediction model that predicts the correlation between pigment information, feature amounts of waste plastic, and color information, by referring to the information acquired by the acquisition unit 21.

[0094] As an example, the learning unit 22 (Prediction model 1) A prediction model that predicts color information indicating the color that will be obtained when a pigment indicated by the pigment information is applied to the waste plastic, based on pigment information and the feature quantities of the waste plastic. (Prediction model 2) A prediction model that predicts pigment information indicating pigments that will cause waste plastic to turn into the color indicated by the color information based on color information and the feature quantities of the waste plastic. The learning unit 22 may learn at least one of the above models. The learning unit 22 may also be configured to acquire ground-truth labels via the acquisition unit 21, and learn the prediction model by supervised learning with reference to the acquired ground-truth labels. An example of the learning process performed by the learning unit 22 will be described later with reference to FIGS. 6 to 8.

[0095] The specific configuration of the predictive model trained by the learning unit 22 does not limit this exemplary embodiment, but may be, for example, a deep learning model having multiple layers or other models. Furthermore, the predictive model may be trained by supervised learning, or may be trained by unsupervised learning or semi-supervised learning.

[0096] The prediction model learned by the learning unit 22 is stored in the storage unit 20, for example, and is referred to in the inference phase. As an example, the prediction model learned by the learning unit 22 is used in the prediction process by the prediction unit 12 described above.

[0097] (Example of learning process by learning unit 22) A specific example of the learning process by the learning unit 22 will be described below with reference to FIGS.

[0098] (Learning process example 1) Fig. 6 is a diagram showing a learning process example 1 by the learning unit 22. As shown in Fig. 6, this example includes an acquisition process S21 and a generated color learning process S22A. Here, the acquisition process S21 of this example includes a waste plastic information reception process S211, a waste plastic feature amount generation process S212A, and a pigment composition reception process S213A.

[0099] (Waste plastic information reception process S211) In the waste plastic information reception process S211, the acquisition unit 21 acquires, for example, waste plastic information WPI related to the target waste plastic. Here, the waste plastic information WPI may include, for example, information related to waste plastic, information related to virgin plastic, or information related to mixed plastics including virgin plastic and waste plastic.

[0100] (Waste plastic feature generation processing S212A) In the waste plastic feature generation process S212A, the feature generation unit 111, as an example, references the waste plastic information WPI regarding the target waste plastic acquired by the acquisition unit 21, and generates a waste plastic feature WPF regarding the target waste plastic.

[0101] (Pigment composition reception process S213A) In the pigment composition reception process S213A, the acquisition unit 21 acquires, as an example, pigment information PI, which is pigment composition information to be applied to the waste plastic.

[0102] (Generated color learning process S22A) In the generated color learning process S22A, the learning unit 22 inputs, as an example, the learning data acquired by the acquisition unit 21 to a prediction model (model PM1) that predicts color information CI indicating the color obtained when the pigment indicated by the pigment information PI is applied to the waste plastic from the pigment information PI and the waste plastic feature amount WPF. Here, the learning data includes Pigment Information PI Waste plastic feature vector WPF The training data includes The actual color (correct label) obtained when the pigment indicated by the pigment information PI is applied to the waste plastic. Then, the learning unit 22 updates one or more parameters of the prediction model so that the color indicated by the prediction result PRED output by the prediction model to which the learning data has been input approaches the color indicated by the correct label.

[0103] (Learning process example 2) FIG. 7 is a diagram illustrating a second example of the learning process performed by the learning unit 22. In FIG.

[0104] 7, this example includes an acquisition process S21 and a pigment composition learning process S22B. Here, the acquisition process S21 of this example includes a waste plastic information reception process S211, a waste plastic feature generation process S212A, and a generated color reception process S213B. Note that in this example, only the generated color reception process S213B and the pigment composition learning process S22B will be described; the other processes are the same as those described in the above learning process example, and therefore will not be described here.

[0105] (Generated color reception process S213B) In the resulting color receiving process S213B, the acquisition unit 21 acquires color information CI, which is, for example, information on the resulting color of the waste plastic.

[0106] (Pigment composition learning process S22B) In the pigment composition learning process S22B, the learning unit 22 inputs the learning data acquired by the acquisition unit 21 to a prediction model (model PM2) that predicts pigment information PI indicating pigments that will cause the waste plastic to have the color indicated by the color information CI from the color information CI and the waste plastic feature amount WPF, for example. Color information CI Waste plastic feature vector WPF The training data includes Pigment information (correct label) indicating the actual pigment that will cause the waste plastic to have the color indicated by the color information CI Then, the learning unit 22 updates one or more parameters of the prediction model so that the pigment information indicated by the prediction result PRED output by the prediction model to which the learning data has been input approaches the pigment information indicated by the correct label.

[0107] (Learning process example 3) FIG. 8 is a diagram illustrating a learning process example 3 performed by the learning unit 22. In FIG.

[0108] 8, this example includes an acquisition process S21 and a generated color learning process S22C. Here, the acquisition process S21 of this example includes a waste plastic information reception process S211, a waste plastic feature amount generation process S212C, an effective color information acquisition process S214, and a pigment composition reception process S213A. Note that in this example, only the waste plastic feature amount generation process S212C, the effective color information acquisition process S214, and the generated color learning process S22C will be described. The other processes are the same as the processes described in the above learning process example, so description thereof will be omitted here.

