Information processing system and information processing method

Abstract

To efficiently perform processing according to merchandise purchased by the same object person and prescription data.SOLUTION: In an information processing system, an information processor includes: a prescription data set describing prescribed medicines prescribed to a plurality of object persons; household item analytical model configured to extract purchase data from a purchase data set according to the purchase data set describing purchase histories of a plurality of first object persons with a certain prescribed medicine as an extraction condition, from among the prescribed medicines included in the prescription data set, and configured, using the extracted purchase data, to estimate a purchase history common to a part of the first object persons in the first object persons to all of whom the certain prescribed medicine is prescribed; and an output part configured to output the estimated purchase history common to the part of the first object persons. The purchase history includes: a purchase history by a personal purchase in which the first object person is a user of a purchased article; and a purchase history by a substitute purchase in which a family member of the first object person is the user of the purchased article.SELECTED DRAWING: Figure 8

Description

[Technical field]

[0001] The present disclosure relates to an information processing system and an information processing method. [Background technology]

[0002] There is known an estimation system capable of estimating the health condition of a corresponding individual without referring to the health checkup data of the individual (for example, see Patent Document 1). This estimation system constructs an estimation model for estimating the health condition of a second subject from the purchase history of the second subject, based on a health dataset describing the health conditions of a plurality of first subjects and a purchase dataset describing the purchase history of a plurality of first subjects. In recent years, drugstores that sell over-the-counter drugs (OTC drugs) and also retail daily necessities and foodstuffs are increasingly also affixing insurance pharmacies that dispense medicines based on prescriptions, and there are also an increasing number of cases where the parent company of a drugstore chain separately manages an insurance pharmacy chain, making it relatively easy to link purchase history at a drugstore with use of an insurance pharmacy. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6916367 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the estimation system described in Patent Document 1 does not take into consideration the fact that processing is performed based on the purchase history of purchases made by the same subject and prescription data describing prescription drugs.

[0005] The present disclosure has been made in consideration of the above circumstances, and aims to provide an information processing system etc. that can efficiently perform processing based on product and prescription data purchased by the same subject. [Means for solving the problem]

[0006] In one proposal, the information processing system is equipped with an estimation unit that extracts purchasing data from a prescription dataset describing prescription drugs prescribed for multiple subjects and a purchasing dataset describing the purchasing histories of multiple first subjects, using any of the prescription drugs included in the prescription dataset as an extraction condition, and uses the extracted purchasing data to estimate a purchasing history common to a portion of the first subjects for all first subjects for whom any of the prescription drugs are prescribed, and an output unit that outputs the estimated purchasing history common to the portion of first subjects, wherein the purchasing history includes a purchasing history made by the first subject himself / herself as a user of the purchase product, and a purchasing history made by proxy, wherein a family member of the first subject is a user of the purchase product.

[0007] In one proposal, the information processing system includes a model construction unit that constructs an estimation model for estimating a second subject who is predicted to develop in the future a disease corresponding to one of the prescription drugs included in a prescription dataset based on a prescription dataset describing prescription drugs prescribed to multiple subjects and a purchasing dataset describing the purchasing histories of multiple first subjects from the purchasing history of the second subject, a data acquisition unit that acquires purchasing data describing the purchasing history of the second subject, and an estimation unit that estimates the second subject who is predicted to develop in the future a disease corresponding to the prescription drug based on the purchasing history of the second subject described in the purchasing data and the estimation model, and the purchasing history includes a purchasing history made by personal purchases in which the first subject and the second subject are purchase users, and a purchasing history made by proxy purchases in which family members of the first subject and the second subject are purchase users. Effect of the Invention

[0008] According to the present disclosure, by using prescription data, it is possible to easily link it to daily necessities, etc. purchased by the subject, and efficiently make inferences regarding prescription medicines. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is an explanatory diagram showing an overview of a purchasing and dispensing system according to a first embodiment. [Diagram 2] 1 is a block diagram showing an example of the configuration of an information processing device; [Diagram 3] 11 is an explanatory diagram illustrating an example of the data layout of a consumer master table. [Figure 4] FIG. 13 is an explanatory diagram illustrating an example of the data layout of a purchase table. [Diagram 5] FIG. 13 is an explanatory diagram illustrating an example of the data layout of a prescription table. [Figure 6] FIG. 13 is an explanatory diagram illustrating an example of the data layout of a disease association table. [Figure 7] 11 is an explanatory diagram illustrating an example of the data layout of an advice history table; [Figure 8] 2 is a functional block diagram illustrating functional units included in a control unit of the information processing device. FIG. [Figure 9] 10 is a flowchart illustrating a processing procedure performed by a control unit of an information processing device. [Figure 10] FIG. 13 is an explanatory diagram illustrating an example of a display screen (disease report screen) showing disease report information. [Figure 11] FIG. 13 is an explanatory diagram illustrating an example of a display screen (disease report screen) showing disease report information. [Figure 12] FIG. 11 is an explanatory diagram regarding the generation process of a first learning model (disease-specific patient analysis engine) according to embodiment 2 (learning model). [Figure 13] FIG. 11 is an explanatory diagram regarding the generation process of a second learning model (disease awareness optimization engine). [Figure 14] 2 is a functional block diagram illustrating functional units included in a control unit of the information processing device. FIG. [Figure 15]10 is a flowchart illustrating a processing procedure performed by a control unit of an information processing device. [Figure 16] 13 is an explanatory diagram illustrating an example of a display screen (consumer report screen) showing consumer report information. FIG. [Figure 17] FIG. 13 is an explanatory diagram illustrating an example of a display screen showing report information for pharmaceutical companies. [Figure 18] 13 is a flowchart illustrating a processing procedure by a control unit of an information processing device according to embodiment 3 (post-medication follow-up). [Figure 19] FIG. 13 is an explanatory diagram illustrating a method for creating a member master table with family information in accordance with the fourth embodiment. [Figure 20] 13 is an explanatory diagram regarding a duplication process in which duplicated purchase histories are included in a purchase data set for the number of family members. FIG. [Figure 21] FIG. 13 is an explanatory diagram illustrating an example of a reference table (family structure). [Figure 22] FIG. 13 is an explanatory diagram illustrating analysis data (ID-POS analysis) used to create a reference table. [Diagram 23] FIG. 13 is an explanatory diagram illustrating an example of a reference table (disease correspondence). [Figure 24] FIG. 11 is an explanatory diagram illustrating a purchasing data set (copied for the number of family members and with a determination result attached). [Diagram 25] 11 is a flowchart illustrating a processing procedure (purchase data set and report generation) performed by a control unit of the information processing device. [Figure 26] FIG. 13 is an explanatory diagram illustrating an example of the analysis results (extraction of the number of purchasers for each product category among all patients and visitors). [Figure 27] FIG. 13 is an explanatory diagram regarding a process of specifying common purchase history and attribute information (attribute values ​​of target drug and patient) according to the fifth embodiment. [Figure 28] FIG. 13 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (proportion of patients receiving the target drug). [Figure 29] FIG. 13 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (regression analysis results). [Diagram 30]FIG. 13 is an explanatory diagram regarding a process for identifying common purchase history and attribute information (cluster analysis). [Diagram 31] FIG. 13 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (purchase history of a patient for a target drug). [Diagram 32] This is an explanatory diagram regarding the process of identifying common purchase history and attribute information (products that are easy for patients using the target drug to purchase: lift value of purchase frequency). [Diagram 33] This is an explanatory diagram regarding the process of identifying common purchasing history and attribute information (products that are easy for patients using the target drug to purchase: lift value of purchase rate). [Diagram 34] This is an explanatory diagram regarding the process of identifying common purchase history and attribute information (products that the target drug patient began to purchase before their first visit). [Diagram 35] FIG. 13 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (results of decision tree analysis). [Diagram 36] FIG. 13 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (regression analysis results). DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] (Embodiment 1) Fig. 1 is an explanatory diagram showing an overview of a purchasing and dispensing system S (information processing system) according to embodiment 1. Fig. 2 is a block diagram showing an example of the configuration of an information processing device 1. The purchasing and dispensing system S is configured with the information processing device 1 as a main device (server), and the information processing device 1 is communicably connected to a store server TS and an insurance pharmacy server HS via an external network N such as the Internet.

[0011] The store server TS is a server that manages sales at a store such as a drug store. The information processing device 1 acquires purchase data of products such as daily necessities purchased by consumers at the store from the store server TS. That is, the purchase data is related to products that consumers can purchase at the store. In this embodiment, the products are, for example, daily necessities such as OTC drugs, health foods, supplements, foodstuffs, health equipment, cosmetics, pet supplies, stationery, clothing, and nursing care products. The purchase data of the daily necessities (products) includes the names and quantities of these various daily necessities, the name of the store where the purchase was made, date data indicating the time of purchase, and an identification number such as a store membership number or card number that uniquely identifies the consumer. A purchase data set is configured by aggregating the purchase data of multiple consumers.

[0012] The insurance pharmacy server HS is, for example, a server that manages the dispensing operations of an insurance pharmacy. The insurance pharmacy is intended to be a pharmacy such as an insurance pharmacy. The information processing device 1 acquires prescription data related to a prescription received by a consumer at the insurance pharmacy from the insurance pharmacy server HS. The prescription data can identify the prescription drug prescribed to the consumer, and is, for example, a prescription issued based on a doctor's diagnosis, a dispensing fee statement (dispensing receipt) issued in response to dispensing at the insurance pharmacy, or a medical fee statement for a medical institution to bill a health insurance association for medical expenses. A prescription data set is configured by aggregating the prescription data of multiple consumers. The prescription data may be at least one of prescription data and dispensing fee statement (dispensing receipt) data, or a combination of these data.

[0013] The information processing device 1 stores the purchase data and prescription data acquired from the store server TS and the insurance pharmacy server HS in association with each other, thereby saving and managing information regarding the correlation between daily necessities such as OTC drugs purchased by each consumer and the prescription drugs prescribed (dispensed) by each consumer. The information processing device 1 further generates report information including various analysis results using the purchase data and prescription data associated with each consumer, and outputs the report information to the store server TS and the insurance pharmacy server HS.

[0014] The information processing device 1 may be further communicably connected to an external server GS via an external network N. The external server GS is a server operated and managed by each company, such as an advertising agency, an insurance company, or a pharmaceutical company, and the information processing device 1 may provide various data to the advertising agency or the like that operates and manages the external server GS by outputting various data generated by the information processing device 1 to each of the external servers GS.

[0015] The information processing device 1 includes a control unit 2, a storage unit 3, and a communication unit 4. The control unit 2 includes one or more central processing units (CPUs), micro-processing units (MPUs), and graphics processing units (GPUs). The information processing device 1 performs various information processing, control processing, and the like by reading and executing a program P (program product) stored in the storage unit 3.

[0016] The storage unit 3 includes a volatile storage area such as a static random access memory (SRAM), a dynamic random access memory (DRAM), a flash memory, etc., and a non-volatile storage area such as an EEPROM or a hard disk. The storage unit 3 stores in advance a program P (program product) and data to be referenced during processing. The program P (program product) stored in the storage unit 3 may be a program P (program product) read from a recording medium 31 readable by the information processing device 1. Alternatively, the program P (program product) may be downloaded from an external computer (not shown) connected to a communication network (not shown) and stored in the storage unit 3.

[0017] The storage unit 3 may store a purchase and dispensing DB 300 that stores and manages the acquired purchase data and prescription data in association with each other. The purchase and dispensing DB 300 includes, for example, a consumer master table, a purchase table, a dispensing table, a disease correspondence table, and an advice history table. Details of these various tables will be described later.

