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

Abstract

To provide an information processing device which grasps demands of users for each mode of use of a nonwoven fabric product, an information processing method, and an information processing program.SOLUTION: In an information processing system 1 configured by connecting by wire or wirelessly an SNS server 10, a delivery company server 20 and an information processing device 100 over a network N so as to communicate with each other, the information processing device includes: a first extraction unit 132 that extracts, from among posted information that has been posted on the network by users, posted information containing information related to a predetermined nonwoven fabric product; a second extraction unit 133 that extracts, from among the posted information extracted by the first extraction unit 132, posted information related to the use of the nonwoven fabric product; and an estimation unit 134 that estimates, on the basis of the posted information related to the use of the nonwoven fabric product, information related to a mode of use when the users use the nonwoven fabric product.SELECTED DRAWING: Figure 2

Description

Technical Field

[0004] ,

[0006] , , , , ,

[0005] , , , , ,

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

Background Art

[0002] Conventionally, there is known a technique in which a demand prediction system uses past information of SNS (Social Networking Service) related to similar concerts as performance information to predict the demand of spectators such as wanting beer, wanting tea, and wanting to eat ice.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the above conventional technology merely predicts the demand for products based on the posted information posted on the SNS by the user. For example, in the case of a non-woven product whose daily usage times are limited, depending on the usage mode of the non-woven product, there may be times when there are non-woven products that the user wants to use and non-woven products that the user refrains from using. In such a case, it is not always possible to make an appropriate demand prediction for the product.

[0005] The present application has been made in view of the above, and an object thereof is to grasp the demand of the user for each usage mode of the non-woven product.

Means for Solving the Problems

[0006] The information processing device according to the present application is characterized by comprising: a first extraction unit that extracts posted information containing information about a predetermined nonwoven fabric product from among the posted information posted on a network by a user; a second extraction unit that extracts posted information concerning the use of the nonwoven fabric product from among the posted information extracted by the first extraction unit; and an estimation unit that estimates information concerning the manner in which a user uses the nonwoven fabric product based on the posted information concerning the use of the nonwoven fabric product. [Effects of the Invention]

[0007] According to one embodiment of the system, user demand can be grasped for each usage scenario of the nonwoven fabric product. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of information processing performed by the information processing device according to the embodiment. [Figure 2] Figure 2 shows an example of the configuration of an information processing system according to the embodiment. [Figure 3] Figure 3 shows an example of a post information storage unit according to the embodiment. [Figure 4] Figure 4 shows an example of a product information storage unit according to the embodiment. [Figure 5] Figure 5 shows an example of an estimation result information storage unit according to the embodiment. [Figure 6] Figure 6 is a flowchart showing an example of the delivery process flow executed by the information processing device according to the embodiment. [Figure 7] Figure 7 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0009] The following matters become clear from this specification and the accompanying drawings:

[0010] An information processing device comprising: a first extraction unit that extracts posted information containing information about a predetermined nonwoven fabric product from among the posted information posted on the network by users; a second extraction unit that extracts posted information concerning the use of the nonwoven fabric product from among the posted information extracted by the first extraction unit; and an estimation unit that estimates information about the manner in which a user uses the nonwoven fabric product based on the posted information concerning the use of the nonwoven fabric product.

[0011] Such an information processing device can, for example, extract information posted by users on social networking services (SNS) that contains information about a specified nonwoven fabric product, such as wet wipes. Examples of posted information include, but are not limited to, text, still images, and moving images.

[0012] Here, it is likely that the posted information containing information about a specified nonwoven fabric product includes not only information on how and in what manner the nonwoven fabric product is being used, but also information that simply indicates the nonwoven fabric product. If user needs are estimated using such posted information, there is a risk that user demand may not be accurately grasped.

[0013] For example, with products like wet wipes, which are used only a limited number of times a day, there may be certain types of wet wipes that users prefer and others that they avoid. For instance, when users go outdoors, they tend to prefer small, easy-to-carry packs. On the other hand, when users want to use wet wipes indoors, they tend to prefer large packs.

[0014] Furthermore, it is predicted that there will be demand for wet wipes indoors for wiping items such as tables and chairs. Therefore, if an increase in indoor wet wipe use is predicted, it would be desirable to manufacture wet wipes with ingredients and sizes suitable for wiping items. On the other hand, it is predicted that there will be demand for wet wipes outdoors for wiping hands for disinfection. Therefore, if an increase in outdoor wet wipe use is predicted, it would be desirable to manufacture wet wipes with ingredients and sizes suitable for wiping hands.

[0015] Under these trends, for example, if it is predicted that the demand for wet wipes will increase indoors, such as during outbreaks of various infectious diseases, it is desirable to manufacture a large quantity of wet wipes in large packs or wet wipes with ingredients and sizes suitable for wiping objects. However, during outbreaks of various infectious diseases, as a result of increased remote work, there may be an increase in activities such as taking walks in nearby parks to alleviate lack of exercise. In this case, instead of large packs, there may be an increase in demand for small packs of wet wipes that are easy for users to carry, or wet wipes with ingredients and sizes suitable for wiping hands.

[0016] As mentioned above, accurate demand forecasting is difficult for nonwoven fabric products such as wet wipes, which can sometimes prevent the implementation of appropriate manufacturing plans. Therefore, the information processing device extracts user-submitted information related to the use of nonwoven fabric products. Based on this user-submitted information, the information processing device estimates information about how users utilize nonwoven fabric products. In other words, the information processing device extracts user-submitted information related to the use of nonwoven fabric products based on highly immediate posting information such as that found on social media, and uses the extracted information to estimate information about usage patterns in a timely manner. This allows the information processing device to estimate, for example, the appropriate ratio of small-capacity and large-capacity packs of wet wipes, as well as product forms that match demand, such as ingredients or size.

[0017] In addition, the information processing device extracts, as posting information including information about the predetermined non-woven fabric product, posting information including a keyword indicating the non-woven fabric product.

[0018] According to such an information processing device, for example, among the posting information retrieved from the storage unit of an SNS server that provides an SNS, posting information including wet tissue as a keyword is extracted. Thereby, the information processing device can appropriately extract posting information including information about the predetermined non-woven fabric product.

[0019] In addition, the information processing device extracts, as posting information including information about the predetermined non-woven fabric product, posting information including a keyword indicating the type of the non-woven fabric product.

[0020] According to such an information processing device, for example, among the posting information retrieved from the storage unit of an SNS server that provides an SNS, posting information including keywords indicating the product name of wet tissue or the series name of the product is extracted. Thereby, the information processing device can comprehensively extract posting information including information about the predetermined non-woven fabric product.

[0021] In addition, the information processing device extracts, as posting information about the use of the non-woven fabric product, posting information including information about the behavior of a user who uses the non-woven fabric product, and estimates information about the usage mode when the user uses the non-woven fabric product based on the posting information including information about the behavior of the user.

[0022] According to such an information processing device, for example, among the posting information including wet tissue as a keyword, posting information including the behavior of the user or the current location of the user as a keyword is extracted. Subsequently, the information processing device estimates information about the usage mode when the user uses the non-woven fabric product based on the posting information including the behavior of the user and the current location of the user. Thereby, the information processing device can grasp the needs of the user for each usage mode of the non-woven fabric product.

[0023] Furthermore, the information processing device extracts posted information containing keywords indicating the user's actions, as posted information containing information about the user's actions.

[0024] According to this information processing device, for example, it can extract posts containing user actions as keywords from posts containing "wet wipes" as a keyword. This allows the information processing device to appropriately extract posts containing user actions.

[0025] Furthermore, the information processing device extracts posted information containing keywords indicating the date and time related to the user's actions, as posted information containing information about the user's actions.

[0026] According to such an information processing device, for example, it can extract posts containing keywords related to the user's actions, such as "wet wipes," from among posts containing the keyword "wet wipes." This allows the information processing device to appropriately extract posts containing keywords related to the user's actions.

[0027] Furthermore, the information processing device extracts posted information that includes keywords indicating the user's location, as posted information that includes information about the user's actions.