[0109] (Acceptable color information acquisition process S214) In the effective color information acquisition process S214, the acquisition unit 21 acquires effective color information. Here, the effective color information is an example of the reference information RI described above. For example, the effective color information may include: - Information on each color obtained by actually applying each of several types of pigments to each of several types of waste plastics Information showing the effectiveness (efficacy, color development) of one or more pigments for one or more types of waste plastics For example, the effective color information includes: - For waste plastics of type P1, the color development by pigment D1 is about 0.8 compared to virgin material, but the color development by pigment D2 is about 1.2 compared to virgin material. It may include information such as:

[0110] The above-mentioned effective color information may be stored in the storage unit 20 or the database 52, for example, and may be accessible from other external devices connected to the information processing system 1A via the network N.

[0111] (Waste plastic feature generation processing S212C) In the waste plastic feature generation process S212C, the feature generation unit 111, as an example, generates a waste plastic feature WPF for the target waste plastic by referring to the waste plastic information WPI for the target waste plastic acquired by the acquisition unit 21 and the effective color information including information on each color obtained by actually applying each of multiple types of pigments to each of multiple types of waste plastic.

[0112] (Generated color learning process S22C) In the generated color learning process S22C, the learning unit 22 inputs the learning data acquired by the acquisition unit 21 to a prediction model (model PM3) that predicts color information CI indicating the color obtained when the pigment indicated by the pigment information PI is applied to the waste plastic, based on the waste plastic feature amount WPF generated by referring to the pigment information PI, the waste plastic information WPI, and the effective color information, for example. Here, the learning data includes Pigment Information PI Waste plastic feature value WPF generated by referring to waste plastic information WPI and effective color information The training data includes The actual color (correct label) obtained when the pigment indicated by the pigment information PI is applied to the waste plastic. Then, the learning unit 22 updates one or more parameters of the prediction model so that the color indicated by the prediction result PRED output by the prediction model to which the learning data has been input approaches the color indicated by the correct label.

[0113] As an example, model PM3 may be a predictive model that predicts color information CI, i.e., effective color information, which indicates the color obtained by actually applying each of multiple types of pigments to each of multiple types of waste plastics.

[0114] As another example, the correct label associated with the learning data may be the color obtained by actually applying each of a plurality of types of pigment to each of a plurality of types of waste plastic, i.e., effective color information.

[0115] Also, as an example, the concentration of the pigment contained in the mixture in which the pigment is applied to the waste plastic may be determined arbitrarily.

[0116] (Example of prediction process by prediction unit 12) A specific example of the prediction process by the prediction unit 12 will be described below with reference to FIGS.

[0117] (Prediction processing example 1) FIG. 9 is a diagram showing a first example of a prediction process performed by the prediction unit 12. As shown in FIG. 9, this example includes an acquisition process S11, a prediction process S12, and a pigment composition output process S13A. Here, the acquisition process S11 of this example includes a waste plastic information reception process S111, a waste plastic feature value generation process S112A, a pigment composition candidate generation process S113, and a target color information reception process S114. Furthermore, the prediction process S12 of this example includes a generated color prediction process S121A and a color information comparison process S122.

[0118] (Waste plastic information reception process S111) In the waste plastic information reception process S111, the acquisition unit 11 acquires, as an example, waste plastic information WPI relating to the target waste plastic.

[0119] (Waste plastic feature generation processing S112A) In the waste plastic feature generation process S112A, the feature generation unit 111, as an example, references the waste plastic information WPI regarding the target waste plastic acquired by the acquisition unit 11, and generates a waste plastic feature WPF regarding the target waste plastic.

[0120] (Pigment composition candidate generation process S113) In the pigment composition candidate generation process S113, the acquisition unit 11 generates, for example, pigment information PI, which is pigment composition candidate information indicating usable pigment compositions. Here, for example, the pigment information PI generated by the acquisition unit 11 may be information on multiple pigment composition candidates. Note that, for example, the acquisition unit 11 may acquire pigment information PI indicating candidate pigments.

[0121] (Target color information reception process S114) In the target color information reception process S114, the acquisition unit 11 acquires, for example, color information CI indicating a target color. Here, the color information CI acquired by the acquisition unit 11 is, for example, target color information indicating a target color.

[0122] (Generated color prediction process S121A) In the generated color prediction process S121A, the prediction unit 12, for example, uses a prediction model to predict color information CI indicating a color corresponding to the pigment information PI from the pigment information PI and the waste plastic feature value WPF acquired by the acquisition unit 11. At this time, the prediction unit 12, for example, uses a trained model, i.e., trained model PM1, as the prediction model, which predicts color information CI indicating a color obtained when the pigment indicated by the pigment information PI is applied to the waste plastic from the pigment information PI and the waste plastic feature value WPF. In this case, for example, the prediction unit 12 inputs each of multiple candidate pigment information PI into model PM1, thereby predicting color information CI corresponding to each candidate.

[0123] (Color information comparison process S122) In the color information comparison process S122, the prediction unit 12, for example, compares the color information CI predicted using the model PM1 with the color information CI that is the target color information acquired by the acquisition unit 11. Then, for example, the prediction unit 12 performs a search process so that the predicted color information CI approaches the color information CI that is the target color information acquired by the acquisition unit 11, thereby further predicting pigment information PI that indicates the pigment composition corresponding to the color information CI that is the target color information acquired by the acquisition unit 11.