[0018] The communication unit 4 is a communication interface for communicating with the store server TS, the insurance pharmacy server HS, the external server GS, etc., via the Internet, etc., by wire or wirelessly.

[0019] 3 is an explanatory diagram illustrating an example of the data layout of a consumer master table. The consumer master table includes, as management items (metadata), for example, a consumer ID, a purchasing membership number, an insurer number, a name, a sex, a date of birth, and an email address.

[0020] The item of consumer ID stores ID information for uniquely identifying a consumer who is registered (subscribed) to the purchasing and dispensing system S. The consumer ID may be set as a primary key.

[0021] The purchasing membership number field stores a number included in the purchasing data, such as the membership number registered at the store or the credit card number used at the time of purchase. The number (purchasing membership number) identifies the consumer in the purchasing data.

[0022] The insurer number field stores, for example, the insurer number and the insured person number (including the branch number) contained in the prescription data (e.g., dispensing fee statement, etc.). The number (the insurer number and the insured person number including the branch number) identifies the consumer of the prescription data. Consumers who are not insured and do not have an insurer number are assigned a temporary number equivalent to the insurer number and used as the insurer number.

[0023] The name field stores the name of the resident. The gender field stores the gender of the resident. The date of birth field stores the date of birth of the resident. It goes without saying that the current age of the resident is calculated by using the date of birth. The email address field stores the email address of the resident. The resident master table may further include various attribute information such as physical attributes such as the height and weight of the resident, regional information of the place of residence, nationality, family structure, and occupation. These various attribute information correspond to the attribute data of the resident. An attribute data set is configured by aggregating the attribute data of multiple residents. The attribute data may further include browser search history data by the resident or behavior data on the Internet. The control unit 2 of the information processing device 1 may acquire the attribute data from the insurance pharmacy server HS, the store server TS, or the external server GS. When acquiring the attribute data from the insurance pharmacy server HS, the attribute data may be configured as a part of the prescription data. The residents whose attribute data are stored in the residents master table include residents who are registered in the information processing system in this embodiment as having been prescribed prescription drugs, and unregistered residents. Residents who are registered in the information processing system as having been prescribed prescription drugs correspond to the first target. Unregistered residents who are registered in the information processing system as having been prescribed prescription drugs and for whom prescription data of the prescription drug of the extraction condition is not registered correspond to the second target. In addition, unregistered residents (second target) who are not registered in the prescription data of the prescription drug of the extraction condition include residents who are not registered in the prescription data of any prescription drug, and residents who are not registered in the prescription data of the prescription drug of the extraction condition but are registered in the prescription data of the prescription drug (other prescription drug) other than the extraction condition. In this case, the above-mentioned second target is a resident who is not registered in the prescription data of the prescription drug of the extraction condition, and it is possible that the presence or absence of registration of the prescription data of the prescription drug other than the extraction condition is not taken into consideration.Alternatively, the second subject may be a consumer whose prescription data of the extraction condition prescription drug is not registered, and the second subject may be further classified according to whether or not prescription data of other prescription drugs (prescription drugs other than the extraction condition) is registered. In this case, the second subject is classified into a second subject whose prescription data of other prescription drugs (prescription drugs other than the extraction condition) is registered (a person who has received a prescription for any prescription drug) and a second subject whose prescription data of any prescription drug is not registered (a person who has not received a prescription for any prescription drug). When performing various analysis processes, etc. on a second subject whose prescription data of the extraction condition prescription drug is not registered, the information processing device 1 may further perform the analysis processes, etc. by taking into consideration (subdividing) the classification of the second subject (whether or not the second subject has not received a prescription for any prescription drug).

[0024] Fig. 4 is an explanatory diagram illustrating an example of the data layout of a purchasing table. The purchasing table includes, as management items (metadata), for example, a purchasing membership number, purchase date and time, household goods, names and quantities of household goods, store names, and POS machine numbers. A purchasing data set is constructed by aggregating these management items (metadata) of multiple consumers. The purchasing membership number field stores the purchasing membership number included in the purchasing data, and is associated with consumer IDs, etc. managed in the consumer master table.

[0025] The purchase date and time item stores the purchase date and time (year, month, date, time) included in the purchase data, that is, the date and time data when the daily necessities were purchased.

[0026] The item of daily necessities stores detailed information of daily necessities, including OTC drugs, health foods, supplements, foodstuffs, cosmetics, pet supplies, stationery, clothing, nursing care supplies, and general daily necessities, included in the purchase data. The detailed information of daily necessities may include, for example, the name, type, classification, and quantity of each of these daily necessities, and may be saved as object data in an XML file. By saving the detailed information of daily necessities in this way as an XML file, it is possible to parse the information using extended tags used in XML and extract the names and quantities of OTC drugs and other items included in the daily necessities.

[0027] The store name field stores the store name included in the purchase data, i.e., the name of the store where the daily necessities were purchased. When the control unit 2 of the information processing device 1 acquires the purchase data, it extracts the above-mentioned various data from the purchase data and registers them in the purchase table.

[0028] FIG. 5 is an explanatory diagram illustrating an example of the data layout of the dispensing table. The dispensing table includes, as management items (metadata), for example, the insurer number, dispensing date and time, insurance pharmacy name, prescription drug, YJ code (individual drug code), quantity, dosage, prescription period, and disease. A prescription data set is constructed by aggregating these management items (metadata) of multiple consumers. The insurer number item stores the insurer number and the insured person number including the branch number included in the prescription data, and is associated with the consumer ID, etc. managed in the consumer master table.

[0029] The dispensing date and time item stores the dispensing date and time (year, month, date, time) included in the prescription data, that is, the date and time data when the prescription was dispensed at the insurance pharmacy based on the prescription.

[0030] The insurance pharmacy name field stores the name of the insurance pharmacy included in the prescription data.

[0031] The prescription drug item stores the name of the prescription drug included in the prescription data. The prescription drug stored in this item may be a medical drug, including those used by a doctor or dentist, or those used by prescription or instruction.

[0032] The disease item stores the disease corresponding to the prescription drug stored in the same record. The correspondence between the prescription drug and the disease is defined in a disease correspondence table described later. When the control unit 2 of the information processing device 1 acquires prescription data, it extracts the above-mentioned various data from the prescription data and registers them in the dispensing table.

[0033] 6 is an explanatory diagram illustrating an example of the data layout of a disease correspondence table. The disease correspondence table includes, for example, prescription drugs and diseases as management items (metadata). The prescription drug item stores the names of various prescription drugs. The disease item stores diseases corresponding to prescription drugs stored in the same record.

[0034] The control unit 2 of the information processing device 1 can identify the disease corresponding to the prescription drug included in the prescription data by referring to the disease correspondence table (using it as a look-up table). In the disease correspondence table, the correspondence between the prescription drug and the disease is not limited to the case where a disease is identified by a single prescription drug, but may be the case where any disease is identified by a combination of multiple prescription drugs. The data on the correspondence between the prescription drug and the disease included in the disease correspondence table may be updated by periodically acquiring the data from, for example, a pharmaceutical company's server.

[0035] 7 is a diagram illustrating an example of the data layout of an advice history table. The advice history table includes, as management items (metadata), items (fields) of, for example, a consumer ID, advice date and time, and advice information.

[0036] The consumer ID field stores the consumer ID defined in the consumer master table.

[0037] The advice date and time field stores the date and time (year, month, date, time) when advice information for a consumer (consumer ID) stored in the same record was output.

[0038] In the item of advice information, advice information (content data) for a resident stored in the same record is stored. The advice information (content data) may be saved as object data in a file in PDF format, for example.

[0039] In this embodiment, the consumer ID, which is the primary key of the consumer master table, is used to associate the purchasing member number, which is the primary key of the purchasing table, with the insurer number, which is the primary key of the dispensing table. This allows the purchasing data registered in the purchasing table of each consumer to be associated with the prescription data and diseases registered in the dispensing table, and to be stored and managed. The normalization configuration of each table in this embodiment (schema of the purchasing and dispensing DB300) is one example for the purpose of associating these data, and is not limited thereto, and it goes without saying that the purchasing and dispensing DB300 may have a table configuration different from that of this embodiment.

[0040] 8 is a functional block diagram illustrating functional units included in the control unit 2 of the information processing device 1. The control unit 2 of the information processing device 1 executes a program stored in the storage unit 3 to function as an acquisition unit 21, a disease identification unit 22, a DB registration unit 23, a daily necessities analysis model 24, a disease report generation unit 25, and an output unit 26.

[0041] The acquisition unit 21 acquires, for example, purchase data from the store server TS and prescription data from the insurance pharmacy server HS. For example, in the case of a store such as a drug store that has both daily necessities including OTC drugs and a dispensing section where prescriptions are dispensed, the purchase data and prescription data may be acquired from the sales management server of the drug store. The acquisition unit 21 outputs the acquired data to other functional units that handle subsequent processes, such as the disease identification unit 22.

[0042] The disease identification unit 22 extracts the name or classification code of the prescription drug included in the prescription data from the acquisition unit 21, and identifies the disease corresponding to the name of the prescription drug by, for example, referring to a disease correspondence table. The prescription data is, for example, a dispensing fee statement issued by an insurance pharmacy, and can identify the prescription drug prescribed to the consumer. Although the dispensing fee statement does not state the disease of the patient (consumer) to whom the prescription was issued, by using the disease correspondence table, it is possible to reverse-look up the disease, i.e., the disease name, which is the name of the disease, from the prescribed prescription drug.

[0043] The DB registration unit 23 associates the purchase data and prescription data from the acquisition unit 21 with the disease identified by the disease identification unit 22, and registers them, for example, in the purchase and dispensing DB 300. The purchase data and prescription data include identification information for identifying a consumer, and the identification information included in the purchase data is a purchase membership number, and the identification information included in the prescription data is an insured person number including an insurer number and a branch number.

[0044] The DB registration unit 23, for example, by referring to the consumer master table, extracts a consumer ID corresponding to the purchasing member number included in the purchase data and the insured number including the insurer number and the sub-number included in the prescription data, thereby identifying a consumer registered in the purchase and dispensing system S. Based on the identified consumer ID, the DB registration unit 23 retrieves and registers attribute information of the consumer, such as date of birth, sex, height, weight, regional information of the residence, nationality, family structure, occupation, whether the prescription is new or not, browser search history data, behavior data on the Internet, etc., from the consumer master table as attribute data. The DB registration unit 23 registers the purchase data in the purchase table and the prescription data and the expected disease in the dispensing table, so that these data are associated and stored. When the table configuration of the purchase and dispensing DB 300 is normalized as described above, the purchase data registered in the purchase table and the prescription data and disease registered in the dispensing table are associated with each other by the consumer ID defined in the consumer master table and the purchasing member number and the insurer number corresponding to the consumer ID.

[0045] In the purchase and dispensing DB300, prescription data, purchase data, and attribute data of the same consumer are registered, and these data include date information (date and time of dispensing the prescription (within 4 days including the date of issuance)) and date and time of purchase of daily necessities such as OTC drugs. This makes it possible to identify the temporal relationship (chronological element) between the purchase of daily necessities and the dispensing of the prescription for each individual consumer based on the date information. For example, it is possible to identify the purchase history of daily necessities such as OTC drugs purchased before the dispensing of the prescription based on the time of dispensing of the prescription. This makes it possible to derive a correlation or causal relationship between the purchase history of daily necessities such as OTC drugs and the issued prescription. In addition, by identifying the purchase history of daily necessities such as OTC drugs purchased after the dispensing of the prescription, it is possible to derive and grasp the situation of combined use of prescription drugs and OTC drugs.