[0028] According to this information processing device, for example, it can extract posts containing the user's current location from among posts that include the keyword "wet wipes." This allows the information processing device to appropriately extract posts that include the user's current location.

[0029] Furthermore, the information processing device estimates information regarding the usage location, which is the place where the user uses the nonwoven fabric product, as information regarding the usage pattern.

[0030] According to this type of information processing device, for example, if the posted information includes keywords such as picnic or cafe, it can be estimated that the location where the user uses wet wipes is outdoors. This allows the information processing device to accurately estimate the location of use.

[0031] Furthermore, the information processing device estimates, based on the information regarding the place of use, whether or not the user will carry the nonwoven fabric product to the place of use.

[0032] According to such an information processing device, for example, if it is estimated that the place of use is outdoors, it is estimated that the user will carry the wet wipes to the place of use. This allows the information processing device to accurately estimate whether or not the user will carry the nonwoven fabric product to the place of use.

[0033] Furthermore, the information processing device estimates information regarding the demand for each product form of the nonwoven fabric product based on the information regarding the usage patterns.

[0034] According to such an information processing device, for example, if it is estimated that the usage location is outdoors and that the user will carry the wet wipes to the usage location, it will estimate information regarding the demand for small-capacity and large-capacity packs. As a result, the information processing device can accurately estimate information regarding the demand for each product form of nonwoven fabric products.

[0035] Furthermore, the information processing device estimates information regarding the demand for each product form, which differs in the number of nonwoven fabric products included in the product form.

[0036] According to such an information processing device, for example, it can estimate that the demand for small-capacity packs, which are easy to use outdoors and easy to carry, is higher than the demand for large-capacity packs. As a result, the information processing device can accurately estimate information regarding the demand for each product form with different numbers of nonwoven fabric products.

[0037] Furthermore, the information processing device estimates the demand for each provision method of the nonwoven fabric product based on the information regarding the usage method.

[0038] According to such an information processing device, for example, based on information that there is high demand for small-capacity packs, it can estimate that the number of small-capacity packs sold at convenience stores should be increased as a way of providing small-capacity packs. This allows the information processing device to facilitate the purchase of nonwoven fabric products at the appropriate time for the user.

[0039] Furthermore, the information processing device estimates information regarding the demand for each product form of the nonwoven fabric product based on the changes in usage patterns.

[0040] According to such an information processing device, for example, it may estimate that there is a high demand for large-capacity packs based on information such as a shift in the location where users use wet wipes from outdoors to indoors. This allows the information processing device to accurately estimate the demand for nonwoven fabric products in a timely manner.

[0041] Furthermore, the information processing device extracts posts from a designated social networking service (SNS) that contain information related to the nonwoven fabric product.

[0042] According to such an information processing device, for example, posts containing the keyword "wet wipes" can be extracted from the memory of an SNS server. This allows the information processing device to appropriately extract posts containing information related to nonwoven fabric products.

[0043] Furthermore, the information processing device performs a delivery process to deliver nonwoven fabric products in product forms corresponding to the estimated usage pattern.

[0044] According to such an information processing device, for example, if it estimates that there is a high demand for small-capacity packs of wet wipes, it sends a delivery request to a delivery company to have small-capacity packs of wet wipes delivered to retail stores. This allows the information processing device to provide appropriate nonwoven fabric products to retail stores.

[0045] Below, an example of an embodiment for implementing an information processing device, an information processing method, and an information processing program (hereinafter referred to as "embodiment") will be described in detail with reference to the drawings. Note that this embodiment does not limit the information processing device, information processing method, and information processing program. Furthermore, the same parts will be denoted by the same reference numerals in the following embodiments, and redundant explanations will be omitted.

[0046] [Embodiment] [1. An example of information processing performed by an information processing device] An example of information processing performed by the information processing device 100 according to the embodiment will be explained using Figure 1. Figure 1 is a diagram showing an example of information processing performed by the information processing device 100 according to the embodiment. For convenience, the steps shown in Figure 1 include the actions of natural persons, etc.

[0047] In the following, the SNS server 10 will be assumed to provide a service (sometimes referred to as "Service A") that makes user-submitted posts publicly available to other users. An example of Service A is a microblog that makes relatively short text-based posts publicly available to each user.

[0048] In this case, the information processing device 100 extracts posts containing information about wet wipes (an example of a nonwoven fabric product) from the posted information. Next, the information processing device 100 extracts posts containing information about the user's behavior from the extracted posted information. Then, an example is described in which the information processing device 100 estimates information about the user's usage patterns when using wet wipes based on the posted information containing information about the user's behavior that it has extracted.

[0049] First, as shown in Figure 1, the user makes a post about wet wipes (Step S1). In this case, the user is assumed to be registered with Service A. For example, the user is assumed to have registered user information etc. with Service A and has an account with Service A.

[0050] In the example in Figure 1, user U1 posts information PO1 on service A stating, "Wet wipes are essential for picnics." User U2 also posts information PO2 on service A stating, "Wet wipes are convenient." User U3 also posts information PO3 on service A stating, "Wet wipes are essential at cafes." In this way, the SNS server 10 receives information about the date and time of posting along with the posted information from each user.

[0051] Next, the information processing device 100 searches the memory unit of the SNS server 10 for posted information and extracts posted information that includes information about wet wipes (step S2).

[0052] For example, the information processing device 100 searches for posted information from the memory unit of the SNS server 10. Subsequently, the information processing device 100 extracts posted information from the searched posted information that contains "wet wipes" as a keyword. Here, a keyword is a predetermined word. For example, if the keyword is "wet wipes," the keyword may include alternative names for wet wipes such as alcohol wipes, disinfectant and antibacterial wipes, or names of different types of wet wipes (for example, wet wipes containing alcohol, wet wipes without alcohol, etc.).

[0053] To give a more specific example, the information processing device 100 uses conventional techniques such as morphological analysis and semantic analysis to determine whether the text of the posted information contains the keyword "wet wipes." If the posted information contains "wet wipes," the information processing device 100 extracts the posted information.

[0054] In the example shown in Figure 1, the information processing device 100 extracts post information PO1 to PO3 containing the keyword "wet wipes" from the storage unit of the SNS server 10. This processing may also be implemented using, for example, the search function of the SNS server 10. For example, the SNS server 10 may extract post information containing text containing the keyword, or it may use conventional techniques such as image analysis to extract post information containing still images or moving images of objects related to the keyword.

[0055] Then, the information processing device 100 extracts posts from the extracted posts that contain information about the actions of users who use wet wipes (step S3). In other words, the information processing device 100 filters out posts that contain content indicating the use of wet wipes from the search results based on keywords indicating wet wipes, such as the product name of the wet wipes. For example, the information processing device 100 extracts posts that contain keywords related to user actions or the user's current location from among posts that contain "wet wipes" as a keyword.

[0056] To give a more specific example, the information processing device 100 uses conventional techniques such as morphological analysis and semantic analysis to determine whether the text of the posted information contains keywords related to the user's actions or the user's current location. If the posted information contains the user's actions or current location, the information processing device 100 extracts such posted information.

[0057] In the example in Figure 1, in post information PO1, "Wet wipes are essential for picnics," "picnic" is assumed to be a keyword indicating the user's action. Also, in post information PO3, "Wet wipes are essential at cafes," "cafe" is assumed to be a keyword indicating the user's current location. In this case, the information processing device 100 extracts post information PO1 and PO3 that contain keywords indicating the user's action or the user's current location from post information PO1 to PO3, which include wet wipes.

[0058] Furthermore, the information processing device 100 may use predetermined keywords as keywords indicating user behavior. For example, it may use a learning model that estimates whether or not posted information such as still images, moving images, or text contains information indicating the use of wet wipes by the user (for example, a learning model that has been trained to output information indicating that information indicating the use of wet wipes is included in the posted information when posted information that has been previously extracted as containing information indicating the use of wet wipes is input) to extract posted information indicating user behavior.

[0059] Next, the information processing device 100 estimates information about the usage pattern when using wet wipes based on posted information that includes information about the user's behavior (step S4). In the example in Figure 1, the information processing device 100 estimates that the location where the user uses wet wipes is outdoors, based on the extracted posted information PO1 and PO3.