[0124] (Pigment composition output processing S13A) In the pigment composition output process S13A, the output unit 13 outputs, as an example, pigment information PI included in the prediction result PRED by the prediction unit 12, that is, the pigment composition.

[0125] (Display example 1 of output result by output unit 13) FIG. 10 is a diagram showing a display example 1 of the output result by the output unit 13 in the pigment composition output process S13A described with reference to FIG. 9. As an example, the output unit 13 visually presents presentation information including the prediction result PRED by the prediction unit 12 to the user via the input / output unit 40. Display example 1 shown in FIG. 10 is a diagram showing a display example 1 of the output result by the output unit 13 in the pigment composition output process S13A described with reference to FIG. 9. -ID assigned to each waste plastic material, · Color information CI, which is information about the target color, and Pigment information PI that shows the pigment composition that will turn waste plastic into the target color 10 shows an example of how the amount of pigment information used is expressed by weight, but this is not intended to limit the present example. For example, the amount of pigment information used may be shown as a percentage of the total weight of the waste plastic used.

[0126] (Prediction processing example 2) FIG. 11 is a diagram showing a second example of a prediction process performed by the prediction unit 12. As shown in FIG. 11, this example includes an acquisition process S11, a prediction process S12, and a pigment composition output process S13A. The acquisition process S11 of this example includes a waste plastic information reception process S111, a waste plastic feature value generation process S112A, and a target color information reception process S114. The prediction process S12 of this example includes a pigment composition prediction process S121B. In this example, only the pigment composition prediction process S121B will be described; the other processes are similar to those described in the above-described prediction process example, and therefore will not be described again.

[0127] (Pigment composition prediction processing S121B) In the pigment composition prediction process S121B, the prediction unit 12 uses, as an example, a prediction model to predict pigment information PI indicating the pigment corresponding to the color information CI from the color information CI and the waste plastic feature amount WPF acquired by the acquisition unit 11. At this time, as an example, the prediction unit 12 uses, as the prediction model, a trained model that predicts, from the color information CI and the waste plastic feature amount WPF, pigment information PI indicating the pigment that will cause the waste plastic to have the color indicated by the color information CI, i.e., a trained model PM2.

[0128] In other words, as an example, the prediction unit 12 predicts pigment information PI indicating the pigment corresponding to the color information CI acquired by the acquisition unit 11 by inputting the color information CI acquired by the acquisition unit 11 and the waste plastic feature WPF into the model PM2.

[0129] (Prediction processing example 3) FIG. 12 is a diagram illustrating a third example of a prediction process performed by the prediction unit 12. As shown in FIG. 12, this example includes an acquisition process S11, a prediction process S12, and a pigment composition output process S13A. The acquisition process S11 of this example includes a waste plastic information reception process S111, a waste plastic feature value generation process S112C, a pigment composition candidate generation process S113, a target color information reception process S114, and an effective color information acquisition process S115. The prediction process S12 of this example includes a generated color prediction process S121C and a color information comparison process S122. Note that this example only describes the waste plastic feature value generation process S112C, the effective color information acquisition process S115, and the generated color prediction process S121C. The other processes are similar to those described in the above-described prediction process examples, and therefore will not be described here.

[0130] (Acceptable color information acquisition process S115) In the effective color information acquisition process S115, the acquisition unit 11 acquires effective color information. Here, the effective color information is an example of the above-mentioned reference information RI. Details of the effective color information have been described above, so a detailed description will be omitted here.

[0131] (Waste plastic feature generation processing S112C) In the waste plastic feature generation process S112C, the feature generation unit 111, as an example, generates a waste plastic feature WPF for the target waste plastic by referring to the waste plastic information WPI for the target waste plastic acquired by the acquisition unit 21 and the effective color information including information on each color obtained by applying each of multiple types of pigments to each of multiple types of waste plastic.

[0132] (Generated color prediction process S121C) In the generated color prediction process S121C, the prediction unit 12, for example, uses a prediction model to predict color information CI indicating a color corresponding to the pigment information PI from the pigment information PI acquired by the acquisition unit 11 and the waste plastic feature value WPF generated with reference to the waste plastic information WPI and effective color information. In this case, the prediction unit 12 uses, for example, a trained model PM3 as the prediction model. This trained model predicts color information CI indicating a color obtained when the pigment indicated by the pigment information PI is applied to the waste plastic from the pigment information PI and the waste plastic feature value WPF generated with reference to the waste plastic information WPI and effective color information. In this case, for example, the prediction unit 12 inputs each of multiple candidate pigment information PI into the model PM3 to predict color information CI corresponding to each candidate.

[0133] As an example, the prediction unit 12 may use the model PM3 to predict color information CI including effective color information corresponding to the pigment information PI from the pigment information PI acquired by the acquisition unit 11 and the waste plastic feature WPF generated by referring to the waste plastic information WPI and effective color information.

[0134] Also, as an example, the concentration of the pigment contained in the mixture in which the pigment is applied to the waste plastic may be determined arbitrarily.

[0135] Also, as an example, the prediction result PRED including the effective color information predicted by the prediction unit 12 may be stored in a storage medium such as the storage unit 20. Then, as an example, the prediction unit 12 may use a prediction model to further predict color information CI from the waste plastic feature amount WPF generated by referring to the pigment information PI, the waste plastic information WPI, and the effective color information included in the prediction result PRED.