[0046] The disease report generating unit 25 generates disease report information using purchase data, prescription data, disease, and attribute data extracted (searched) from the purchased and dispensed medicine DB 300 using predetermined extraction conditions (search conditions). The extraction conditions may include, for example, the type of disease (prescription medicine). The disease report generating unit 25 may input the purchase data into the daily necessities analysis model 24 to obtain an analysis result regarding the purchase data, and generate disease report information including the analysis result. The disease report information may be displayed, for example, as a disease report screen. The disease report screen (disease report information) will be described in detail later.

[0047] The daily necessities analysis model 24 is an estimation unit that receives purchase data and attribute data extracted according to the extraction conditions from the disease report generation unit 25 as input data, and outputs the results of an analysis process that estimates purchase history and attribute information for the data. This makes it possible to estimate purchase history and attribute information common to a portion of subjects out of all subjects who meet the extraction conditions (e.g., disease type (prescription drugs)). The daily necessities analysis model 24 may be configured, for example, by an unsupervised learning model having a function of clustering (cluster analysis) or association analysis.

[0048] When the daily necessities analysis model 24 has a clustering function, purchasing data including purchasing histories of daily necessities and attribute data, etc. are inputted into the daily necessities analysis model 24, which outputs information regarding groupings (categorised daily necessities and attributes) inherent in the purchasing data and attribute data, etc. When the daily necessities analysis model 24 has an association analysis function, purchasing data and attribute data, etc. are inputted into the daily necessities analysis model 24, which outputs analysis results regarding trends in attribute information included in the purchasing data and attribute data, etc., trends in daily necessities, or correlations among a plurality of daily necessities. The daily necessities analysis model 24 is not limited to cluster analysis or association analysis, and may perform various analytical processes such as statistical analysis such as Bayesian analysis or principal component analysis.

[0049] By inputting purchase data and attribute data of multiple consumers (group of consumers) who have developed a specific disease into the daily necessities analysis model 24, it is possible to analyze the purchase history of multiple consumers (patients) who have developed the disease for each attribute until prescription drugs corresponding to the disease are dispensed, that is, until prescription data including the prescription drugs are obtained. That is, by aggregating purchase data and attribute data of multiple consumers for each disease classification using the search function of the purchase and dispensing DB 300 and inputting the aggregated purchase data for each disease classification into the daily necessities analysis model 24, it is possible to obtain analysis results such as graphs or numerical values ​​of changes in purchasing behavior (purchasing trends) before and after prescription for each disease classification for each attribute. As a result, it is possible to grasp the purchasing tendency of daily necessities such as OTC drugs until a prescription is issued for each disease classification for consumers who have developed a disease, and it is possible to grasp the patient journey for each attribute from the perspective of purchasing the daily necessities.

[0050] The output unit 26 outputs the disease report information from the disease report generating unit 25, for example, to the insurance pharmacy server HS of the insurance pharmacy that provided the prescription data and the store server TS of the store that provided the purchase data. The output unit 26 further outputs the disease report information to, for example, an external server GS of an advertising agency, an insurance company, or a pharmaceutical company. When outputting the disease report information to these external servers GS, the output unit 26 may exclude personal information that identifies the resident from the disease report information. By outputting the disease report information that excludes personal information and has anonymity to the external servers GS used by advertising agencies, insurance companies, pharmaceutical companies, etc., these related companies can efficiently use the disease report information according to their respective business types. In addition, predicted information on the current and future progression of the disease state of the first subject may be output together with information on purchasing behavior corresponding to the disease state.

[0051] 9 is a flowchart illustrating a processing procedure performed by the control unit 2 of the information processing device 1. The control unit 2 of the information processing device 1 acquires purchase data (S101). The control unit 2 of the information processing device 1 acquires the purchase data from, for example, a store server TS that manages sales in a store such as a drugstore.

[0052] The control unit 2 of the information processing device 1 acquires the prescription data (S102). The control unit 2 of the information processing device 1 acquires the prescription data from, for example, an insurance pharmacy server HS that manages the dispensing operations of the insurance pharmacy.

[0053] The control unit 2 of the information processing device 1 identifies a disease that is expected from the prescription data (S103). For example, the control unit 2 of the information processing device 1 refers to a disease correspondence table stored in the storage unit 3, and identifies a disease that corresponds to a prescription drug included in the prescription data such as a dispensing fee statement.

[0054] The control unit 2 of the information processing device 1 stores the purchase data and the prescription data in association with each other (S104). For example, the control unit 2 of the information processing device 1 registers the purchase data in a purchase table, and registers the prescription data and the identified disease in a prescription table. The purchasing member number included in the purchase data and the insured person number including the insurer number and the sub-number included in the prescription data are linked by the consumer ID in the consumer master table, so that the purchase data and the prescription data of the same consumer can be stored in association with each other. At this time, the attribute data linked by the consumer ID is retrieved from the consumer master table and registered. Note that the attribute data may be the date of birth, sex, etc. included in the prescription data.

[0055] The control unit 2 of the information processing device 1 outputs disease report information based on the associated and stored purchasing data, prescription data, etc. (S105). The control unit 2 of the information processing device 1 generates disease report information using the purchasing data, prescription data, disease and attribute data extracted (searched) from the purchasing and dispensing DB 300 using a predetermined extraction condition. The extraction condition may be set, for example, based on the gender, age group, or residential area of ​​the resident.

[0056] FIG. 10 is an explanatory diagram illustrating a display screen (disease report screen) showing disease report information. When outputting the disease report information, the control unit 2 of the information processing device 1 generates screen data constituting the disease report screen showing the disease report information, and outputs the generated screen data to the store server TS and the insurance pharmacy server HS. Alternatively, the control unit 2 of the information processing device 1 may use a web server function to display the disease report screen on a mobile terminal of an associate of the store or insurance pharmacy. The disease report screen includes, for example, an extraction condition area showing extraction conditions for extracting (searching) data from the purchased and dispensed medicine DB 300, and a list display area for displaying the extraction results in a list.

[0057] In the extraction condition area, extraction conditions for the purchase and dispensing DB 300 are displayed in order to specify the purchase data and prescription data that are the subject of the disease report information. The extraction conditions include, for example, the period of dispensing date and time, the age range of the subject residents, sex, type of disease (prescription drug), and region.

[0058] The list display area includes, as examples of display items, prescription data (prescription drugs), diseases, number of applicable residents, number of people using OTC drugs concomitantly, concomitant use rate, analysis results, and history data. The prescription data (prescription drugs) item displays the name of the prescription drug dispensed based on the prescription. The disease item displays the disease corresponding to the prescription drug, and the disease is identified, for example, from a disease correspondence table.

[0059] The number of applicable consumers field displays the number of consumers with the relevant disease among those extracted using the set extraction conditions. The number of people using concomitant OTC drugs field displays the number of consumers with the relevant disease who purchased OTC drugs. The concomitant use rate field displays the percentage of consumers who purchased the OTC drug in question, based on the number of consumers with the relevant disease.

[0060] In the analysis result item, a link for displaying a pop-up analysis result display screen is displayed. By clicking the link, an analysis result display screen including analysis results such as cluster analysis and association analysis on the purchase data of consumers who have the corresponding disease (for each disease classification) is displayed. The cluster analysis result includes information on the grouping of daily necessities (classified daily necessities) in the purchase data of multiple consumers who have the corresponding disease (same disease). The association analysis result includes information on the association or correlation between daily necessities in the purchase data of multiple consumers who have the corresponding disease (same disease). The analysis result display screen allows the user to grasp the statistical analysis results of the purchase data of multiple consumers who have the disease for each individual disease or prescription drug. This allows the user to grasp the matters related to the patient journey of each consumer leading up to the onset of the disease from a statistical perspective.

[0061] In the history data section, a link to pop up a purchase history display screen is displayed. Clicking on the link displays a purchase history display screen that includes the purchase history included in the purchase data of the consumer with the corresponding disease, such as the purchase date and time, purchased daily necessities, and the store where the purchase was made. This makes it possible to understand the purchase history of each consumer up until the onset of the disease for each individual disease or prescription drug.

[0062] 11 is an explanatory diagram illustrating a display screen (disease report screen) showing disease report information. The control unit 2 of the information processing device 1 generates and outputs the disease report screen using various display forms such as the disease report screens exemplified in FIG. 10 and FIG. 11.

[0063] The disease report screen illustrated in FIG. 11 shows, for example, the purchase history and attribute information of a consumer who has been prescribed a prescription drug based on the target disease drug information input to the information processing device 1. The control unit 2 of the information processing device 1, for example, identifies a prescription drug based on the specified target disease drug information, and displays a cluster analysis of multiple consumers who have been prescribed the prescription drug, a distribution of attributes, and changes in purchasing behavior before and after prescription in a graph or table format. The attributes of the consumer may include, for example, the gender, age group, and whether the prescription is new or not for these multiple consumers. The control unit 2 of the information processing device 1 may further include, in the disease report screen, a diagram that visualizes the patient journey and purchasing trends as a disease-specific patient analysis based on the specified target disease drug information.

[0064] According to this embodiment, the control unit 2 of the information processing device 1 registers prescription data and purchase data for the same consumer using the consumer's identification number, for example, in the purchase and dispensing DB 300, and stores the prescription data and purchase data in association with each other. This makes it possible to create and utilize the purchase and dispensing DB 300, which includes prescription data for each consumer and purchase data for daily necessities including OTC drugs, and to build a base environment for providing consumers with comprehensive information on medicine in general.

[0065] According to this embodiment, prescription data and purchase data by the same consumer are registered in the purchase and dispensing DB 300, and both of these data include date information, such as the purchase date and time of daily necessities such as OTC drugs. The control unit 2 of the information processing device 1 identifies a chronological element that is a temporal relationship between the purchase of daily necessities and the dispensing (issuance) of a prescription for each individual consumer based on the date information, and can derive a correlation between the purchase history of daily necessities such as OTC drugs and the issued prescription based on the dispensing of the prescription. In addition, by identifying the purchase history of daily necessities such as OTC drugs purchased after the dispensing of the prescription, it is possible to derive (understand) the combined use status of prescription drugs and OTC drugs. The purchase history includes a purchase history by the first subject who is a purchase user and a purchase history by proxy purchase by the first subject's family who is a purchase user.

[0066] According to this embodiment, disease report information including associated purchasing data and prescription data, etc. is output to the insurance pharmacy that provided the prescription data and the store that provided the purchasing data, thereby enabling these insurance pharmacies or stores to support their medical awareness activities when they conduct such activities to raise awareness about medicine for consumers. (Embodiment 2)

[0067] FIG. 12 is an explanatory diagram regarding the generation process of the first learning model 201 according to the second embodiment (learning model). The control unit 2 of the information processing device 1 uses training data for the first learning model 201 to train, for example, a neural network, and generates the first learning model 201 that receives purchasing data of a resident as input and outputs information about a disease in the resident. The information about the disease includes, for example, the disease and the probability (possibility) of the disease occurring. That is, the first learning model 201 (disease model) functions as a disease-specific patient analysis engine that outputs the occurrence probability of each disease in the resident based on the input purchasing data of the resident.