[0060] To give a more specific example, the information processing device 100 performs morphological analysis on the text of post information PO1, which states, "Wet wipes are essential for picnics," and extracts text such as "picnic." Similarly, the information processing device 100 performs morphological analysis on the text of post information PO2, which states, "Wet wipes are essential at cafes," and extracts text such as "cafe." Next, based on the extracted text, the information processing device 100 estimates how users utilize wet wipes.

[0061] For example, the information processing device 100 has a table (hereinafter sometimes referred to as the "usage pattern table") in a predetermined storage unit that associates usage patterns with keywords, and based on the usage pattern table, it identifies the usage patterns associated with keywords that match the text extracted from each post. Then, based on the trends of the identified usage patterns, the information processing device 100 estimates how users are using wet wipes.

[0062] To give a more specific example, suppose a designated memory unit holds a usage pattern table in which usage patterns such as "outdoors," "eating and drinking," and "dining out" are associated with the keyword "cafe." Also, suppose a designated memory unit holds a usage pattern table in which usage patterns such as "outdoors," "going out," "exercise," and "walking" are associated with the keyword "picnic." In this case, the information processing device 100 estimates "outdoors" as the usage pattern with the highest commonality among the usage patterns associated with "cafe" and "picnic."

[0063] Furthermore, the information processing device 100 may consider usage patterns associated with similar keywords, in addition to keywords that match the text extracted from each post. The information processing device 100 may also estimate usage patterns by considering weighting according to the degree of similarity.

[0064] Furthermore, the information processing device 100 may estimate usage patterns using, for example, a learning model that has been trained to output the degree to which wet wipes are used for each predetermined usage pattern. For example, when post information indicating the use of wet wipes outdoors is input to the information processing device 100, the learning model has been trained to output a higher score when post information indicating the use of wet wipes indoors is input to the information processing device 100. If post information PO1 and post information PO2 are input to the learning model and the learning model outputs a score equal to or greater than a predetermined value, the information processing device 100 may estimate "outdoors" as the usage pattern.

[0065] Next, the information processing device 100 estimates whether the user will carry the wet wipes to the place of use, based on information about the place of use. In the example in Figure 1, the information processing device 100 estimates that the user will carry the wet wipes to the place of use, based on the information that the place of use is outdoors. This estimation process may be implemented, for example, based on a table that associates usage patterns with whether or not carrying occurs. Alternatively, the estimation process may be implemented by a learning model that has learned the characteristics of usage patterns in which carrying occurs.

[0066] Next, the information processing device 100 estimates the demand for each product form of wet wipes based on the information regarding usage patterns. In the example shown in Figure 1, the wet wipes are available in small-capacity packs containing fewer than a predetermined number of wipes and large-capacity packs containing more than a predetermined number of wipes. In this case, the information processing device 100 estimates the demand for the small-capacity packs and large-capacity packs based on information such as the usage location being outdoors and the user carrying the wet wipes to the usage location. Here, the information processing device 100 estimates that the demand for small-capacity packs, which are easy to use outdoors and easy to carry, is higher than the demand for large-capacity packs. Such estimation can be implemented, for example, based on a table that associates usage behaviors such as carrying with products suitable for such behaviors.

[0067] Then, the information processing device 100 performs a delivery process to deliver wet wipes in a product form corresponding to the estimated usage pattern (step S5). For example, based on information that there is a high demand for small-capacity packs of wet wipes, the information processing device 100 sends a delivery request to the delivery company server 20 to deliver small-capacity packs of wet wipes to the retail store SH1. Subsequently, the delivery company LO1, which manages the delivery company server 20, arranges for delivery based on this delivery request.

[0068] Next, delivery company LO1, which manages the delivery server 20, delivers small-capacity packs of wet wipes to retail store SH1 (step S6). For example, delivery company LO1 delivers the small-capacity packs of wet wipes to retail store SH1, which is the delivery destination corresponding to the delivery request it received. As a result of this process, retail store SH1 can prepare small-capacity packs of wet wipes, which are in higher demand than large-capacity packs. Therefore, when a user visits retail store SH1, they can purchase small-capacity packs of wet wipes.

[0069] Traditionally, product demand was predicted based solely on user-generated posts on social media, which limited the range of products for which demand could be predicted. For example, in the case of wet wipes, which are used a limited number of times per day, users may have different preferences for certain types of wet wipes depending on their usage patterns. In such cases, it was sometimes impossible to accurately predict the demand for wet wipes.

[0070] Therefore, the information processing device 100 extracts information from the posted information on the network by users that includes information about a specified nonwoven fabric product. Next, the information processing device 100 extracts information from the extracted posted information that relates to the use of the nonwoven fabric product. Then, based on the extracted posted information relating to the use of the nonwoven fabric product, the information processing device 100 estimates information about the usage patterns of the nonwoven fabric product when a user uses it. In this way, the information processing device 100 can grasp the user's demand for each usage pattern of the nonwoven fabric product. As a result, the information processing device 100 can estimate the demand for the nonwoven fabric product desired by the user at the time the user wants to use the nonwoven fabric product, and can provide the user with the nonwoven fabric product they desire.

[0071] [2. Configuration of the Information Processing System] Next, the configuration of the information processing system 1 according to the embodiment will be described using Figure 2. Figure 2 is a diagram showing an example of the configuration of the information processing system 1 according to the embodiment. As shown in Figure 2, the information processing system 1 includes an SNS server 10, a delivery company server 20, and an information processing device 100. The SNS server 10, the delivery company server 20, and the information processing device 100 are connected to each other via a network N, either by wired or wireless communication. Note that the information processing system 1 shown in Figure 2 may include multiple SNS servers 10, multiple delivery company servers 20, and multiple information processing devices 100.

[0072] The SNS server 10 is an information processing device that provides various SNS services, and is implemented, for example, by a server device or a cloud system. For example, the SNS server 10 accepts posts from users, such as microblogs, blogs, articles, messages, still images, and videos. Subsequently, the SNS server 10 stores such posts in its storage unit. Then, the SNS server 10 makes the posts stored in the storage unit public to other users who are different from the user who posted the posts.

[0073] The delivery company server 20 is an information processing device that performs delivery-related processing in response to various delivery requests, and is implemented, for example, by a server device or a cloud system. For example, the delivery company server 20 receives various delivery requests and arranges deliveries based on the received delivery requests. The delivery company that manages the delivery company server 20 then delivers the nonwoven fabric products to the delivery destinations corresponding to the received delivery requests.

[0074] The information processing device 100 is an information processing device that can communicate with various devices via a network N such as the Internet, and is implemented, for example, by a server device or a cloud system. For example, the information processing device 100 is connected to other various devices via the network N in a way that allows for communication.

[0075] [3. Configuration of the Information Processing Device] Next, the configuration of the information processing device 100 according to the embodiment will be described using Figure 2. Figure 2 shows an example of the configuration of the information processing device 100 according to the embodiment. As shown in Figure 2, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0076] (Regarding Communications Unit 110) The communication unit 110 is implemented, for example, by a NIC (Network Interface Card). The communication unit 110 is connected to the network N by wire or wireless connection and transmits and receives information with various other devices.

[0077] (Regarding memory unit 120) The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs. For example, the storage unit 120 has a posting information storage unit 121, an estimation result information storage unit 122, and a product information storage unit 123.

[0078] Furthermore, the memory unit 120 stores information about various tables, such as a usage pattern table, a table associating whether or not the product is carried, and a table associating actions taken during use with products suitable for those actions. The memory unit 120 also stores a learning model that estimates whether or not the posted information contains information indicating that the user is using the nonwoven fabric product, and a learning model that has learned the characteristics of usage patterns in which the product is carried.

[0079] (Regarding the submission information storage unit 121) The posting information storage unit 121 stores posting information and related information in association with the posting information. Here, Figure 3 shows an example of the posting information storage unit 121 according to the embodiment. In the example shown in Figure 3, the posting information storage unit 121 has items such as "Posting Information ID (Identifier)" and "Posting Information". For example, "Posting Information" has items such as "User ID", "User Information", "Date and Time", and "Posting Information".