[0136] (Prediction processing example 4) FIG. 13 is a diagram showing a fourth example of a prediction process performed by the prediction unit 12. As shown in FIG. 13, this example includes an acquisition process S11, a prediction process S12, an output process S13, a generated color prediction process S15, and a comparison information generation process S16. The acquisition process S11 of this example includes a waste plastic information reception process S111, a waste plastic feature value generation process S112A, a pigment composition candidate generation process S113, and a target color information reception process S114. The prediction process S12 of this example includes a generated color prediction process S121A and a color information comparison process S122. The output process S13 of this example includes a pigment composition output process S13A and a comparison information output process S13B. In this example, only the generated color prediction process S15, the contrast information generation process S16, and the contrast information output process S13B will be described, and the other processes are the same as those described in the above prediction process example, so their description will be omitted here.

[0137] (Generated color prediction process S15) In the resulting color prediction process S15, the prediction unit 12 predicts, using a prediction model, color information CI indicating a color corresponding to the pigment information PI from the pigment information PI acquired by the acquisition unit 11. Here, the prediction unit 12 predicts, using model PM1, color information CI indicating a color obtained when the pigment indicated by the pigment information PI is applied to virgin plastic. Furthermore, the prediction unit 12 further predicts, using model PM2, pigment information PI indicating a pigment that will cause virgin plastic to have the color indicated by the color information CI.

[0138] (Comparative information generation process S16) In the contrast information generation process S16, the prediction unit 12, for example, uses color information CI obtained when the pigment indicated by the pigment information PI is applied to waste plastic in the generated color prediction process S121A, and color information CI obtained when the pigment indicated by the pigment information PI is applied to virgin plastic in the generated color prediction process S15, to further predict color information CI indicating the color obtained when the pigment indicated by the pigment information PI is applied to mixed plastic containing virgin plastic and waste plastic. Then, for example, the prediction unit 12 - Color information CI obtained when the pigment indicated by the pigment information PI is applied to virgin plastic, -Color information CI obtained when the pigment indicated by the pigment information PI is applied to a mixed plastic containing virgin plastic and waste plastic; Contrasting information is generated by comparing the above.

[0139] Further, as an example, the prediction unit 12 may further predict pigment information PI indicating pigments that will cause mixed plastics containing virgin plastics and waste plastics to become the target color indicated by the color information CI, using pigment information PI indicating pigments that will cause waste plastics to become the target color indicated by the color information CI obtained in the generated color prediction process S121A and pigment information PI indicating pigments that will cause virgin plastics to become the target color indicated by the color information CI obtained in the generated color prediction process S15. pigment information PI indicating pigments that will make virgin plastics have the target color indicated by color information CI; Pigment information PI indicating a pigment that makes a mixed plastic containing virgin plastic and waste plastic have a target color indicated by the color information CI; Alternatively, comparison information may be generated that is information obtained by comparing the above.

[0140] (Comparative information output processing S13B) In the comparison information output process S13B, the output unit 13 outputs the comparison information generated by the prediction unit 12, for example.

[0141] (Display example 2 of output result by output unit 13) 14 is a diagram showing a display example 2 of the output result by the output unit 13 in the pigment composition output process S13A and the contrast information output process S13B described with reference to FIG. 13. As an example, the output unit 13 visually presents presentation information including the prediction result PRED by the prediction unit 12 to the user via the input / output unit 40. Display example 2 shown in FIG. 14 is a diagram showing a display example 2 of the output result by the output unit 13 in the pigment composition output process S13A and the comparison information output process S13B described with reference to FIG. 13. As an example, the output unit 13 visually presents presentation information including the prediction result PRED by the prediction unit 12 to the user via the input / output unit 40. -ID assigned to each waste plastic material, - ID of virgin plastic to be mixed with the waste plastic · Color information CI, which is information on the target color; Pigment information PI, which indicates the pigment composition that will turn waste plastic into the target color; Pigment information PI, which indicates the pigment composition that results in the target color of virgin plastic material (virgin material), and Pigment information PI that indicates the pigment composition so that mixed plastic materials (mixtures) containing virgin plastic materials and waste plastic materials will have the target color. This is an example of the display.

[0142] 14, the amount of pigment information used is shown by weight, but this is not a limitation of this example. For example, the amount of pigment information used may be shown as a percentage of the total weight of the waste plastic used.

[0143] (Prediction processing example 5) FIG. 15 illustrates a fifth example of a prediction process performed by the prediction unit 12. As shown in FIG. 15, this example includes an acquisition process S11, a prediction process S12, an output process S13, a generated color prediction process S15, and a comparison information generation process S16. The acquisition process S11 of this example includes a waste plastic information reception process S111, a waste plastic feature value generation process S112A, a pigment composition candidate generation process S113, a target color information reception process S114, and a blending instruction reception process S116. The prediction process S12 of this example includes a generated color prediction process S121A and a color information comparison process S122. The output process S13 of this example includes a pigment composition output process S13A and a comparison information output process S13B. In this example, only the blending instruction reception process S116 will be described; the other processes are similar to those described in the above-described prediction process examples, and therefore will not be described here.

[0144] (Mixing instruction reception process S116) In the blending instruction receiving process S116, the acquisition unit 11 acquires, from a user, an instruction regarding the blending ratio of virgin plastic and waste plastic in the mixed plastic, for example. Here, as an example, the blending ratio of virgin plastic and waste plastic in the mixed plastic may be determined arbitrarily. Note that in the pigment composition candidate generation process S113 described below, as an example, the acquisition unit 11 may generate pigment information PI, which is pigment composition candidate information indicating usable pigment compositions, according to the blending ratio of virgin plastic and waste plastic in the mixed plastic.