[0068] The training data includes question data and answer data, where each purchase data of an individual consumer corresponds to the question data, and the diseases corresponding to the prescription drugs included in the prescription data of the consumer correspond to the answer data. The question data is composed of purchase data, i.e., information on the purchase history of daily necessities. Alternatively, the question data may include physical attributes such as the consumer's age, sex, height, and weight in addition to the purchase data. The answer data is composed of diseases identified based on prescription data with a dispensing date and time that is later than the last purchase date and time included in the purchase data. This makes it possible to establish a correlation between the purchase history of daily necessities and issued prescriptions over time.

[0069] The purchase data used as the problem data may be data from a predetermined period, such as up to one year ago, based on the prescription data dispensing date and time. In this way, by determining the retroactive period (how many years ago data is used) of the purchase data used as the problem data based on the prescription data dispensing date and time, it is expected that the accuracy of the answer data can be improved. The retroactive period of the purchase data may be different depending on the classification of the prescription drug included in the prescription data. These data can be aggregated based on sales management data of a store such as a drugstore that has a dispensing corner that dispensing medicines based on prescriptions, including daily necessities including OTC medicines, and a prescription, and the training data can be generated using the sales management data. The purchase and dispensing system S in this embodiment includes a purchase and dispensing DB300 that associates and stores (saves and manages) the purchase data and prescription data, so that the control unit 2 of the information processing device 1 can efficiently generate training data using the data stored in the purchase and dispensing DB300.

[0070] The dataset of question data and answer data contained in the training data for learning a learning model, such as the first learning model 201, is synonymous with the dataset of input data and output data when using the learning model (such as learning model 101), and if it is defined in either dataset, it naturally applies to the other dataset.

[0071] The neural network (first learning model 201) trained using the training data is expected to be used as a program module that is part of artificial intelligence software. The first learning model 201 (disease model) is used in the information processing device 1 equipped with the control unit 2 (CPU, etc.) and memory unit 3 as described above, and is executed in the information processing device 1 having such calculation processing capabilities to form a neural network system. That is, the control unit 2 of the information processing device 1 performs calculations to extract features of the purchase data input to the input layer according to instructions from the first learning model 201 stored in the memory unit 3, and outputs information related to the disease from the output layer.

[0072] The first learning model 201 (disease model) is, for example, configured by a DNN (Deep Neural Network), and has an input layer that accepts input of purchase data, an intermediate layer that extracts features of the purchase data, and an output layer that outputs information about the disease. The input layer has a plurality of neurons that accept input of character strings and values ​​included in the purchase data, and passes the input values ​​to the intermediate layer. The intermediate layer is defined using an activation function such as a ReLU function or a sigmoid function, has a plurality of neurons that extract features of each input value, and passes the extracted features to the output layer. Parameters such as weighting coefficients and bias values ​​of the activation function are optimized using an error backpropagation method. The output layer is, for example, configured by a fully connected layer, and outputs information about the disease based on the features output from the intermediate layer. Alternatively, the output layer may be, for example, configured by a softmax layer, and outputs the probability for each of a plurality of types of diseases (the possibility of occurrence for each type of disease).

[0073] In this embodiment, the first learning model 201 (disease model) is a DNN, but is not limited to this, and may be a first learning model 201 (disease model) constructed with other learning algorithms, such as neural networks other than DNN, transformers, BERT, GPT, RNN (Recurrent Neural Network), LSTM (Long-short term model), CNN, SVM (Support Vector Machine), Bayesian networks, linear regression, regression trees, multiple regression, random forests, and ensembles.

[0074] FIG. 13 is an explanatory diagram regarding the generation process of the second learning model 202. The control unit 2 of the information processing device 1 uses training data for the second learning model 202 to train, for example, a neural network, and generates the second learning model 202 that inputs the purchase data of a resident and outputs advice information for the resident. The advice information includes, for example, a disease awareness schedule for dealing with a disease that is likely to occur in the future, lifestyle improvement content, and the like. Furthermore, in a case where the purchase data includes an OTC drug, the advice information may include a suggestion to switch from the OTC drug to a prescription drug dispensed based on a prescription. In this way, the advice information is output as a disease awareness optimization program, and the disease awareness optimization program includes at least one of product information optimal for improving the disease state and information that encourages the resident to change his or her lifestyle. That is, the second learning model 202 (advice model) functions as a disease awareness optimization engine that outputs advice to raise awareness of measures against a disease of concern in the resident based on the input purchase data of the resident.

[0075] The training data includes question data and answer data, and each purchase data of an individual consumer corresponds to the question data, and advice information for the consumer corresponds to the answer data. The question data is composed of purchase data, i.e., information on the purchase history of daily necessities (product name, quantity, purchase date and time of daily necessities such as OTC drugs). Alternatively, the question data may include physical attributes such as the consumer's age, sex, height, and weight in addition to the purchase data.

[0076] The advice information, which is the answer data, may be generated in the purchase and dispensing DB 300 based on the prescription data associated with the purchase data, which is the problem data. The control unit 2 of the information processing device 1 may generate advice information including content suggesting switching to the prescription drug based on the type of prescription drug included in the prescription data, for example. In the second learning model 202, as in the first learning model 201, the retroactive period of the purchase data used as the problem data, that is, how many years ago the data to be used, may be determined based on the dispensing date and time of the prescription data. Alternatively, the control unit 2 of the information processing device 1 may refer to correspondence information including lifestyle improvement items for the intake amount of foodstuffs, etc. included in the purchase data, and configure the advice information using the lifestyle improvement items. As in the first learning model 201, the control unit 2 of the information processing device 1 may efficiently generate training data for the second learning model 202 using data stored in the purchase and dispensing DB 300, and train and generate the second learning model 202 using the training data.

[0077] The second learning model 202 (advice model) is, for example, configured with a DNN (Deep Neural Network), and has an input layer that accepts input of purchase data, an intermediate layer that extracts features of the purchase data, and an output layer that outputs advice information. The input layer has a plurality of neurons that accept input of character strings and values ​​contained in the purchase data, and passes the input values ​​to the intermediate layer. The intermediate layer is defined using an activation function such as a ReLU function or a sigmoid function, has a plurality of neurons that extract features of each input value, and passes the extracted features to the output layer. Parameters such as the weighting coefficient and bias value of the activation function are optimized using an error backpropagation method. The output layer is, for example, configured with a fully connected layer, and outputs advice information based on the features output from the intermediate layer.

[0078] In this embodiment, the second learning model 202 is a DNN, but is not limited to this, and may be a second learning model 202 constructed with other learning algorithms, such as a neural network other than a DNN, similar to the first learning model 201.

[0079] 14 is a functional block diagram illustrating functional units included in the control unit 2 of the information processing device 1. The control unit 2 of the information processing device 1 executes a program stored in the storage unit 3 to function as an acquisition unit 21, a first learning model 201 (disease-specific patient analysis engine), a disease assumed person determination unit 27, a second learning model 202 (disease awareness optimization engine), a consumer report generation unit 28, and an output unit 26.

[0080] The acquisition unit 21 acquires purchase data from, for example, the store server TS. The acquisition unit 21 extracts the purchasing member number included in the purchase data, and identifies the resident of the purchasing member number. Based on the identified resident ID, the acquisition unit 21 retrieves and registers the attribute information of the resident, such as date of birth, sex, height, weight, regional information of the place of residence, nationality, family structure, occupation, whether the prescription is new or not, browser search history data, behavior data on the Internet, etc., as attribute data from the resident master table in the purchase and dispensing DB 300. From this attribute data, it is possible to know whether the resident is an unregistered resident for whom the prescription drug of the extraction condition has not yet been registered. As for the unregistered resident for whom the prescription drug of the extraction condition has not been registered, as described above, the prescription data of the prescription drug of the extraction condition itself is unregistered, and it is also possible to not take into consideration whether the prescription data of the prescription drug (other prescription drug) other than the extraction condition has been registered. The unregistered consumer refers to a consumer who does not have prescription data registered within a specified period, such as the past year, prior to the purchase date and time included in the purchase data. This includes consumers who are registered in the information processing system as having been prescribed prescription drugs, and unregistered consumers in this embodiment. A consumer who is registered in the information processing system as having been prescribed prescription drugs corresponds to a first subject. An unregistered consumer who is not registered in the information processing system as having been prescribed prescription drugs corresponds to a second subject. The purchase history includes a purchase history of personal purchases in which the first subject and the second subject are purchase users, and a purchase history of proxy purchases in which the family members of the first subject and the second subject are purchase users.

[0081] Among the consumers registered in the purchasing and dispensing system S, data on unregistered consumers is stored only in the purchasing table of the purchasing and dispensing DB 300, and is not stored in the dispensing table. The processing in this embodiment is, as an example, processing for the unregistered consumers, but the same processing may also be performed for registered consumers.

[0082] As described above, the first learning model 201 is a model construction unit that constructs an estimation model that estimates the possibility of prescription drugs being prescribed to a subject from a purchase history, using a prescription dataset describing prescription drugs prescribed to the subject and a purchase dataset describing the purchase history of the same subject. By inputting the purchase data from the acquisition unit 21, information regarding diseases in the resident (unregistered resident) of the purchase data is output. The information regarding the disease is information indicating the possibility of the resident (unregistered resident) developing a disease within a predetermined period, such as within one year from the present time. The first learning model 201 may output the possibility (degree of certainty) for each type of disease based on the input purchase data.

[0083] The disease assumed person determination unit 27 is an estimation unit that, together with the first learning model 201, as a disease-specific patient analysis engine, estimates whether or not a resident (a resident who is not registered for the prescription drug of the extraction condition) corresponds to a disease assumed person based on information on the disease output by the first learning model 201. Since the estimation unit performs processing based on the prescription drug specified as the extraction condition, even if a resident is prescribed any prescription drug, a resident who is not prescribed the prescription drug specified as the extraction condition corresponds to an unregistered resident, and therefore becomes a target for estimation by the estimation unit as to whether or not the resident corresponds to a disease assumed person. When the first learning model 201 outputs the possibility (accuracy) for each type of disease, if the value of the possibility for any type of disease is lower (less than) a predetermined value, the disease assumed person determination unit 27 determines that the possibility of any disease occurring in the unregistered resident in the future is low. In this case, the unregistered resident is determined not to correspond to a disease assumed person. When the probability value for one or more types of disease is equal to or greater than a predetermined value, the disease suspected person determination unit 27 determines that the unregistered resident is highly likely to develop a disease whose probability value is equal to or greater than a predetermined value in the future. In this case, the unregistered resident is determined to be a person suspected of having a disease. The predetermined value may be set again to satisfy a desired number of subjects while checking the number of subjects who are suspected to develop a disease corresponding to the prescription drug in the disease suspected person determination unit in the future.

[0084] Based on the result of the determination, the disease assumed person determination unit 27 controls the input of purchase data, etc. to the second learning model 202. In other words, if it is determined that the person is a disease assumed person, the purchase data of the disease assumed person (a consumer who is not registered for the prescription drug of the extraction condition) is input to the second learning model 202.

[0085] The second learning model 202 is an enlightenment evaluation unit and an enlightenment change unit, and outputs advice information for a disease assumed person (a consumer who has not registered the prescription drug of the extraction condition) based on the judgment result of the disease assumed person judgment unit 27. The advice information may include, for example, a schedule or contents in accordance with disease awareness.