[0080] The "Post Information ID" is an identifier that identifies the posted information. The "User ID" is an identifier that identifies the user who posted the information associated with the "Post Information ID". "User Information" is information about the user associated with the "Post Information ID". For example, user information includes the user's age, gender, address, and location information.

[0081] "Date and Time" refers to information about the date and time the post information associated with the "Post Information ID" was posted. "Post Information" refers to the post information associated with the "Post Information ID". For example, post information may be in text format.

[0082] For example, in Figure 3, "P1," identified by the post information ID, has a user ID of "UI1," user information of "IU1," date and time of "DT1," and post information of "PO1."

[0083] In the example shown in Figure 3, user information is represented by an abstract code such as "IU1," but user information may also be numerical data, string information, or the file format of a file containing user information.

[0084] (Regarding the estimated result information storage unit 122) The estimation result information storage unit 122 stores information about the estimated estimation result. Here, Figure 4 shows an example of the estimation result information storage unit 122 according to the embodiment. In the example shown in Figure 4, the estimation result information storage unit 122 has items such as "Estimated Result ID", "Date and Time", and "Estimated Result".

[0085] The "Estimated Result ID" is an identifier that identifies the estimated result. The "Date and Time" is information about the date and time corresponding to the estimated result associated with the "Estimated Result ID". The "Estimated Result" is information about the estimated result associated with the "Estimated Result ID".

[0086] For example, in Figure 4, "R1," identified by the estimated result ID, has a date and time of "DT1" and an estimated result of "LI1." Note that in the example shown in Figure 5, the date and time are represented by abstract codes such as "DT1," but the date and time may also be numerical values, string information, or a file format containing information about the date and time.

[0087] (Regarding the product information storage unit 123) The product information storage unit 123 stores various information about the product. Here, Figure 5 shows an example of the product information storage unit 123 according to this embodiment. In the example shown in Figure 5, the product information storage unit 123 has items such as "product ID" and "product information". For example, "product information" has items such as "type", "product", and "quantity".

[0088] "Product ID" is an identifier that identifies a product. "Type" is information about the type of product associated with the "Product ID". For example, the type is information about the product form, such as small-capacity packs or large-capacity packs. For example, a small-capacity pack is a product form in which wet wipes are packaged in less than a predetermined number of sheets. Here, a small-capacity pack indicates a product form that is divided into smaller portions. A large-capacity pack is a product form in which wet wipes are packaged in a predetermined number or more sheets. "Number of Sheets" is information about the number of sheets of a product associated with the "Product ID".

[0089] For example, in Figure 5, "M1," identified by the product ID, has a type of "MT1," a product of "MA1," and a quantity of "MN1." Note that in the example shown in Figure 4, the type, etc., were represented by abstract codes such as "MT1," but the type, etc., could also be a numerical value, string information, or a file format containing information about the type, etc.

[0090] (Regarding the control unit 130) The control unit 130 is a controller, and is implemented, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs (an example of an information processing program) stored in the memory device inside the information processing device 100 using RAM as the working area. Alternatively, the control unit 130 is a controller and can be implemented, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0091] As shown in Figure 2, the control unit 130 includes a search unit 131, a first extraction unit 132, a second extraction unit 133, an estimation unit 134, and a delivery processing unit 135, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 2, and other configurations are also possible as long as they perform the information processing described later. Also, the connection relationships of each processing unit in the control unit 130 are not limited to the connection relationships shown in Figure 2, and other connection relationships are also possible.

[0092] (Regarding search unit 131) The search unit 131 searches for various types of information. For example, the search unit 131 searches for posted information from the storage unit of the SNS server 10.

[0093] (Regarding the first extraction unit 132) The first extraction unit 132 extracts various types of information. Specifically, the first extraction unit 132 extracts posts from users posted on the network that contain information about a specified nonwoven fabric product. For example, the first extraction unit 132 extracts posts from the search unit 131 that contain "wet wipes" (an example of a specified nonwoven fabric product) as a keyword.

[0094] To give a more specific example, the first extraction unit 132 uses conventional techniques such as morphological analysis and semantic analysis to determine whether the text of the posted information contains the keyword "wet wipes." If the posted information contains "wet wipes," the first extraction unit 132 extracts the posted information.

[0095] In this case, the first extraction unit 132 extracts information related to the extracted post information, such as an ID that identifies the user who posted the post, user information about the user, and information regarding the date and time the post was posted. The first extraction unit 132 then stores the extracted post information and the information related to the post information in the post information storage unit 121.

[0096] (Regarding the second extraction unit 133) The second extraction unit 133 extracts various types of information from the information extracted by the first extraction unit 132. Specifically, the second extraction unit 133 extracts posts related to the use of nonwoven fabric products from the posted information extracted by the first extraction unit 132.

[0097] For example, the second extraction unit 133 extracts post information, including wet wipes, stored by the post information storage unit 121, that includes user behavior and the user's current location as keywords (an example of post information regarding the use of nonwoven fabric products).

[0098] To give a more specific example, the second extraction unit 133 uses conventional techniques such as morphological analysis and semantic analysis to determine whether the text of the posted information contains keywords related to the user's actions or the user's current location. If the second extraction unit 133 contains the user's actions or current location, it extracts the posted information. The second extraction unit 133 then stores the extracted posted information in the storage unit 120.

[0099] In the example in Figure 1, in post information PO1, "Wet wipes are essential for picnics," "picnic" is assumed to be a keyword indicating the user's action. Also, in post information PO3, "Wet wipes are essential at cafes," "cafe" is assumed to be a keyword indicating the user's current location. In this case, the second extraction unit 133 extracts post information PO1 and PO3 containing keywords indicating the user's action or the user's current location from post information PO1 to PO3 that include wet wipes.

[0100] Furthermore, the second extraction unit 133 may use predetermined keywords as keywords indicating user behavior. For example, it may use a learning model that estimates whether or not posted information such as still images, moving images, or text contains information indicating the use of wet wipes by the user (for example, a learning model that has been trained to output information indicating that the use of wet wipes is included in the posted information when posted information that has been previously extracted as containing information indicating the use of wet wipes is input) to extract posted information indicating user behavior.

[0101] (Regarding Estimation Section 134) The estimation unit 134 estimates various types of information. Specifically, the estimation unit 134 estimates information regarding how users use nonwoven fabric products based on posted information about the use of nonwoven fabric products. In the example in Figure 1, the estimation unit 134 estimates that the location where the user uses the wet wipes is outdoors, based on the extracted posted information PO1 and PO3.

[0102] To give a more specific example, the estimation unit 134 performs morphological analysis on the text of post information PO1, which reads, "Wet wipes are essential for picnics," and extracts text such as "picnic." Similarly, the estimation unit 134 performs morphological analysis on the text of post information PO2, which reads, "Wet wipes are essential at cafes," and extracts text such as "cafe." Based on the extracted text, the estimation unit 134 then estimates how users utilize wet wipes.

[0103] For example, the memory unit 120 may have a usage pattern table in which usage patterns and keywords are associated. In this case, the estimation unit 134 identifies the usage patterns associated with keywords that match the text extracted from each post information, based on the usage pattern table. Subsequently, the estimation unit 134 estimates how users are using wet wipes based on the trends of the identified usage patterns.

[0104] To give a more specific example, suppose the memory unit 120 holds a usage pattern table where usage patterns such as "outdoors," "eating and drinking," and "dining out" are associated with the keyword "cafe." Also, suppose the memory unit 120 holds a usage pattern table where usage patterns such as "outdoors," "going out," and "exercise" are associated with the keyword "picnic." In this case, the estimation unit 134 estimates "outdoors" as the usage pattern with the highest commonality among the usage patterns associated with "cafe" and "picnic."

[0105] Furthermore, the estimation unit 134 may consider usage patterns associated with similar keywords, in addition to keywords that match the text extracted from each post. The estimation unit 134 may also estimate usage patterns by considering weighting according to the degree of similarity.