[0145] (Effects of information processing device 100A) As described above, in the information processing device 100A, obtaining said pigment information indicating candidate pigments; Predicting color information indicating a color corresponding to the pigment information from the pigment information and the feature amount of the waste plastic. Therefore, in addition to the effects of the information processing device 1, the information processing device 100A can also provide the effect of being able to suitably predict toning of plastic materials including waste plastics from pigment information.

[0146] In addition, in the information processing device 100A, obtaining the color information indicating a target color; Predicting pigment information indicating the pigment corresponding to the color information from the color information and the feature amount of the waste plastic. Therefore, in addition to the effects of the information processing device 1, the information processing device 100A can also provide the effect of being able to suitably predict toning of plastic materials including waste plastics from color information.

[0147] In addition, in the information processing device 100A, Generate the feature quantity of the waste plastic by referring to the information about the waste plastic. Therefore, in addition to the effects of the information processing device 1, the information processing device 100A can also provide the effect of converting information about waste plastics, including non-numerical information, so that it can be referenced by a machine learning model.

[0148] In addition, in the information processing device 100A, The feature quantity of the waste plastic is generated by further referring to reference information including information on each color obtained by applying each of a plurality of types of pigments to each of a plurality of types of waste plastic. Therefore, according to the information processing device 100A, in addition to the effect achieved by the information processing device 1, it is possible to perform color matching prediction by referring to information on each color obtained by actually applying pigments to waste plastics.

[0149] In addition, in the information processing device 100A, - Output the prediction results by the prediction method Therefore, according to the information processing device 100A, in addition to the effects of the information processing device 1, the effect of being able to conveniently check the prediction result can be obtained.

[0150] In addition, in the information processing device 100A, The color obtained when the pigment indicated in the pigment information is applied to virgin plastic or a mixed plastic containing virgin plastic and waste plastic, and A pigment that makes virgin plastic or a mixed plastic containing virgin plastic and waste plastic the color indicated by the color information. Further predicting at least one of - Visually present the information including the prediction results from the prediction means to the user. Therefore, according to the information processing device 100A, in addition to the effect achieved by the information processing device 1, the effect of being able to predict toning according to the mixture ratio of virgin plastic and waste plastic can be obtained.

[0151] In addition, in the information processing device 100A, Registering information including at least one of the prediction results by the prediction means and information referenced by the prediction means in the database. Therefore, in addition to the effects of the information processing device 1, the information processing device 100A has the effect of being able to suitably use the prediction result by the prediction means and the information referred to by the prediction means.

[0152] In addition, in the information processing device 100A, A trained model that predicts color information indicating the color that will be obtained when a pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic is used as the prediction model. Therefore, according to the information processing device 100A, in addition to the effects of the information processing device 1, it is possible to obtain an effect of being able to perform color matching prediction using a model that predicts color information from pigment information and feature amounts of waste plastics.

[0153] In addition, in the information processing device 100A, A trained model that predicts pigment information indicating pigments that will cause the waste plastic to have the color indicated by the color information and the feature values ​​of the waste plastic, is used as the prediction model. Therefore, according to the information processing device 100A, in addition to the effects of the information processing device 1, it is possible to obtain an effect of being able to perform color matching prediction using a model that predicts pigment information from color information and feature amounts of waste plastics.

[0154] Third Exemplary Embodiment A third exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technology shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0155] (Configuration of information processing system 1B) The configuration of an information processing system 1B according to this exemplary embodiment will be described with reference to Fig. 16. Fig. 16 is a block diagram showing the configuration of the information processing system 1B. As shown in Fig. 16, the information processing system 1B includes an information processing device 100B and a server device 50 connected to the information processing device 100B via a network N. The configuration of the information processing system 1B, other than the information processing device 100B, is the same as that of the information processing system 1A according to the second exemplary embodiment.

[0156] (Configuration of information processing device 100B) 16, the information processing device 100B does not include the learning unit 22 among the components included in the information processing device 100A according to exemplary embodiment 2. The other components are the same as those of the information processing device 100A.

[0157] In this way, the information processing device 100B: An acquisition means (acquisition unit 11 (21)) for acquiring either color information or pigment information and a feature amount of waste plastic; A prediction means (prediction unit 12) for predicting the other of the color information and the pigment information from the acquired information using a prediction model that has learned the correlation between the pigment information, the feature amount of the waste plastic, and the color information; an output means (output unit 13) for outputting a prediction result by the prediction means; a registration means (registration unit 14) for registering information including at least one of the prediction result by the prediction means and information referred to by the prediction means in a database; This configuration also provides the various effects of the exemplary embodiments described above.

[0158] [Software implementation example] Some or all of the functions of the information processing devices 1, 2, 100A, and 100B (hereinafter also referred to as "each of the above devices") may be realized by hardware such as an integrated circuit (IC chip), or by software.

[0159] In the latter case, each of the above devices is realized by, for example, a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 17. Figure 17 is a block diagram showing the hardware configuration of computer C that functions as each of the above devices.

[0160] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to operate as each of the above-mentioned devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above-mentioned devices.