[0086] The consumer report generating unit 28 is a disease awareness unit that generates consumer report information based on the advice information output by the second learning model 202 and the purchase data of the disease assumed person (a consumer who is not registered for the prescription drug of the extraction condition). The consumer report information may be displayed as a consumer report screen, for example, and includes a patient awareness program and a plan / content. The consumer report screen (consumer report information) will be described in detail later.

[0087] The output unit 26 outputs the consumer report information from the consumer report generating unit 28, for example, to the insurance pharmacy server HS of the insurance pharmacy that provided the prescription data and the store server TS of the store that provided the purchase data. The output unit 26 may further output the consumer report information to, for example, an external server GS of an advertising agency, an insurance company, or a pharmaceutical company. When outputting the consumer report information to these external servers GS, the output unit 26 may output attribute information, such as age, sex, height, weight, and place of residence, from the consumer report information, excluding personal information that identifies the consumer (a person suspected of having a disease). Alternatively, the output unit 26 may directly output and transmit the consumer report information to the consumer who is the subject of the consumer report information by transmitting the consumer report information to the email address of the consumer who is the subject of the consumer report information. Furthermore, the output unit 26 may output the conditions of the purchase pattern of a person without a registered prescription who is expected to become ill in the future as attribute information of a second subject.

[0088] 15 is a flowchart illustrating a processing procedure by the control unit 2 of the information processing device 1. The control unit 2 of the information processing device 1 acquires purchase data (S201). The control unit 2 of the information processing device 1 acquires the purchase data from the store server TS, similar to S101 in the first embodiment.

[0089] The control unit 2 of the information processing device 1 may identify a consumer based on a purchasing membership number included in the acquired purchasing data, and if the consumer is an unregistered consumer who has not yet registered the prescription drug that meets the extraction criteria, the control unit 2 of the information processing device 1 may refer to the dispensing table, and if there is no prescription registered before the purchase date and time included in the purchasing data, i.e., no registered prescription data, within a specified period, such as the past year, determine that the consumer of the purchasing data is unregistered.

[0090] The control unit 2 of the information processing device 1 determines whether the consumer of the purchasing data corresponds to a person with a suspected disease as a disease-specific patient analysis engine (S202). The control unit 2 of the information processing device 1, for example, inputs the acquired purchasing data to the first learning model 201, and acquires information on diseases in the consumer of the purchasing data output by the first learning model 201. The first learning model 201 may output the possibility (probability) of occurrence of each type of disease based on the input purchasing data.

[0091] When the first learning model 201 outputs the possibility (degree of certainty) for each type of disease, if the possibility value for any type of disease is lower (less than) a predetermined value, the control unit 2 of the information processing device 1, as a disease-specific patient analysis engine, determines that the resident of the purchasing data does not correspond to a person suspected of having a disease. If the possibility value for one or more types of diseases is equal to or greater than a predetermined value, the control unit 2 of the information processing device 1 determines that the resident of the purchasing data corresponds to a person suspected of having a disease.

[0092] When it is determined that the person corresponds to a person suspected of having a disease (S202: YES), the control unit 2 of the information processing device 1 derives advice information based on the purchase data, etc. (S203). For example, the control unit 2 of the information processing device 1 inputs the acquired purchase data to the second learning model 202 and acquires the advice information output by the second learning model 202, thereby deriving advice information for the consumer of the purchase data. The advice information may include, for example, a schedule or content in accordance with disease awareness, and further, if the purchase data includes OTC drugs, may include a suggestion to switch from the OTC drugs to prescription drugs dispensed based on a prescription.

[0093] The control unit 2 of the information processing device 1 outputs consumer report information including advice information, etc. (S204). The control unit 2 of the information processing device 1 generates consumer report information based on the advice information output by the second learning model 202 and the purchase data of the assumed disease individual, and outputs it to, for example, the insurance pharmacy server HS of the insurance pharmacy that provided the prescription data and the store server TS of the store that provided the purchase data.

[0094] The consumer report information output to the insurance pharmacy server HS or the store server TS may be made into disease awareness materials such as leaflets or flyers and distributed to consumers who visit the insurance pharmacy or store. Alternatively, the consumer report information may be sent by email or the like to a mobile device of a consumer via the insurance pharmacy server HS or the store server TS. Alternatively, the consumer report information may be distributed using an electronic prescription notebook.

[0095] FIG. 16 is an explanatory diagram illustrating a display screen (consumer report screen) showing consumer report information. When outputting consumer report information, the control unit 2 of the information processing device 1 generates screen data constituting the consumer report screen showing the consumer report information, and outputs the generated screen data to the store server TS and the insurance pharmacy server HS. Alternatively, the control unit 2 of the information processing device 1 may use a web server function to display the consumer report screen on a mobile terminal of an associated person of the store or insurance pharmacy. The consumer report screen includes, for example, a consumer item area showing bibliographic items of the target consumer, a purchase history area showing the purchase history of the consumer, and an advice information display area showing advice information for the consumer.

[0096] The consumer information area displays the bibliographic information of the target consumer, including the consumer ID, purchasing membership number, insurer number, name, etc. The purchase history area displays the target consumer's purchase history in list form, including purchase date and time, purchased household goods, and purchased stores, etc. The advice information display area displays advice information derived based on the purchase history.

[0097] If it is determined that the person does not fall under the category of a person suspected of having a disease (S202: NO), or after executing the process of S204, the control unit 2 of the information processing device 1 stores the determination result, etc. (S205). The control unit 2 of the information processing device 1 stores the advice information generated according to the determination result, etc., in the storage unit 3, for example, by registering it in an advice history table. The control unit 2 of the information processing device 1 may also register the determination result for a person determined not to fall under the category of a person suspected of having a disease, for example, in the advice history table. In this case, the advice information item in the advice history table may store a determination result (determination result) that the person does not fall under the category of a person suspected of having a disease, such as non-applicability.

[0098] The control unit 2 of the information processing device 1 may generate a disease awareness report for a pharmaceutical company based on the result of this process, and output the report to an external server GS used by the pharmaceutical company. FIG. 17 is an explanatory diagram illustrating a display screen showing report information for a pharmaceutical company. The display screen showing report information for a pharmaceutical company (report screen for a pharmaceutical company) includes, for example, an area showing the status of consultation recommendation (acquisition of new patients) and an area showing the status of medication continuation follow-up as a verification report. In the consultation recommendation area, the type of disease awareness program included in the advice information, the number of subjects of each disease awareness program, the number of people with prescriptions, and the number of new patients are displayed in list form. In the medication continuation follow-up area, the type of disease awareness program included in the advice information, the number of subjects who continue to take medication for each disease awareness program, and the number of people who continue to take medication are displayed in list form.

[0099] The control unit 2 of the information processing device 1 calculates the number of relevant residents for each piece of advice information generated according to the type of disease of the resident, based on the type of disease awareness program included in the advice information, and calculates the respective number of residents to be displayed on the report screen for the pharmaceutical company. In this way, by generating a report including the counted result of the number of target residents for each disease awareness program as a disease awareness report for the pharmaceutical company and outputting it to the pharmaceutical company's external server GS, it is possible to efficiently provide the pharmaceutical company with useful information.

[0100] According to this embodiment, the control unit 2 of the information processing device 1 can efficiently generate the first learning model 201 by training a neural network using, for example, the purchasing data and prescription data registered in the purchasing and dispensing DB 300. The control unit 2 of the information processing device 1 can derive information on the disease of the unregistered resident by inputting the purchasing data of the unregistered resident who has not registered the prescription drug of the extraction condition into the first learning model 201. The information on the disease includes the possibility of developing the disease in the future. The first learning model 201 may derive the possibility for each type of disease according to the classification (type) of the disease corresponding to each prescription data. In this way, by using the first learning model 201 trained using the data registered in the purchasing and dispensing DB 300, information (information on the disease) including the possibility of the unregistered resident developing the disease in the future can be derived for the unregistered resident who does not currently have a registered prescription.

[0101] According to this embodiment, the control unit 2 of the information processing device 1 can derive advice information for a person (a person with a disease) who is likely to develop a disease in the future, based on the purchase data of the person with a disease, by using the second learning model 202. The advice information may include, for example, a suggestion to switch from an OTC drug included in the purchase data of the person with a disease to a prescription drug dispensed based on a prescription.

[0102] According to this embodiment, the control unit 2 of the information processing device 1 generates consumer report information including advice information for the suspected disease person and purchase data on which the advice information is based, and outputs the consumer report information to the insurance pharmacy that provided the prescription data and the store that provided the purchase data. By outputting or disclosing the consumer report information to the insurance pharmacy or store, it is possible to support the insurance pharmacy or store in providing efficient advice to the suspected disease person. The control unit 2 of the information processing device 1 may further remove personal information that identifies the consumer (suspected disease person) from the consumer report information, and output or disclose the consumer report information from which the personal information has been removed to an advertising agency, an insurance company, or a pharmaceutical company.

[0103] (Embodiment 3) 18 is a flowchart illustrating a processing procedure by the control unit 2 of the information processing device 1 according to the third embodiment (post-medication follow-up). The control unit 2 of the information processing device 1 identifies the person who is assumed to have a disease and who is the target of the output advice information (S301). The control unit 2 of the information processing device 1 identifies the person who is assumed to have a disease and who is the target of the output advice information (resident ID) by, for example, referring to the advice history table.

[0104] The control unit 2 of the information processing device 1 judges whether or not prescription data of the identified patient has been acquired after the advice information was output (S302). The control unit 2 of the information processing device 1 judges whether or not prescription data of the patient who is the subject of the advice information has been registered in the purchased dispensing DB 300 (dispensing table) after the output date and time of the advice information, for example, by referring to the advice history table and dispensing table of the purchased dispensing DB 300. In this way, by utilizing the purchased dispensing DB 300, it is possible to verify whether or not prescription data for the patient has been acquired, that is, whether or not the patient has been diagnosed by a doctor or the like and a prescription has been registered, after the advice information for the patient has been output.

[0105] When the prescription data is not acquired (S302: NO), the control unit 2 of the information processing device 1 re-learns (updates) the second learning model 202 (S303). When the prescription data is not acquired, that is, when the prescription has not been dispensed within a predetermined period, such as one month, since the advice information was output, the control unit 2 of the information processing device 1, as an enlightenment evaluation unit, determines that the usefulness of the output advice information is low. The control unit 2 of the information processing device 1 may re-learn, transfer learn, fine tune, or the like, and update the second learning model 202 as an enlightenment change unit in order to improve the advice information. In the purchase and dispensing DB300, data for the above-mentioned predetermined period is additionally registered after the previous advice information was output. The control unit 2 of the information processing device 1 may re-learn the second learning model 202 using training data regenerated by updating the advice information, which is the answer data of the second learning model 202, by using the purchase and dispensing DB300 with the latest data registration status. In this case, it is preferable that the change related to the advice information includes a change in at least one of the content of the advice information, the time when the advice information is output, and the means for outputting the advice information.

[0106] The control unit 2 of the information processing device 1 re-outputs the consumer report information (S304). The control unit 2 of the information processing device 1 generates advice information again using the re-learned (updated) second learning model 202, and outputs (re-outputs) the generated advice information again in the same manner as in process S204 of the second embodiment.

[0107] When prescription data is acquired (S302: YES), the control unit 2 of the information processing device 1 outputs follow-up information (S3021). When prescription data is acquired, that is, when a prescription is dispensed within a predetermined period, such as one month, after the advice information is output, the control unit 2 of the information processing device 1, as an enlightenment evaluation unit, determines that the usefulness of the output advice information is high. The control unit 2 of the information processing device 1 may then generate follow-up information, such as a reminder, so that the consumer who is the subject of the advice information continues to receive prescriptions in the future, and output the information to the insurance pharmacy server HS of the insurance pharmacy that provided the prescription data and the store server TS of the store that provided the purchase data.