[0106] Furthermore, the estimation unit 134 may estimate usage patterns using a learning model that has been trained to output the degree to which wet wipes are used for each predetermined usage pattern. For example, the estimation unit 134 may input posting information PO1 and posting information PO2 to a learning model that has been trained to output a higher score when posting information about wet wipes being used outdoors than when posting information about wet wipes being used indoors, and if the learning model outputs a score of a predetermined value or higher, it may estimate "outdoors" as the usage pattern.

[0107] Next, the estimation unit 134 estimates whether the user will carry the wet wipes to the place of use, based on information about the place of use. In the example in Figure 1, the estimation unit 134 estimates that the user will carry the wet wipes to the place of use, based on the information that the place of use is outdoors. Such estimation processing may be implemented, for example, based on a table that associates usage patterns with whether or not carrying occurs. Alternatively, such estimation processing may be implemented by a learning model that has learned the characteristics of usage patterns in which carrying occurs.

[0108] Next, the estimation unit 134 estimates the demand for each product form of wet wipes based on the information regarding usage patterns. The estimation unit 134 then stores the estimation results in the estimation result information storage unit 122.

[0109] In the example shown in Figure 1, the wet wipe product is assumed to come in two forms: a small-capacity pack containing fewer than a predetermined number of wet wipes, and a large-capacity pack containing more than a predetermined number of wet wipes. In this case, the estimation unit 134 estimates the demand for the small-capacity pack and the large-capacity pack based on information such as the location of use being outdoors and the user carrying the wet wipes to the location of use. For example, the estimation unit 134 estimates that the demand for the small-capacity pack, which is easy to use outdoors and easy to carry, is higher than the demand for the large-capacity pack. This estimation process can be implemented, for example, based on a table that associates user behavior, such as carrying the wipes, with products suitable for such behavior.

[0110] (Regarding shipping processing item 135) The delivery processing unit 135 executes a delivery process to deliver nonwoven fabric products in product forms that correspond to the usage patterns estimated by the estimation unit 134. Specifically, based on information such as high demand for small-capacity packs of wet wipes, the delivery processing unit 135 selects small-capacity packs of wet wipes from among the types (product forms) corresponding to the product identification IDs stored in the product information storage unit 123. Subsequently, the delivery processing unit 135 sends a delivery request to the delivery company server 20 to deliver the small-capacity packs of wet wipes to retail stores. Note that the delivery processing unit 135 is not limited to the above example, and may, for example, send various information to various servers.

[0111] [4. Processing Procedure] Next, the procedure for the delivery process executed by the information processing device 100 according to the embodiment will be explained using Figure 6. Figure 6 is a flowchart showing an example of the flow of the delivery process executed by the information processing device 100 according to the embodiment.

[0112] As shown in Figure 6, the search unit 131 determines whether or not it is a predetermined timing (step S101). The predetermined timing here refers to, for example, the timing when the information processing device 100 is operated by an administrator who manages the information processing device 100.

[0113] Specifically, if the search unit 131 determines that it is not the predetermined timing (step S101; No), it waits until it determines that it is the predetermined timing.

[0114] On the other hand, if the search unit 131 determines that a predetermined timing has been reached (step S101; Yes), it searches for the posted information stored in the memory unit of the SNS server 10 (step S102).

[0115] Next, the first extraction unit 132 extracts posts containing information about nonwoven fabric products from the posts retrieved by the search unit 131 (step S103). Then, the second extraction unit 133 extracts posts containing information about nonwoven fabric products from the posts containing information about nonwoven fabric products extracted by the first extraction unit 132, and includes information about the behavior of users who use nonwoven fabric products (step S104).

[0116] Next, the estimation unit 134 estimates information regarding the usage patterns of nonwoven fabric products based on the posted information, which includes information about the user's behavior extracted by the second extraction unit 133 (step S105). Then, the delivery processing unit 135 executes a delivery process to deliver nonwoven fabric products of the type corresponding to the usage patterns estimated by the estimation unit 134 (step S106).

[0117] [5. Variations] The information processing device 100 described above may be implemented in various other forms besides those described above. Therefore, other embodiments of the information processing device 100 will be described below.

[0118] [5-1. Nonwoven fabric products] In the above embodiment, the nonwoven fabric product was described as a wet wipe, but it is not limited to this. For example, the nonwoven fabric product may be a sanitary material other than wet wipes. The nonwoven fabric product may also be tissue, diapers, baby wipes, sanitary products, pads for light incontinence, urine pads, bed sheets, masks, breast pads, cleaning supplies, makeup puffs, etc. Another example is that the nonwoven fabric product may be a diaper for pets, a pet sheet, etc.

[0119] [5-2. Subjects for estimating demand] In the above embodiment, the example of estimating demand was given using small-capacity packs and large-capacity packs with different numbers of wet wipes as examples, but it is not limited to this. For example, the items to be estimated for demand may be products with different sizes of wet wipes, or products with different components of the liquid added to the wet wipes. Here, the components of the liquid added to the wet wipes include components of a liquid that is gentle on the skin, or components of a liquid that is used for disinfection or antibacterial purposes.

[0120] Furthermore, if the nonwoven fabric product is a children's diaper, the products for which demand is estimated may include products with different numbers of diapers, different sizes, or different types of diapers (e.g., pull-up diapers, tape diapers, etc.). In addition, the products for which demand is estimated may include products with different uses, such as training diapers, nighttime diapers, swim diapers, summer diapers, or winter diapers. Furthermore, the products for which demand is estimated may include products that differ by gender or products with different grades of diapers.

[0121] Furthermore, if the nonwoven fabric product is an adult diaper, the products for which demand is estimated may include products with different numbers of diapers, different sizes, or different types of diapers (for example, pull-up diapers, tape diapers, or pants with an absorbent pad). The products for which demand is estimated may also include products with different uses, such as diapers for nighttime use or diapers for daytime use. Additionally, the products for which demand is estimated may also include products that differ by gender or products with different absorbency levels.

[0122] Furthermore, if the nonwoven fabric product is a pet diaper, the target of demand estimation may be products with different numbers of diapers or different diaper sizes. Also, the target of demand estimation may be products that differ by gender or whether the pet is neutered or not. Also, the target of demand estimation may be products that differ by the fragrance added to the diaper.

[0123] Furthermore, if the nonwoven fabric product is a sanitary product, the target of demand estimation may be products with different numbers of sanitary products or products with different absorbency levels. Also, the target of demand estimation may be products of different types, such as sanitary napkins or panty-type sanitary napkins. Also, the target of demand estimation may be products with different features, such as the presence or absence of wings on the sanitary product. Also, the target of demand estimation may be products with different uses, such as sanitary products for sleeping, sanitary products for daytime use, or sanitary products for heavy menstrual flow. Also, the target of demand estimation may be products with different fragrances added to the sanitary product.

[0124] Furthermore, if the subject of demand estimation is pet food instead of nonwoven fabric products, the subject of demand estimation may be products that differ by animal species, or products that differ in the amount of pet food, etc. Also, the subject of demand estimation may be products such as staple food or supplementary food, or wet or dry food, etc. Also, the subject of demand estimation may be products that differ by sex, products that differ depending on whether the animal is neutered or not, or products that differ depending on weight, etc.

[0125] Note that the items for which demand is estimated do not have to be the products listed in the examples above. For example, the products could be pet sheets, pet litter boxes, cat litter, etc.

[0126] [5-3. Posting Information] In the above embodiment, the target was information posted by users on social networking services (SNS), but the embodiment is not limited to this. For example, the posted information may be blogs, articles, messages, etc., posted by users.

[0127] Furthermore, the posted information may be still images or moving images. For example, the first extraction unit 132 may identify the actions of a person captured in still images or moving images based on the posted information such as still images or moving images. For example, the first extraction unit 132 may identify a child standing based on still images or moving images of a child. Also, the first extraction unit 132 may identify actions such as a child crawling on their stomach with their body dragging on the floor, crawling on all fours, or walking while touching a wall, based on still images or moving images of a child.