[0161] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0162] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0163] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0164] Furthermore, the functions of each of the devices may be realized by a single processor provided in a single computer, by multiple processors provided in a single computer working in cooperation, or by multiple processors provided in each of multiple computers working in cooperation. Furthermore, the programs for causing each of the devices to realize the functions may be stored in a single memory provided in a single computer, or may be distributed and stored in multiple memories provided in a single computer, or may be distributed and stored in multiple memories provided in each of multiple computers.

[0165] [Appendix A] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0166] (Appendix A1) An acquisition means for acquiring either color information or pigment information and a feature amount of the waste plastic; a prediction means for predicting the other of the color information and the pigment information from the information acquired by the acquisition means, using a prediction model that has learned the mutual correlation between the pigment information, the feature amount of the waste plastic, and the color information; An information processing device comprising:

[0167] (Appendix A2) the acquiring means acquires the pigment information indicating candidate pigments, The prediction means predicts color information indicating a color corresponding to the pigment information from the pigment information and the feature amount of the waste plastic. 10. The information processing device according to claim 1,

[0168] (Appendix A3) the acquiring means acquires the color information indicating a target color; The prediction means predicts pigment information indicating a pigment corresponding to the color information from the color information and the feature amount of the waste plastic. 10. The information processing device according to claim 1,

[0169] (Appendix A4) The acquisition means A feature generating means for generating the feature of the waste plastic by referring to information about the waste plastic is provided. An information processing device according to any one of appendices A1 to A3.

[0170] (Appendix A5) The feature generating means The feature quantity of the waste plastic is generated by further referring to reference information including information on each color obtained by applying each of a plurality of types of pigments to each of a plurality of types of waste plastic. 1. The information processing device according to claim 1,

[0171] (Appendix A6) The system further includes an output unit that outputs the prediction result by the prediction unit. An information processing device according to any one of appendices A1 to A3.

[0172] (Appendix A7) The prediction means The color obtained when the pigment indicated in the pigment information is applied to virgin plastic or a mixed plastic containing virgin plastic and waste plastic; and A pigment that makes virgin plastic or a mixed plastic containing virgin plastic and waste plastic the color indicated by the color information. Further predicting at least one of The output means The presentation information including the prediction result by the prediction means is visually presented to the user. 10. The information processing device according to claim 9, wherein the information processing device is a

[0173] (Appendix A8) a registration means for registering information including at least one of the prediction result by the prediction means and information referenced by the prediction means in a database; Equipped with An information processing device according to any one of appendices A1 to A3.

[0174] (Appendix A9) The prediction means A trained model that predicts color information indicating the color obtained when a pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic is used as the prediction model. An information processing device according to any one of appendices A1 to A3.

[0175] (Appendix A10) The prediction means A trained model that predicts pigment information indicating pigments that will cause the waste plastic to have the color indicated by the color information and the feature amount of the waste plastic, is used as the prediction model. An information processing device according to any one of appendices A1 to A3.

[0176] (Appendix A11) An acquisition means for acquiring either color information or pigment information and a feature amount of the waste plastic; a learning means for learning a prediction model that predicts the correlation between pigment information, feature amounts of waste plastic, and color information by referring to the information acquired by the acquisition means; An information processing device comprising:

[0177] [Appendix B] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0178] (Appendix B1) An acquisition process in which at least one processor acquires either color information or pigment information and feature amounts of waste plastic; a prediction process in which the at least one processor predicts the other of the color information and the pigment information from the information acquired in the acquisition process using a prediction model that has learned the mutual correlation between pigment information, feature amounts of waste plastic, and color information; An information processing method comprising:

[0179] (Appendix B2) In the obtaining process, the at least one processor obtains the pigment information indicating candidate pigments; In the prediction process, the at least one processor predicts color information indicating a color corresponding to the pigment information from the pigment information and the feature amount of the waste plastic. 1. The information processing method described in Appendix B1.

[0180] (Appendix B3) In the obtaining process, the at least one processor obtains the color information indicating a target color; In the prediction process, the at least one processor predicts pigment information indicating a pigment corresponding to the color information from the color information and the feature amount of the waste plastic. 1. The information processing method described in Appendix B1.

[0181] (Appendix B4) In the acquisition process, the at least one processor: The at least one processor includes a feature generation process for generating the feature of the waste plastic by referring to information about the waste plastic. 1. An information processing method according to any one of appendices B1 to B3.

[0182] (Appendix B5) In the feature generation process, the at least one processor The feature quantity of the waste plastic is generated by further referring to reference information including information on each color obtained by applying each of a plurality of types of pigments to each of a plurality of types of waste plastic. The information processing method described in Appendix B4.

[0183] (Appendix B6) The at least one processor further includes an output process for outputting a prediction result from the prediction process. 1. An information processing method according to any one of appendices B1 to B3.

[0184] (Appendix B7) In the prediction process, the at least one processor: The color obtained when the pigment indicated in the pigment information is applied to virgin plastic or a mixed plastic containing virgin plastic and waste plastic; and A pigment that makes virgin plastic or a mixed plastic containing virgin plastic and waste plastic the color indicated by the color information. Further predicting at least one of In the output process, the at least one processor Presentation information including the prediction result obtained by the prediction process is visually presented to the user. An information processing method as described in Appendix B6.

[0185] (Appendix B8) a registration process in which the at least one processor registers information including at least one of the prediction result of the prediction process and information referenced by the prediction process in a database; Contains 1. An information processing method according to any one of appendices B1 to B3.