[0108] The follow-up information output to the insurance pharmacy server HS may be made into disease awareness materials such as leaflets or flyers and distributed to consumers who visit the insurance pharmacy. Alternatively, the follow-up information may be sent by email or the like to a mobile device of a consumer via the insurance pharmacy server HS. Alternatively, the follow-up information may be distributed using an electronic prescription notebook. By distributing flyers or the like generated using the follow-up information to consumers who visit the insurance pharmacy, it is possible to improve adherence by the consumer.

[0109] After executing the process of S3021 or S304, the control unit 2 of the information processing device 1 ends a series of processes in this flow. By performing such processes, the control unit 2 of the information processing device 1 functions as an enlightenment evaluation unit that evaluates the advice information based on the prescription data set prescribed after the advice information is output, and an enlightenment change unit that changes the advice information depending on the evaluation result. The control unit 2 of the information processing device 1 that functions as the enlightenment change unit may change the advice information, as well as the timing of outputting the advice information, or the means for outputting the advice information, when re-outputting the consumer report information.

[0110] According to this embodiment, the control unit 2 of the information processing device 1 continues the process of acquiring prescription data and purchase data, and registering these data in the purchase and dispensing DB 300 in association with each other. The control unit 2 of the information processing device 1 outputs advice information for any of the disease assumed persons (residents), for example, to a store that provided the purchase data, and then determines whether or not the prescription data of the disease assumed person (resident) has been acquired. If the prescription data of the disease assumed person (resident) has not been acquired, the control unit 2 of the information processing device 1 determines that the output advice information is of low usefulness. The control unit 2 of the information processing device 1 may update the second learning model 202 by re-learning, transfer learning, fine tuning, or the like, in order to improve the advice information determined to be of low usefulness. This allows the quality of advice information to be continuously improved.

[0111] When the prescription data of the person suspected of having a disease (resident) is acquired, the control unit 2 of the information processing device 1 determines that the output advice information is highly useful. The control unit 2 of the information processing device 1 may output notification information (follow-up information) for the person suspected of having a disease (resident) after a predetermined period of time to the insurance pharmacy that provided the prescription data. By outputting such notification information (follow-up information), it is possible to support the person suspected of having a disease to continue taking prescription medicines appropriately.

[0112] (Embodiment 4) FIG. 19 is an explanatory diagram illustrating a method of creating a family information-attached member master table (extension of the consumer master table) according to the fourth embodiment. In the family information-attached member master table in this embodiment, the relationship between the purchaser (member ID) of a product (daily necessities) and the family of the purchaser (member ID) is defined. The family information-attached member master table may be an extended version of the consumer master table in the first embodiment. In this case, the family information-attached member master table may include all the management items of the consumer master table in the first embodiment and may also include the patient ID (insurer number) of the family of the consumer (consumer ID) in the management items. The control unit 2 of the information processing device 1 generates the family information-attached member master table based on, for example, the patient list of the acquired prescription prescription, the family structure, and the list of the family members' names, dates of birth, and gender. The control unit 2 of the information processing device 1 may store and manage the patient list of the acquired prescription prescription, the family structure, the list of the family members' names, dates of birth, and gender, and the family information-attached member master table in the purchase and dispensing DB 300 as an attribute data set.

[0113] The patient list of the prescription includes the patient ID (e.g., insurer number), name, sex, and date of birth. The list of family structure and names, dates of birth, and sex of family members includes the member ID (e.g., member ID of a point card at a store), the person's name, sex, date of birth, and the name, sex, and date of birth of each of the person's (member ID) family members, i.e., information on the family structure of the first subject (member of the point card) identified by the member ID. The control unit 2 of the information processing device 1 associates the member ID indicating the person with the patient ID according to the identity between the name and date of birth according to the member ID (person) and the name and date of birth according to the patient ID. The control unit 2 of the information processing device 1 associates the member ID indicating the person with the patient ID of each of the family members of the member ID (person) according to the identity between the name and date of birth of each of the associated family members of the member ID (person) and the name and date of birth according to the patient ID. The control unit 2 of the information processing device 1 generates a member master table with family information by associating the member ID (self) with the patient ID of the self and the patient ID of each of the self's family members. The control unit 2 of the information processing device 1 can grasp the correspondence relationship between the purchaser (self) of a product (daily necessities) indicated by the member ID and the patient ID of the purchaser (self) and each of the purchaser's (self) family members, based on the member master table with family information, the patient list of prescription prescriptions, and the attribute data set consisting of information contained in the family composition and the list of family members' names, birth dates, and genders.

[0114] 20 is an explanatory diagram of a duplication process for including duplicated purchase histories for the number of family members in a purchasing data set. The control unit 2 of the information processing device 1 can obtain information on the purchase history of a purchaser (self) of a product (daily necessities) indicated by a member ID by acquiring POS data, for example, and can generate a purchasing data set by aggregating the purchase histories of multiple purchasers (self). In the purchasing data set thus generated from POS data, etc., the control unit 2 of the information processing device 1 generates duplicate data for the purchase history (purchase data indicating purchased products) of the purchaser (self) for the number of family members of the purchaser (self), and adds the generated duplicate data to the purchasing data set.

[0115] In the illustrated embodiment, the control unit 2 of the information processing device 1 adds duplicate data for the number of family members (5 people) of the person (member ID: Drug07011) to the purchasing data set for the purchase history (purchase data indicating purchased products) of the person (member ID: Drug07011) for the product (product name: product0001). As a result, the number of purchase history records (purchase data indicating purchased products) of the person (member ID: Drug07011) for the product (product name: product0001) becomes 6 records, including the person and the number of family members (5 people). In the purchasing data set to which duplicate data for the number of family members has been added in this way, a classification defining whether each record is for the person (member) or family is set as a management item. In other words, if the product purchasers Receipt00003 (member ID: Drug07011) and Receipt00107, Receipt02010, etc. are family members, the control unit 2 of the information processing device 1 will copy (duplicate) the purchasing history of Receipt00003 (Drug07011) "the purchaser" and link them, and also assign a category (member (the purchaser) or family) so that they can be distinguished.

[0116] FIG. 21 is an explanatory diagram illustrating a reference table (family structure). In the storage unit 3 of the information processing device 1, reference information used to determine whether a purchase history is a purchase by the person himself or a purchase by proxy is stored, for example, in a table format (reference table). In the reference table (table for determining proxy purchase), a plurality of records according to the family structure of the first subject are associated with each of the daily necessities included in the purchase history, and each of the records includes information regarding the probability of a personal purchase for the first subject and the probability of a proxy purchase for the family of the first subject. The reference table (table for determining proxy purchase) configured in this manner includes, as management items, for example, purchased product, respondent (product purchaser), family_1, family_1 gender and age, family_2, family_2 gender and age, and the purchase probability of each person, such as the person himself (purchase probability), husband (purchase probability), wife (purchase probability), and child (purchase probability).

[0117] The purchased item management item stores the name of the item (daily necessities) that is the subject of proxy purchase judgment. The purchased item management item in the reference table may store the names of all items (daily necessities) included in the purchase data set. The respondent (product purchaser) stores the gender and age (gender and age), which are attributes of the actual purchaser (first target person (member of the point card)) of the item (daily necessities). The family_1 management item stores the relationship of the family members of the respondent (product purchaser), and the family_1 gender and age management item stores the gender and age (gender and age) of the family members. In this embodiment, the number of members of a family is two (family_1, family_2), but is not limited to this, and may be three or more (family_n: n≧3). As the purchase probability of each person, the purchase probability of each family member according to the family structure of the respondent (product purchaser) is stored in the self (purchase probability), husband (purchase probability), wife (purchase probability), and child (purchase probability). The control unit 2 of the information processing device 1 may calculate a purchase probability indicating for whom the product is purchased, using the product (daily necessities) and purchaser attributes as keys.

[0118] For each household item included in the purchase history, in this embodiment, a record (four records in this embodiment) according to the number of types of expected family structures is associated with a specific product (purchased product: product 0001). That is, for the same product (purchased product: product 0001), multiple records are associated based on the attributes (gender and age) and family structure of the actual purchaser of the product (household item) (first target person (point card member)), and each record indicates the purchase probability for each family member.

[0119] FIG. 22 is an explanatory diagram illustrating analysis data (ID-POS analysis) used to create a reference table. The control unit 2 of the information processing device 1 may use, for example, ID-POS analysis data when creating a reference table. The analysis data includes, for example, data on the composition ratio of the number of purchasers by gender and age, and data on the purchase rate by gender and age (what percentage of 100 people purchase). The data on the composition ratio of the number of purchasers by gender and age indicates the purchase rate by gender and age for each product. This allows the tendency of the attributes (gender, age) of the main purchasers for each product to be grasped and used to create a reference table. The purchase rate by gender and age (what percentage of 100 people purchase) indicates which products are purchased by customers who visit a store, as a purchase rate (for example, what percentage of 100 people purchase) according to the attributes (gender, age) of the customers. This allows the probability of what attributes purchase the product to be quantified and used to create a reference table.

[0120] Alternatively, the control unit 2 of the information processing device 1 may acquire information on the family structure of the actual purchaser of the product (daily necessities) and for whom the purchaser made the purchase, based on the results of a hearing from the purchaser when the actual purchaser (first target person (member of a point card)) joins a member of a store or the like or when purchasing a product, and generate a reference table using the acquired information. Alternatively, the control unit 2 of the information processing device 1 may acquire (estimate) attributes of the user of the product (daily necessities) from a word-of-mouth site such as an SNS or online sales, and generate a reference table using the acquired information. Alternatively, the control unit 2 of the information processing device 1 may acquire product information from a sales company of the product (daily necessities), confirm who the product is intended to be used by, and generate a reference table using the acquired information. Alternatively, the control unit 2 of the information processing device 1 may generate a reference table using an analysis result of an image captured by an AI camera or the like installed in a store (purchasing by the purchaser himself (for example, long viewing time) or purchasing by proxy (for example, short viewing time) depending on the length of viewing time).

[0121] By using a reference table (proxy purchase determination table) according to family structure in this way, the control unit 2 of the information processing device 1 can efficiently determine whether a purchase of a product by a first subject (e.g., a member of a point card) is a personal purchase by the first subject who is the purchaser (target purchaser) or a proxy purchase by a family member of the first subject who is the purchaser (target purchaser). Furthermore, in the case of a proxy purchase, the control unit 2 of the information processing device 1 can efficiently determine which family member the product purchase is for.

[0122] FIG. 23 is an explanatory diagram illustrating an example of a reference table (disease matching). The reference table may further include information on disease matching of any family member in addition to family structure. The reference table taking into account disease matching further includes management items for diseases of the product purchaser (purchaser attribute) and each family member (family_1, family_2). The management items for diseases of the product purchaser (purchaser attribute) and each family member store the presence or absence of a disease in each person, and if a disease is present, the type of the disease. The management items for each person's purchase probability store a purchase probability according to the presence or absence of a disease, and for example, a relatively high value is set for the purchase probability of a specific product (purchased product) for a person with a specific disease.