[0128] [5-4. Extraction process by the first extraction unit] In the above embodiment, an example was given in which the first extraction unit 132 extracts posted information containing information about a predetermined nonwoven fabric product from among the posted information posted on the network by users, but it is not limited to this. For example, the first extraction unit 132 may extract posted information containing keywords indicating the type of nonwoven fabric product. Alternatively, the first extraction unit 132 may extract posted information containing keywords indicating the product name or series name of a nonwoven fabric product sold by a predetermined manufacturer. In this way, the first extraction unit 132 can comprehensively extract posted information related to nonwoven fabric products.

[0129] [5-5. Extraction process by the second extraction unit] In the above embodiment, an example was given in which the second extraction unit 133 extracts posting information related to the use of nonwoven fabric products from the posting information extracted by the first extraction unit 132, but the embodiment is not limited to this. For example, the second extraction unit 133 may extract posting information that includes keywords indicating the date and time related to the user's actions, as posting information that includes information about the user's actions.

[0130] To give a more specific example, suppose a post containing wet wipes includes post information PO4. Here, post information PO4 is "Go on a picnic by 9 o'clock. Wet wipes are essential for a picnic." Furthermore, within post information PO4, "picnic" is a keyword indicating the user's action, and "9 o'clock" is a keyword indicating the date and time related to the user's action. In this case, the second extraction unit 133 extracts post information PO4 containing the date and time related to the user's action from the post containing wet wipes. As a result, the second extraction unit 133 can comprehensively extract post information containing various information related to the user's action. Note that the second extraction unit 133 is not limited to the above example, and may extract post information containing keywords indicating the season instead of the date and time.

[0131] Furthermore, the second extraction unit 133 may extract posted information that includes information about caregivers, such as children or elderly people, cared for by the user, instead of information about the user's behavior. For example, the second extraction unit 133 may extract posted information that includes keywords indicating caregivers cared for by the user. This allows the second extraction unit 133 to accurately extract posted information related to nonwoven fabric products that are presumed to be used by caregivers. Note that the caregiver may not be a human being, but may be a pet or other animal cared for by the user.

[0132] [5-6. Estimation Process (1)] In the above embodiment, the estimation unit 134 was described as estimating information regarding the manner in which users utilize nonwoven fabric products based on posted information regarding the use of nonwoven fabric products, but it is not limited to this. For example, the estimation unit 134 may further estimate information regarding the demand for each manner in which nonwoven fabric products are provided, based on the information regarding the manner of use.

[0133] For example, let's consider a case where the estimation unit 134 estimates that the location where users use wet wipes is outdoors, based on the posted information it extracts. In this case, the estimation unit 134 may estimate that there will be a high demand for small, portable packs, based on the information that the location of use is outdoors. Subsequently, based on the information that there is a high demand for small packs, the estimation unit 134 may estimate that the number of small packs sold at convenience stores will be increased as a means of providing small packs. For example, when a user goes outdoors, they may forget to bring wet wipes with them. In such cases, it is desirable for the user to be able to easily purchase wet wipes. Therefore, the estimation unit 134 estimates that the number of small packs sold at convenience stores will be increased.

[0134] On the other hand, let's explain an example in which the estimation unit 134 estimates that the location where users use wet wipes is indoors, based on the posted information extracted by the estimation unit 134. In this case, the estimation unit 134 may estimate that the demand for large-capacity packs will be high, based on the information that the location of use is indoors. Subsequently, based on the information that the demand for large-capacity packs is high, the estimation unit 134 may estimate that the number of large-capacity packs sold at supermarkets, drugstores, and e-commerce services will be increased as a means of providing large-capacity packs. For example, when users spend time indoors, such as at home, it is desirable to be able to purchase large-capacity packs of wet wipes that are suitable for wiping items placed in the home. Therefore, the estimation unit 134 estimates that the number of large-capacity packs sold at supermarkets, drugstores, and e-commerce services will be increased. As a result, the estimation unit 134 may further estimate information regarding the demand for each means of providing nonwoven fabric products, based on the information regarding the manner of use.

[0135] In this way, the estimation unit 134 further estimates information regarding the demand for each type of nonwoven fabric product based on information regarding usage patterns, thereby promoting the purchase of nonwoven fabric products at an appropriate time for the user.

[0136] [5-7. Estimation Process (2)] In the above embodiment, the estimation unit 134 was described as estimating information regarding how users utilize nonwoven fabric products based on posted information about the use of nonwoven fabric products, but it is not limited to this. For example, the estimation unit 134 may further estimate information regarding the demand for each product form of nonwoven fabric products based on changes in usage patterns.

[0137] For example, let's assume that the total number of posts extracted by the second extraction unit 133 is stored in the storage unit 120. In this case, the estimation unit 134 estimates whether the usage pattern has changed based on the total number of posts extracted by the second extraction unit 133 and the corresponding date and time. Here, let's assume that the usage pattern has changed. Specifically, let's assume that the location where the user uses wet wipes has changed from outdoors to indoors.

[0138] In this case, the estimation unit 134 may estimate that there is a high demand for large-capacity packs based on information such as a change in the location where users use wet wipes, from outdoors to indoors. In this way, the estimation unit 134 further estimates information regarding the demand for each product form of nonwoven fabric products based on changes in usage patterns, thereby enabling timely and accurate estimation of the demand for nonwoven fabric products.

[0139] [5-8. Other estimation processes] Furthermore, the estimation unit 134 may further estimate information regarding the demand for various products. For example, the estimation unit 134 may estimate information regarding the demand for products with different chemical components added to wet wipes.

[0140] To give a more specific example, let's consider a case where the estimation unit 134 estimates that the place of use is outdoors and that the user carries the wet wipes to the place of use. In this case, let's assume there are three types of wet wipes: one with a standard amount of alcohol added, one with a larger than standard amount of alcohol added, and one with no alcohol added. In this case, the estimation unit 134 may estimate that the demand for the wet wipes with a standard amount of alcohol added and the wet wipes with a larger than standard amount of alcohol added is higher than the demand for the wet wipes with no alcohol added.

[0141] Next, we will explain an example in which the estimation unit 134 estimates that the place of use is outdoors and that the user carries the wet wipes to the place of use. In this case, it is assumed that there is an outbreak of various infectious diseases. In this case, the estimation unit 134 may estimate that the demand for wet wipes with a larger-than-standard amount of alcohol added is higher than the demand for wet wipes with a standard amount of alcohol added. Alternatively, the estimation unit 134 may estimate that the demand for wet wipes with a standard amount of alcohol added is higher than the demand for wet wipes without alcohol added.

[0142] Next, we will explain an example in which the estimation unit 134 estimates that the place of use is outdoors and that the user carries the wet wipes to the place of use. In this case, it is assumed that there is an outbreak of various infectious diseases. Furthermore, it is assumed that there are two types of wet wipes: one with skin-protecting ingredients and a standard amount of alcohol, and another with a standard amount of alcohol. In this case, the estimation unit 134 may estimate that the demand for the wet wipes with skin-protecting ingredients and a standard amount of alcohol is higher than the demand for the wet wipes with a standard amount of alcohol. Such estimation processing can be implemented, for example, based on a table that associates actions during use, such as carrying the wipes, with products suitable for those actions.

[0143] As another example, the estimation unit 134 may estimate information regarding the demand for products with different types of openings on the wet wipe packaging. To give a more specific example, let's consider a case where the estimation unit 134 estimates that the place of use is outdoors and that the user carries the wet wipes to the place of use. In this case, let's assume there are products with a plastic lid on the opening of the wet wipe packaging and products with a seal-type lid on the opening of the wet wipe packaging. In this case, the estimation unit 134 may estimate that the demand for products with a seal-type lid on the opening of the wet wipe packaging is higher than the demand for products with a plastic lid on the opening of the packaging. For example, when a user goes outdoors, it is desirable for the user to be able to easily open the lid of the wet wipes. Therefore, the estimation unit 134 estimates that the number of products with a seal-type lid on the opening of the packaging will increase. Such estimation processing can be implemented, for example, based on a table that associates actions during use, such as carrying, with products with different types of openings suitable for such actions.