[0186] (Appendix B9) In the prediction process, the at least one processor: A trained model that predicts color information indicating the color obtained when a pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic is used as the prediction model. 1. An information processing method according to any one of appendices B1 to B3.

[0187] (Appendix B10) In the prediction process, the at least one processor: A trained model that predicts pigment information indicating pigments that will cause the waste plastic to have the color indicated by the color information and the feature amount of the waste plastic, is used as the prediction model. 1. An information processing method according to any one of appendices B1 to B3.

[0188] (Appendix B11) an acquisition process in which the at least one processor acquires either color information or pigment information and a feature amount of the waste plastic; a learning process in which the at least one processor learns a prediction model that predicts the correlation between pigment information, feature amounts of waste plastic, and color information by referring to the information acquired in the acquisition process; An information processing method comprising:

[0189] [Appendix C] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0190] (Appendix C1) A program that causes a computer to function as an information processing device, The computer An acquisition means for acquiring either color information or pigment information and a feature amount of the waste plastic; a prediction means for predicting the other of the color information and the pigment information from the information acquired by the acquisition means, using a prediction model that has learned the mutual correlation between the pigment information, the feature amount of the waste plastic, and the color information; An information processing program that functions as a

[0191] (Appendix C2) the acquiring means acquires the pigment information indicating candidate pigments, The prediction means predicts color information indicating a color corresponding to the pigment information from the pigment information and the feature amount of the waste plastic. An information processing program as described in Appendix C1.

[0192] (Appendix C3) the acquiring means acquires the color information indicating a target color; The prediction means predicts pigment information indicating a pigment corresponding to the color information from the color information and the feature amount of the waste plastic. An information processing program as described in Appendix C1.

[0193] (Appendix C4) The computer The acquisition means The method functions as a feature generation process for generating the feature of the waste plastic by referring to information about the waste plastic. An information processing program according to any one of appendices C1 to C3.

[0194] (Appendix C5) The feature generating means The feature quantity of the waste plastic is generated by further referring to reference information including information on each color obtained by applying each of a plurality of types of pigments to each of a plurality of types of waste plastic. An information processing program as described in Appendix C4.

[0195] (Appendix C6) The computer The device further functions as an output device for outputting the prediction result by the prediction device. An information processing program according to any one of appendices C1 to C3.

[0196] (Appendix C7) The prediction means The color obtained when the pigment indicated in the pigment information is applied to virgin plastic or a mixed plastic containing virgin plastic and waste plastic; and A pigment that makes virgin plastic or a mixed plastic containing virgin plastic and waste plastic the color indicated by the color information. Further predicting at least one of The output means The presentation information including the prediction result by the prediction means is visually presented to the user. An information processing program as described in Appendix C6.

[0197] (Appendix C8) The computer a registration process for registering information including at least one of the prediction result by the prediction means and information referenced by the prediction means in a database; to function as An information processing program according to any one of appendices C1 to C3.

[0198] (Appendix C9) The prediction means A trained model that predicts color information indicating the color obtained when a pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic is used as the prediction model. An information processing program according to any one of appendices C1 to C3.

[0199] (Appendix C10) The prediction means A trained model that predicts pigment information indicating pigments that will cause the waste plastic to have the color indicated by the color information and the feature amount of the waste plastic, is used as the prediction model. An information processing program according to any one of appendices C1 to C3.

[0200] (Appendix C11) The computer An acquisition means for acquiring either color information or pigment information and a feature amount of the waste plastic; a learning process in which a prediction model that predicts the correlation between pigment information, feature amounts of waste plastic, and color information is learned by referring to the information acquired by the acquisition means; An information processing program that functions as a

[0201] [Appendix D] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0202] (Appendix D1) at least one processor, An acquisition process for acquiring either color information or pigment information and feature amounts of waste plastic; a prediction process for predicting the other of the color information and the pigment information from the information acquired by the acquisition process using a prediction model that has learned the mutual correlation between the pigment information, the feature amount of the waste plastic, and the color information; An information processing device that executes the above.

[0203] The information processing device may further include a memory, and the memory may store a program for causing the at least one processor to execute each of the processes.

[0204] (Appendix D2) In the obtaining process, the at least one processor obtains the pigment information indicating candidate pigments; In the prediction process, the at least one processor predicts color information indicating a color corresponding to the pigment information from the pigment information and the feature amount of the waste plastic. 10. The information processing device according to claim 9, wherein the information processing device is an information processing device according to claim 1.

[0205] (Appendix D3) In the obtaining process, the at least one processor obtains the color information indicating a target color; In the prediction process, the at least one processor predicts pigment information indicating a pigment corresponding to the color information from the color information and the feature amount of the waste plastic. 10. The information processing device according to claim 9, wherein the information processing device is an information processing device according to claim 1.

[0206] (Appendix D4) In the acquisition process, the at least one processor: Execute a feature generation process to generate the feature of the waste plastic by referring to the information about the waste plastic. An information processing device according to any one of appendices D1 to D3.

[0207] (Appendix D5) In the feature generation process, the at least one processor The feature quantity of the waste plastic is generated by further referring to reference information including information on each color obtained by applying each of a plurality of types of pigments to each of a plurality of types of waste plastic. 10. The information processing device according to claim 9, wherein the information processing device is an information processing device according to claim 1 ....

[0208] (Appendix D6) the at least one processor: An output process is further executed to output a prediction result obtained by the prediction process. An information processing device according to any one of appendices D1 to D3.