[0123] The control unit 2 of the information processing device 1, for example, confirms a purchasing pattern that a person with a specific disease is more likely to purchase a specific product than the general customer population, based on the analysis results of prescriptions (prescription data set) and purchase data (purchase history). By using a reference table that reflects the confirmation results and takes into account disease compatibility, the control unit 2 of the information processing device 1 can estimate that if a family member of the first subject (point card member) who is the product purchaser has a family member with the specific disease, the purchase is for that person (a family member).

[0124] 24 is an explanatory diagram illustrating a purchasing data set (copied for the number of family members and with a determination result attached). The control unit 2 of the information processing device 1 performs the processing described above to generate a purchasing data set (a purchasing data set for which a proxy purchase determination has been made) in which the purchasing history is copied for the number of family members and a determination result is attached to one of them. The purchasing data set (a purchasing data set for which a proxy purchase determination has been made) includes, as management items, for example, patient ID, gender, age, member ID, purchase date, receipt number, product name, quantity, amount, category, family structure, relationship to the member, and user (proxy purchase determination).

[0125] In the management items, the association between the patient ID and the member ID, etc., is as explained in Fig. 20 etc., and the management item of the patient ID stores, for example, the health insurance card number, and the member ID stores, for example, the member number (member ID of the point card) of the store where the product is purchased, etc. The gender and age stores the gender and age (attributes) of the person specified by the patient ID (the patient himself / herself or his / her family member).

[0126] The purchase date, receipt number, product name, quantity, amount, and category store each item corresponding to the purchased product. The family structure management item stores the family structure of the person identified by the patient ID (the patient himself / herself or his / her family members). The relationship management item from the member's perspective stores the relationship (the patient himself / herself, husband, wife, children, etc.) indicating the family relationship with the person identified by the member ID (the member (point card member) who purchased the product). The user (proxy purchase determination) management item stores the result of the proxy purchase determination performed based on the reference table in the purchase history (purchase data) of the patient himself / herself and the purchase history (purchase data) copied for the patient's family. In this embodiment, a record marked with a circle indicates that it is a record of the user who purchased the product.

[0127] FIG. 25 is a flowchart illustrating a processing procedure (purchase data set and report generation) by the control unit 2 of the information processing device 1. The control unit 2 of the information processing device 1 executes data input using the acquired purchase data and prescription data (S401). The control unit 2 of the information processing device 1 acquires purchase data and prescription data in the same manner as in processes S101 and S102 of the first embodiment, and stores the acquired data in the storage unit 3. A purchase data set is configured by aggregating the purchase data (purchase history) of multiple consumers (first subjects). The purchase data set at this point does not include the purchase history that is duplicated for family members. A prescription data set is configured by aggregating the prescription data of multiple consumers (subjects).

[0128] The control unit 2 of the information processing device 1 executes data integration using the input purchase data and prescription data (S402). The control unit 2 of the information processing device 1 refers to the member master table with family information to associate the first subject of the purchase data with the subject of the prescription data, and executes data integration between the purchase data and the prescription data. As a result, by executing data integration between the purchase data and the prescription data, the first subject who purchased the daily necessities is associated with the subject who was prescribed the prescription drug (associated based on identity based on name and date of birth) between the purchase data and the prescription data. The control unit 2 of the information processing device 1 may execute data integration using the input purchase data and prescription data, and register (import) the integrated data in the purchase and dispensing DB300.

[0129] The control unit 2 of the information processing device 1 refers to the member master table with family information and executes a process of duplicating the purchase history of the first subject for the number of family members of the first subject (family purchase data linking) (S403). The family structure of each first subject is stored in the storage unit 3 as, for example, a member master table with family information. The control unit 2 of the information processing device 1 identifies the family structure of each first subject by referring to the member master table with family information, and duplicates the purchase history of the first subject for the number of family members of the first subject according to the identified family structure.

[0130] When the family structure of the first subject is two people, the first subject and his / her spouse, the control unit 2 of the information processing device 1 copies the spouse. As a result, the purchase history (purchase data of products) of the first subject becomes two records, consisting of the purchase history of the first subject and the purchase history of the copied spouse. When the family structure of the first subject is four people, consisting of the first subject, his / her spouse and two children, the control unit 2 of the information processing device 1 copies the spouse and two children. As a result, the purchase history (purchase data of products) of the first subject becomes four records, consisting of the purchase history of the first subject and the purchase history of the copied spouse and two children. When the family structure of the first subject is one person, consisting of the first subject only, the control unit 2 of the information processing device 1 does not copy the family. As a result, the purchase history (purchase data of products) of the first subject becomes one record, consisting of the purchase history of the first subject only.

[0131] The control unit 2 of the information processing device 1 refers to the reference table (table for determining proxy purchase) and executes a determination (proxy purchase determination) as to whether the purchase history of the first target is a personal purchase with the first target as the purchase user, or a proxy purchase with the first target's family as the purchase user (S404). The reference table (table for determining proxy purchase) defines the purchase probability (purchase probability for the first target and each of the family) for each of a number of aspects of family composition for each of the target products (daily necessities). The control unit 2 of the information processing device 1 specifies the family composition of the first target who is the subject of proxy purchase determination by referring to the member master table with family information.

[0132] The control unit 2 of the information processing device 1 refers to the purchase probability (purchase probability for the first subject and each of the family members) defined in a reference table based on the combination of the product (household item) purchased by the first subject and the identified family composition, and identifies the person (the first subject or any of the first subject's family members) who corresponds to the attribute with the highest purchase probability as the user of the purchased item. As a result, when the first subject is identified, it corresponds to a personal purchase. When any of the first subject's family members is identified, it corresponds to a proxy purchase. The control unit 2 of the information processing device 1 performs this proxy purchase determination for all purchase histories (the first subject's purchase history for each product (household item) and the duplicated purchase history).

[0133] The control unit 2 of the information processing device 1 is not limited to using a reference table when making a proxy purchase decision, and may make a proxy purchase decision using an artificial intelligence chatbot such as ChatGPT. The control unit 2 of the information processing device 1 inputs the product purchased by the first target person (purchaser himself / herself) and the family composition of the first target person to the artificial intelligence chatbot (ChatGPT, etc.). The control unit 2 of the information processing device 1 may obtain a determination result from the artificial intelligence chatbot as to whether the user of the product is the first target person himself / herself (purchaser himself / herself) or any of the family members of the first target person (proxy purchase). In other words, the control unit 2 of the information processing device 1 may cause the artificial intelligence chatbot (ChatGPT, etc.) to function substantially as a reference table (table for proxy purchase decision) and obtain (derive) a determination result of the proxy purchase decision.

[0134] The control unit 2 of the information processing device 1 executes various data analyses using a purchase data set in which the purchase history of the first subject is duplicated for the number of family members of the first subject and further a proxy purchase determination (determination result is given) is performed (S405). The control unit 2 of the information processing device 1 executes report creation based on the results of various data analyses (S406). The control unit 2 of the information processing device 1 specifies subjects (patients) who have been prescribed a prescription drug during a predetermined period by using any of the prescription drugs included in the prescription data set as an extraction condition. This makes it possible to specify multiple subjects (patients) who have a disease corresponding to the prescription drug used as the extraction condition.

[0135] The control unit 2 of the information processing device 1 can obtain a purchase history (purchase history of a patient to whom a prescription drug has been prescribed) including the name, quantity, purchase time, etc. of the product (daily necessities) purchased by the subject (patient) by searching the purchase data set using the specified subject (patient) as a search key. The purchase history of the patient to whom the prescription drug has been prescribed becomes a population from which various analytical processes are performed. Furthermore, the control unit 2 of the information processing device 1 can obtain attributes (attributes of a patient to whom a prescription drug has been prescribed) such as age, sex, and family structure of the subject (patient) by searching an attribute data set consisting of a member master table with family information, etc., using the specified subject (patient) as a search key. The attributes of the patient to whom the prescription drug has been prescribed becomes a population from which various analytical processes are performed. These two populations (a set of purchase history of a patient to whom a prescription drug has been prescribed, and a set of attributes of a patient to whom a prescription drug has been prescribed) are associated and normalized by a patient ID used as a primary key. The control unit 2 of the information processing device 1 performs various analytical processes by using the two populations (a set of purchase histories of patients to whom prescription drugs have been prescribed, and a set of attributes of patients to whom prescription drugs have been prescribed).

[0136] The control unit 2 of the information processing device 1, for example, extracts (estimates) products (daily necessities) purchased by at least some of the subjects (patients) among a plurality of subjects (patients) who have been prescribed a specific prescription drug used as a search key, as a purchase history common to the portion of subjects (patients). The control unit 2 of the information processing device 1 may extract the number of subjects (patients) who purchased each product (daily necessities) among the products (daily necessities) purchased by the plurality of subjects (patients) who have been prescribed a specific prescription drug, and output (estimate) the distribution of the number of purchasers of each product (daily necessities). Alternatively, the control unit 2 of the information processing device 1 may further subdivide (categorize) the plurality of subjects (patients) who have been prescribed a specific prescription drug according to attributes such as gender or age, and extract (estimate) a purchase history common to some of the subjects (patients) for each attribute. Alternatively, the control unit 2 of the information processing device 1 may extract subjects (patients) who have purchased the same or similar products (daily necessities) from among multiple subjects (patients) to whom a specific prescription drug has been prescribed, and output (estimate) the distribution of the number of people for each attribute of the extracted subjects (patients). In this way, the control unit 2 of the information processing device 1 can perform analysis processing from various perspectives by using a prescription data set, a purchase data set, and an attribute data set (such as a member master table with family information) that are normalized, associated, and stored and managed in the purchase and dispensing DB 300 composed of, for example, an RDB (Relational Database) or the like.

[0137] FIG. 26 is an explanatory diagram illustrating an example of the analysis result (extraction of the number of purchasers for each product category for all patients and visitors). As described above, the control unit 2 of the information processing device 1 performs analysis processing from various viewpoints by using the prescription data set, purchase data set, and attribute data set (member master table with family information, etc.), and an example of this is illustrated. In the illustration in this embodiment, the upper table shows the extraction result of purchase data (proxy purchase determined) and attribute data from the purchase data set and attribute data set using any prescription medicine as an extraction condition. In the extraction result, the correspondence (self or family) between the member ID (point card member: first target person) and the patient ID (patient) is shown, and the category indicates whether the purchase is made by the member (self) or family (may be blank such as null value) or proxy purchase. As the purchase history, the store, purchase date, purchase time, POS machine number, product name, quantity, amount, product name, minor category, medium category, and major category for each purchased product (daily necessities) are shown. As attribute information of the patient ID (patient), gender and year of birth (age group) are shown.

[0138] As an analysis example, the control unit 2 of the information processing device 1 extracts (calculates) the number of purchasers for each category (JICFS product name) for patients and all customers (visitors), and outputs the extraction (calculation) results as the table below. The control unit 2 of the information processing device 1 outputs the analysis results, which are a comparison between the number of patients (patients prescribed prescription drugs, which is the extraction condition) who purchased a specific product (product name) (number of patients who purchased) and the number of people who purchased the specific product (product name) at the store selling the product (number of purchasers overall (visitors)). The control unit 2 of the information processing device 1 may generate and output screen data including the analysis results.