[0144] As another example, the estimation unit 134 may also estimate information regarding the demand for products with different sizes of wet wipes. To give a more specific example, let's consider a case where the estimation unit 134 estimates that the place of use is indoors. In this case, let's assume there are products with large wet wipe sizes and products with small wet wipe sizes. In this case, the estimation unit 134 may estimate that the demand for products with large wet wipe sizes is higher than the demand for products with small wet wipe sizes. For example, when a user spends time indoors, there is a need to wipe items such as tables and chairs. In such cases, it is desirable to use wet wipes of a size that can efficiently wipe items. Therefore, the estimation unit 134 estimates that the number of products with large wet wipe sizes will increase. Such estimation processing can be implemented, for example, based on tables, etc., that are associated with actions during use, such as spending time indoors, and products suitable for such actions.

[0145] The estimation process is not limited to the above example. For example, the estimation unit 134 may estimate whether the place of use is outdoors, indoors, or other locations such as inside a vehicle. The estimation unit 134 may also estimate whether the user of the wet wipes is not the user, but also a caregiver of the user. To give a more specific example, the estimation unit 134 may estimate any usage pattern, such as the user wiping the bottom of a child they are caring for, or the user carrying the wet wipes to the place of use and the child using the wet wipes. Such estimation of usage patterns can be realized using a table that associates predetermined usage patterns with the characteristics of the posted information, or a learning model that has been trained to estimate whether or not wet wipes are being used in a predetermined usage pattern in the input posted information.

[0146] [5-9. Integration with external services] Furthermore, the estimation unit 134 may further estimate information regarding the usage patterns of nonwoven fabric products by users based on various information obtained from external services. Here, external services refer to services that provide information such as temperature, atmospheric pressure, weather, pollen levels, and the degree of air pollution. For example, such services are provided by external servers managed by external businesses or the like. The acquisition process for obtaining information from external servers is implemented by APIs (Application Programming Interfaces) or the like.

[0147] For example, the estimation unit 134 obtains information such as temperature, atmospheric pressure, weather, pollen levels, and the degree of air pollution (e.g., the amount of PM2.5) from an external server. Subsequently, the estimation unit 134 may estimate information about how users use nonwoven fabric products based on the information such as temperature, atmospheric pressure, weather, pollen levels, and the degree of air pollution, as well as posted information regarding the use of nonwoven fabric products.

[0148] To give a more specific example, let's assume that the location of use is estimated to be "outdoors." In this case, the estimation unit 134 may estimate whether the user will carry wet wipes to the location of use based on the information that the location of use is outdoors and information such as temperature, atmospheric pressure, and weather obtained from an external server. For example, let's assume that the weather is clear. In this case, the estimation unit 134 may estimate that the user will carry wet wipes to the location of use based on the information that the location of use is outdoors and the information that the weather is clear.

[0149] In this case, the estimation unit 134 may estimate information regarding the demand for each product form of wet wipes based on information regarding usage patterns. To give a more specific example, suppose the product forms of wet wipes are small-capacity packs containing fewer than a predetermined number of wet wipes and large-capacity packs containing a predetermined number or more of wet wipes. In this case, the estimation unit 134 may estimate information regarding the demand for small-capacity packs and large-capacity packs based on information such as the usage location being outdoors, the weather being clear, and the user carrying the wet wipes to the usage location. For example, the estimation unit 134 may estimate that the demand for small-capacity packs, which are easy to use outdoors and easy to carry, is higher than the demand for large-capacity packs.

[0150] Furthermore, let's assume the weather is sunny followed by heavy rain. In this case, the estimation unit 134 may estimate that the user will not carry wet wipes to the usage location, based on the information that the usage location is outdoors and the information that the weather is sunny followed by heavy rain.

[0151] In this case, the estimation unit 134 may estimate that the demand for large-capacity packs is higher than the demand for small-capacity packs, based on information such as the location of use being outdoors, the weather being sunny followed by heavy rain, and the user not carrying wet wipes to the location of use.

[0152] As another example, suppose the location of use is presumed to be "outdoors." In this case, the estimation unit 134 may estimate whether or not the user will use a mask when carrying a designated product such as wet wipes to the location of use, based on the information that the location of use is outdoors and information such as the amount of pollen and the degree of air pollution obtained from an external server.

[0153] For example, suppose the amount of pollen and the degree of air pollution are both below a predetermined threshold. In this case, the estimation unit 134 may estimate, based on the information that the place of use is outdoors and the information that the amount of pollen and the degree of air pollution are both below a predetermined threshold, that the user will not use a mask when carrying the designated product, such as wet wipes, to the place of use.

[0154] In this case, the estimation unit 134 may estimate that the demand for masks will not increase based on information that the place of use is outdoors, information that the amount of pollen and the degree of air pollution are each below a predetermined threshold, and information that masks are not used.

[0155] Furthermore, it is assumed that either the amount of pollen or the degree of air pollution is above a predetermined threshold. In this case, the estimation unit 134 may estimate that the user will use a mask when carrying a predetermined product such as wet wipes to the place of use, based on the information that the place of use is outdoors and the information that either the amount of pollen or the degree of air pollution is above a predetermined threshold.

[0156] In this case, the estimation unit 134 may estimate that the demand for masks will increase based on information that the place of use is outdoors, information that either the amount of pollen or the degree of air pollution is above a predetermined threshold, and information that masks are used.

[0157] In this way, the estimation unit 134 estimates information regarding how users utilize nonwoven fabric products based on various information obtained from external services, thereby enabling a timely understanding of the demand for nonwoven fabric products.

[0158] [5-10. Instructions to Sales Staff] Furthermore, the business operator managing the information processing device 100 may use the information regarding the demand for various nonwoven fabric products estimated by the estimation unit 134 in its business activities. For example, the delivery processing unit 135 may transmit the information regarding the demand for various nonwoven fabric products to a server managed by a sales representative.

[0159] To give a more specific example, suppose it is estimated that the demand for small-capacity packs of wet wipes is higher than the demand for large-capacity packs. In this case, the delivery processing unit 135 transmits information that the demand for small-capacity packs is higher than the demand for large-capacity packs to a server managed by the sales representative. Subsequently, the sales representative may, based on the information that the demand for small-capacity packs is higher than the demand for large-capacity packs, select products to promote or expand or reduce the product display space (e.g., shelves) set up in retail stores. For example, the sales representative may select best-selling products among the small-capacity packs or expand the product display space for small-capacity packs.

[0160] In this way, sales personnel can conduct appropriate sales activities in response to the demand for various nonwoven fabric products. This allows the delivery processing unit 135 to facilitate efficient sales activities for sales personnel.

[0161] The above examples are not exhaustive, and the items for which demand is estimated may also be sanitary products. For example, suppose the location of use is estimated to be indoors based on the user's behavior. In this case, the delivery processing unit 135 may send information to a server managed by the sales representative indicating that there is high demand for panty-type products that prevent menstrual leakage or for longer-sized sanitary napkins. Alternatively, suppose the location of use is estimated to be outdoors based on the user's behavior. In this case, the delivery processing unit 135 may send information to a server managed by the sales representative indicating that there is high demand for products such as thin sanitary products that are not easily noticeable to third parties.

[0162] Furthermore, the product for which demand has been estimated may be children's diapers. For example, the location of use may be estimated to be outdoors based on the user's behavior. Also, the date and time may be estimated to be summer based on the date and time associated with the user's behavior. In this case, the delivery processing unit 135 may send information that there is a high demand for swim diapers to a server managed by the sales representative.

[0163] [5-11. Instructions for Production Technology] Furthermore, the business operator managing the information processing device 100 may use the information regarding the demand for various nonwoven fabric products estimated by the estimation unit 134 in its manufacturing operations, such as production technology. For example, the delivery processing unit 135 may transmit the information regarding the demand for various nonwoven fabric products to a server managed by the person in charge of production technology.

[0164] To give a more specific example, suppose it is estimated that the demand for small-capacity packs of wet wipes is higher than the demand for large-capacity packs. In this case, the distribution processing unit 135 transmits information that the demand for small-capacity packs is higher than the demand for large-capacity packs to a server managed by the production technology personnel. Subsequently, the production technology personnel may adjust the production of wet wipes to increase the production of small-capacity packs based on the information that the demand for small-capacity packs is higher than the demand for large-capacity packs.