[0209] (Appendix D7) In the prediction process, the at least one processor The color obtained when the pigment indicated in the pigment information is applied to virgin plastic or a mixed plastic containing virgin plastic and waste plastic; and A pigment that makes virgin plastic or a mixed plastic containing virgin plastic and waste plastic the color indicated by the color information. Further predicting at least one of In the output process, the at least one processor Presentation information including the prediction result obtained by the prediction process is visually presented to the user. 10. The information processing device according to claim 9, wherein the information processing device is an information processing device according to claim 8.

[0210] (Appendix D8) The at least one processor: A registration process for registering information including at least one of the prediction result obtained by the prediction process and information referenced by the prediction process in a database. Run An information processing device according to any one of appendices D1 to D3.

[0211] (Appendix D9) In the prediction process, the at least one processor A trained model that predicts color information indicating the color obtained when a pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic is used as the prediction model. An information processing device according to any one of appendices D1 to D3.

[0212] (Appendix D10) In the prediction process, the at least one processor A trained model that predicts pigment information indicating pigments that will cause the waste plastic to have the color indicated by the color information and the feature amount of the waste plastic, is used as the prediction model. An information processing device according to any one of appendices D1 to D3.

[0213] (Appendix D11) The at least one processor: An acquisition process for acquiring either color information or pigment information and feature amounts of waste plastic; a learning process for learning a prediction model that predicts the correlation between pigment information, feature amounts of waste plastic, and color information by referring to the information acquired in the acquisition process; An information processing device that executes the above.

[0214] [Appendix E] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0215] (Appendix E1) A program that causes a computer to function as an information processing device, The computer, An acquisition process for acquiring either color information or pigment information and feature amounts of waste plastic; a prediction process for predicting the other of the color information and the pigment information from the information acquired by the acquisition process using a prediction model that has learned the mutual correlation between the pigment information, the feature amount of the waste plastic, and the color information; A non-transitory recording medium on which an information processing program for executing the above is recorded. [Explanation of symbols]

[0216] 1, 2, 100A, 100B Information processing equipment 1A, 1B Information Processing System 10, 51 Control unit 11, 21 Acquisition Department 12 Prediction Department 13 Output section 14 Registration Department 20 Memory section 22 Learning Department 30, 53 Communications Department 40 Input / output section 50 Server device 52 databases 111 Feature generation unit C1 processor C2 Memory

Claims

1. An acquisition means for acquiring either color information or pigment information and a feature amount of the waste plastic; a prediction means for predicting the other of the color information and the pigment information from the information acquired by the acquisition means, using a prediction model that has learned the mutual correlation between the pigment information, the feature amount of the waste plastic, and the color information; An information processing device comprising:

2. The acquisition means and the prediction means The pigment information indicating candidate pigments is acquired by the acquisition means; The prediction means predicts color information indicating a color corresponding to the pigment information from the pigment information and the feature amount of the waste plastic. The first process is: The acquisition means acquires the color information indicating a target color; The prediction means predicts pigment information indicating a pigment corresponding to the color information from the color information and the feature amount of the waste plastic. and (ii) performing at least one of the following second processes. The information processing device according to claim 1 .

3. The acquisition means A feature generating means for generating the feature of the waste plastic by referring to information about the waste plastic is provided.

3. The information processing device according to claim 1 or 2.

4. The feature generating means The feature quantity of the waste plastic is generated by further referring to reference information including information on each color obtained by applying each of a plurality of types of pigments to each of a plurality of types of waste plastic. The information processing device according to claim 3 .

5. The prediction means The color obtained when the pigment indicated in the pigment information is applied to virgin plastic or a mixed plastic containing virgin plastic and waste plastic; and A pigment that makes virgin plastic or a mixed plastic containing virgin plastic and waste plastic the color indicated by the color information. Further predicting at least one of The information processing device includes: The system further comprises an output unit for visually presenting to a user presentation information including a prediction result by the prediction unit.

3. The information processing device according to claim 1 or 2.

6. a registration means for registering information including at least one of the prediction result by the prediction means and information referenced by the prediction means in a database; Equipped with 3. The information processing device according to claim 1 or 2.

7. The prediction means A trained model that predicts color information indicating the color that will be obtained when a pigment indicated by the pigment information is applied to the waste plastic based on the pigment information and the feature amount of the waste plastic is used as the prediction model, or A trained model that predicts pigment information indicating pigments that will cause the waste plastic to have the color indicated by the color information and the feature amount of the waste plastic, is used as the prediction model.

3. The information processing device according to claim 1 or 2.

8. An acquisition means for acquiring either color information or pigment information and a feature amount of the waste plastic; a learning means for learning a prediction model that predicts the correlation between pigment information, feature amounts of waste plastic, and color information by referring to the information acquired by the acquisition means; An information processing device comprising:

9. Acquiring either color information or pigment information and a feature amount of the waste plastic; predicting the other of the color information and the pigment information from the acquired information using a prediction model that has learned the mutual correlation between the pigment information, the feature amount of the waste plastic, and the color information; An information processing method comprising:

10. A program that causes a computer to function as an information processing device, The program causes the computer to: An acquisition process for acquiring either color information or pigment information and feature amounts of waste plastic; a prediction process for predicting the other of the color information and the pigment information from the information acquired by the acquisition process using a prediction model that has learned the mutual correlation between the pigment information, the feature amount of the waste plastic, and the color information; A program that executes the following.

Images