[0165] In this way, the personnel in charge of production technology can make appropriate production adjustments in response to the demand for various nonwoven fabric products. As a result, the distribution processing unit 135 can enable the personnel in charge of production technology to make efficient production adjustments.

[0166] [5-12. Others] Of the processes described above as being performed automatically, all or part of them may be performed manually. Furthermore, all or part of the processes described as being performed manually may be performed automatically using known methods. In addition, the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed at will unless otherwise specified. For example, the various information shown in each drawing is not limited to the information illustrated.

[0167] Furthermore, each component of the illustrated device is a functional concept and does not necessarily have to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown. Moreover, each component may be configured by functionally or physically distributing and integrating all or part of it in any unit, depending on various loads and usage conditions.

[0168] Furthermore, the processes described above may be combined and executed as appropriate, provided they do not contradict each other.

[0169] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuits." For example, the estimation unit can be replaced with estimation means or estimation circuit.

[0170] [6. Hardware Configuration] Furthermore, the SNS server 10, the delivery company server 20, and the information processing device 100 according to the above-described embodiment are implemented by a computer 1000 having a configuration as shown in Figure 7. Figure 7 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic unit 1030, a cache 1040, a memory 1050, an output interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.

[0171] The arithmetic unit 1030 operates based on programs stored in the cache 1040 and memory 1050, as well as programs read from the input device 1020, and executes various processes. The cache 1040 is a cache that temporarily stores data used by the arithmetic unit 1030 for various calculations, such as RAM. The memory 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is implemented as ROM (Read Only Memory), HDD (Hard Disk Drive), flash memory, etc.

[0172] The output IF1060 is an interface for transmitting information to be output to output devices 1010 that output various types of information, such as monitors and printers. This interface may be implemented using connectors conforming to standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface). On the other hand, the input IF1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, and scanners. This interface may be implemented using USB, for example.

[0173] For example, the input device 1020 may be implemented by a device that reads information from optical recording media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), PDs (Phase Change Rewritable Disks), magneto-optical recording media such as MOs (Magneto-Optical disks), tape media, magnetic recording media, or semiconductor memory. Alternatively, the input device 1020 may be implemented by an external storage medium such as a USB memory stick.

[0174] The network IF1080 has the function of receiving data from other devices via network N and sending it to the arithmetic unit 1030, and also transmitting data generated by the arithmetic unit 1030 to other devices via network N.

[0175] Here, the arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or memory 1050 onto the cache 1040 and executes the loaded program. For example, if the computer 1000 functions as an information processing device 100, the arithmetic unit 1030 of the computer 1000 will realize the functions of the control unit 130 by executing the program loaded onto the cache 1040.

[0176] The embodiments of the present application have been described in detail above with reference to the drawings. However, these are illustrative examples, and the embodiments of the present application can be implemented in various forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention. [Explanation of Symbols]

[0177] N Network 1. Information Processing System 10 SNS Servers 20 Delivery company server 100 Information Processing Devices 110 Communications Department 120 Storage section 121 Post Information Storage Unit 122 Estimation result information storage unit 123 Product information storage section 130 Control Unit 131 Search Section 132 1st extraction part 133 Second extraction part 134 Estimation Department 135 Delivery Processing Department

Claims

1. A first extraction unit extracts information from user-submitted posts on the network that includes information about a specified nonwoven fabric product, A second extraction unit extracts, from the posted information extracted by the first extraction unit, posted information relating to the use of the nonwoven fabric product, Based on posted information regarding the use of the nonwoven fabric product, an estimation unit estimates information regarding the manner in which users use the nonwoven fabric product. Equipped with, The estimation unit, A relationship between the user's behavior estimated based on the usage pattern and the product form of the nonwoven fabric product suitable for that behavior, wherein information regarding the demand for each product form of the nonwoven fabric product is further estimated based on a predetermined relationship. An information processing device characterized by the following:

2. The first extraction unit is, As posted information containing information about the specified nonwoven fabric product, post information containing keywords indicating the nonwoven fabric product is extracted. The information processing apparatus according to feature 1.

3. The first extraction unit is, As posted information containing information about the specified nonwoven fabric product, post information containing keywords indicating the type of the nonwoven fabric product is extracted. The information processing apparatus according to claim 1 or 2.

4. The second extraction unit is, As posted information regarding the use of the aforementioned nonwoven fabric product, we extract posted information that includes information about the behavior of users who use the aforementioned nonwoven fabric product. The estimation unit, Based on posted information including information about the user's behavior, information about the user's usage of the nonwoven fabric product is estimated. The information processing apparatus according to any one of claims 1 to 3.

5. The second extraction unit is, As posted information containing information about the user's actions, post information containing keywords indicating the user's actions is extracted. The information processing apparatus according to feature 4.

6. The second extraction unit is, As posted information containing information about the user's actions, post information containing keywords indicating the date and time related to the user's actions is extracted. The information processing apparatus according to feature 5.

7. The second extraction unit is, As posted information containing information about the user's actions, post information containing keywords indicating the user's location is extracted. The information processing apparatus according to any one of claims 4 to 6.

8. The estimation unit, As information regarding the manner of use, information regarding the place of use, which is the place where the user uses the nonwoven fabric product, is estimated. The information processing apparatus according to any one of claims 1 to 7.

9. The estimation unit, The relationship between the place of use and whether or not the nonwoven product suitable for that place of use is to be carried there, and based on a predetermined relationship, the system further estimates whether or not the user will carry the nonwoven product to the place of use. The information processing apparatus according to feature 8.

10. The estimation unit, Further estimate the demand information for each product form, which differs in the number of nonwoven fabric products included in the aforementioned product form. The information processing apparatus according to feature 1.

11. The estimation unit, A relationship between the user's behavior estimated based on the usage pattern and the form of provision of the nonwoven fabric product suitable for that behavior, wherein information regarding demand for each form of provision of the nonwoven fabric product is further estimated based on a predetermined relationship. An information processing apparatus according to any one of claims 1 to 10.

12. The estimation unit, A relationship between the fluctuations in user behavior estimated based on the usage patterns and the product form of the nonwoven fabric product suitable for those fluctuations in behavior, wherein information regarding the demand for each product form of the nonwoven fabric product is further estimated based on a predetermined relationship. The information processing apparatus according to any one of claims 1 to 11.

13. The first extraction unit is, From the information posted on a designated SNS (Social Networking Service), information containing information about the nonwoven fabric product is extracted. The information processing apparatus according to any one of claims 1 to 12.

14. The system further includes a delivery processing unit that performs delivery processing for delivering nonwoven fabric products in product forms corresponding to the usage patterns estimated by the estimation unit. The information processing apparatus according to any one of claims 1 to 13.

15. A method of information processing performed by a computer, A first extraction step involves extracting information from user-submitted posts on the network that includes information about a specified nonwoven fabric product. A second extraction step is performed to extract, from the posted information extracted by the first extraction step, posted information relating to the use of the nonwoven fabric product, An estimation step of estimating information regarding the manner in which users use the nonwoven fabric product, based on posted information regarding the use of the nonwoven fabric product; Includes, The estimation process described above is: A relationship between the user's behavior estimated based on the usage pattern and the product form of the nonwoven fabric product suitable for that behavior, wherein information regarding the demand for each product form of the nonwoven fabric product is further estimated based on a predetermined relationship. An information processing method characterized by the following:

16. A first extraction procedure for extracting information from user-submitted posts on the network that contains information about a specified nonwoven fabric product, A second extraction procedure for extracting posts related to the use of the nonwoven fabric product from the post information extracted by the first extraction procedure, An estimation procedure for estimating information regarding the manner in which users use the nonwoven fabric product, based on posted information regarding the use of the nonwoven fabric product, and Have the computer run it, The estimation procedure described above is: A relationship between the user's behavior estimated based on the usage pattern and the product form of the nonwoven fabric product suitable for that behavior, wherein information regarding the demand for each product form of the nonwoven fabric product is further estimated based on a predetermined relationship. An information processing program characterized by the following features.

Images