[0139] According to this embodiment, the control unit 2 (estimation unit) of the information processing device 1 performs various search or extraction processes using prescription drugs included in the prescription data set as an extraction condition based on a prescription data set describing prescription drugs prescribed to multiple subjects (including a first subject (e.g., a member of a point card) and the family of the first subject), a purchase data set describing the purchase history of multiple first subjects (e.g., a member of a point card), and an attribute data set describing attribute information of the multiple subjects, and performs various analysis processes on the extracted information. The multiple subjects in the prescription data set include multiple first subjects in the purchase data set and the family of the first subject. The control unit 2 (estimation unit) of the information processing device 1 extracts purchase data and attribute data from the purchase data set and the attribute data set using any of the prescription drugs included in the prescription data set as an extraction condition. That is, the control unit 2 (estimation unit) of the information processing device 1 identifies multiple subjects to whom the prescription drug serving as the search key is prescribed for the prescription data set. The control unit 2 (estimation unit) of the information processing device 1 estimates (extracts) the purchase history of the multiple subjects (subjects to whom the target prescription drug is prescribed) using the identified subjects as a search key for the purchase data set. This makes it possible to estimate (extract) the purchase history of the subjects to whom the target prescription drug is prescribed.

[0140] The estimated purchase history includes purchase histories of various daily necessities by each subject (subject for whom the target prescription drug is prescribed). The control unit 2 (estimation unit) of the information processing device 1 extracts subjects (subject for whom the target prescription drug is prescribed) who purchased specific daily necessities using the category, type, or name of each of these daily necessities as a search key. The control unit 2 (estimation unit) of the information processing device 1, for example, specifies (calculates) the number of subjects (subject for whom the target prescription drug is prescribed) who purchased each of all daily necessities included in the purchase history as a search key. The control unit 2 (output unit) of the information processing device 1 may output, for example, as a bubble chart, the number of subjects (subject for whom the target prescription drug is prescribed) who have purchased each of the daily necessities specified as a search key, in association with the daily necessities that are the search keys. The control unit 2 (output unit) of the information processing device 1 may output a classification result in a table format (classification table) according to attribute information of a subject (subject for whom the target prescription drug is prescribed) identified using each daily necessities as a search key, such as age, sex, and family structure of the subject. When generating and outputting such analysis results, the control unit 2 (output unit) of the information processing device 1 may perform various analysis processes such as drill-down, slicing, or dicing using a BI (Business Intelligence) tool. The control unit 2 (estimation unit, output unit) of the information processing device 1 performs such processing to estimate and output a purchase history common to some of the first subjects among all first subjects for whom any prescription drug is prescribed. Alternatively, the control unit 2 (estimation unit, output unit) of the information processing device 1 estimates and outputs attribute information common to some of the first subjects among all first subjects for whom any prescription drug is prescribed. Alternatively, the control unit 2 (estimation unit, output unit) of the information processing device 1 estimates and outputs both the purchasing history and attribute information that are common to some of the first subjects among all first subjects who have been prescribed any prescription drug.In this way, the control unit 2 (estimation unit, output unit) of the information processing device 1 can estimate and output in three forms: common attribute information only, common purchasing history only, or both common purchasing history and attribute information.

[0141] The subject in the prescription data set indicates the subject himself / herself to whom the prescription drug is prescribed, and the prescription drug is used by the subject. The first subject in the purchase data set indicates the actual purchaser who purchased daily necessities such as OTC drugs, health foods, supplements, groceries, health equipment, and nursing care products, and indicates a member (point card member) of a store or the like that sells the daily necessities. However, if the first subject who is the purchaser has a family living together, for example, the purchased daily necessities are assumed to be either a personal purchase when the first subject uses the daily necessities themselves, or a proxy purchase when the family uses the daily necessities. The purchase history estimated (derived) by the control unit 2 of the information processing device 1 includes a purchase history of a personal purchase by the first subject, who is a purchase user (purchasing subject), and a purchase history of a proxy purchase by the first subject's family, who is a purchase user (purchasing subject), and therefore can handle both personal purchases and proxy purchases.

[0142] According to this embodiment, the control unit 2 (estimation unit) of the information processing device 1 judges whether the purchase history of the first target person (member of the point card) is a purchase by the first target person as the purchase user (purchasing target person) or a proxy purchase by the first target person's family member as the purchasing product user (purchasing target person) by referring to a reference table (proxy purchase determination table) stored in the storage unit 3, for example. Then, the control unit 2 (estimation unit) of the information processing device 1 estimates (derives) the purchase history of the target person for whom the prescription drug is prescribed as the purchasing product user (purchasing target person), so that it is possible to efficiently identify the daily necessities used by the target person for whom the prescription drug is prescribed (daily necessities for which the target person is the purchasing product user (purchasing target person)). In other words, even if the purchase history of the first target person (member of the point card) includes purchases by the first target person and proxy purchases, it is possible to improve the accuracy of estimating the purchasing tendency of daily necessities by the target person for whom the prescription drug is prescribed, by aligning the correspondence between the target person for whom the prescription drug is prescribed and the user (purchasing product user) of the purchased daily necessities.

[0143] According to this embodiment, the reference table (table for determining proxy purchase) includes information on the purchasing demographic for each of the daily necessities (products purchased by the first subject) included in the purchase history. The information on the purchasing demographic is, for example, information indicating the purchase probability according to attributes such as the age, sex, or a combination of these of the purchaser of the daily necessities. The control unit 2 (estimation unit) of the information processing device 1 refers to the reference table based on attributes such as the age or sex of the subject for whom the prescription drug is prescribed and the subject's family, and identifies a person (the first subject or any member of the first subject's family) who corresponds to the attribute with the highest purchase probability as the user of the purchased product. If the first subject is identified as a result, it corresponds to a purchase by the person himself. If any member of the first subject's family is identified, it corresponds to a proxy purchase. By using a reference table (table for determining proxy purchases) containing purchase probabilities according to attributes such as age and gender in this manner, it is possible to efficiently determine (estimate) whether a purchase by a first subject, who is, for example, a member of a point card at a store, etc., is a personal purchase using a product (purchased item) purchased by the first subject (principal person) or a proxy purchase using the purchased item by a family member of the first subject (spouse, child, etc.).

[0144] According to this embodiment, the reference table (table for determining proxy purchase) includes information on the disease corresponding to the prescription drug for each daily necessities (products purchased by the first subject) included in the purchase history. The information on the disease corresponding to the prescription drug is, for example, information indicating the purchase probability according to the person having the disease. In other words, since it is assumed that a person having a specific disease has a high tendency to purchase a specific daily necessities, by setting the presence of the disease as an attribute of the first subject or the first subject's family, it is possible to determine whether the purchase was made by the person himself or by a proxy by taking into account the tendency.

[0145] According to this embodiment, in the reference table (table for determining proxy purchase), a plurality of records corresponding to the family structure of the first subject are associated with each of the daily necessities included in the purchase history. The family structure of the first subject is assumed to be various family structures, such as a single person structure consisting of only the first subject, a married couple structure consisting of the first subject and his / her spouse, a nuclear family structure consisting of the first subject, his / her spouse and one or more children, or a two-family structure consisting of the first subject and his / her parents. In contrast, in the reference table, a record corresponding to each of the assumed family structures is associated with each of the daily necessities to be subjected to various analysis processes, i.e., each classification, type, or name of the daily necessities. The record includes the purchase probability in the corresponding family structure, i.e., information regarding the probability of personal purchase for the first subject and the probability of proxy purchase for the family of the first subject. When referring to the reference table, the control unit 2 (estimation unit) of the information processing device 1 uses a record having a family structure similar to that of the first subject who purchased the daily necessities to identify whether the user of the daily necessities is the first subject (personal purchase) or any member of the family (proxy purchase). By using a reference table having such a record configuration, it is possible to efficiently identify whether the daily necessities were purchased by the first subject himself / herself or by proxy, depending on the family structure of the first subject who purchased the daily necessities.

[0146] According to this embodiment, when the control unit 2 (generation unit) of the information processing device 1 aggregates the purchase data (purchase history) of a plurality of consumers (first subjects) to generate a purchase data set, the control unit 2 (generation unit) copies the purchase data (purchase history) to the number of family members of the first subject who is a purchaser, and includes the copied purchase data in the purchase data set. Therefore, the purchase data set includes the purchase history of the first subject and the purchase history in which the purchase history of the first subject is copied to the number of family members of the first subject. That is, the purchase data set includes a plurality of records (purchase history) for products purchased by the first subject, including the purchase history of the first subject and the purchase history in which the purchase history of the first subject is copied to the number of family members of the first subject. Furthermore, the control unit 2 (generation unit) of the information processing device 1 assigns a determination result of whether the purchase history is a purchase by the first subject or a purchase by proxy to any of the purchase history of the first subject and the copied purchase history. The control unit 2 (generation unit) of the information processing device 1 may, for example, refer to a reference table (table for determining proxy purchase) to determine whether the purchase is made by the person himself or by proxy, and may assign a circle to the record corresponding to the user of the purchased product in either the record of the first subject (purchaser himself) or the records copied for the number of family members, and assign an X or null value to the others. Alternatively, the control unit 2 (generation unit) of the information processing device 1 may input the product purchased by the first subject (purchaser himself) and the family composition of the first subject to an artificial intelligence chatbot such as ChatGPT, and obtain from the artificial intelligence chatbot whether the user of the product is the first subject himself (purchased by himself) or any of the family members of the first subject (purchased by proxy). The control unit 2 (generation unit) of the information processing device 1 may efficiently generate a purchasing data set including not only personal purchases but also proxy purchases by copying the purchase history (purchasing data) of the first subject to the number of family members of the first subject, and assigning a marking (circle indicating the user) to any purchase history (purchasing data) corresponding to the user of the product.

[0147] (Embodiment 5) FIG. 27 is an explanatory diagram regarding the identification process of common purchase history and attribute information (attribute value of target drug patient) according to the fifth embodiment. The control unit 2 of the information processing device 1 performs various analysis processes using a purchase data set, an attribute data set, and a prescription data set normalized and associated by a member ID and a patient ID in the purchase and dispensing DB 300, and outputs the analysis results as illustrated in the present embodiment. The control unit 2 of the information processing device 1 may generate screen data including the analysis results, and output the screen data to an information terminal such as a smartphone. The purchase data set used when performing various analysis processes is not limited to the purchase data set for which proxy purchase determination has been performed as described in the fourth embodiment, but may be the purchase data set described in the first embodiment (a purchase data set for which proxy purchase determination has not been performed).

[0148] The control unit 2 of the information processing device 1 extracts attribute data from the attribute dataset based on the patient ID extracted from the prescription dataset using any of the prescription drugs as an extraction condition, and outputs the classification results of the attribute values ​​of the target drug patients as a process of identifying common attribute information. The control unit 2 of the information processing device 1 outputs a table that compiles the target drug patients for each of the age and gender attributes (gender and age) of patients (target drug patients) to whom a specific prescription drug has been prescribed. This makes it possible to identify the gender and age that make up a high proportion of the number of patients. Furthermore, the control unit 2 of the information processing device 1 can identify the gender and age that make up a high proportion of the number of new patients based on the time and number of times a specific prescription drug was prescribed.

[0149] FIG. 28 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (proportion of patients taking target drugs). The control unit 2 of the information processing device 1 extracts attribute data from the attribute dataset based on the patient ID extracted from the prescription dataset using any prescription drug as an extraction condition, and outputs a classification result of the proportion of patients taking target drugs as the process of identifying common attribute information. The control unit 2 of the information processing device 1 counts the number of new patients and continuing patients for each of the age and gender attributes (gender and age) of patients (patients taking target drugs) based on the time and number of times a specific prescription drug was prescribed, and outputs the classification result including the calculation results of the new rate and continuing rate in a table format. This allows the control unit 2 of the information processing device 1 to identify the gender and age with a high proportion of new patients among the total number of patients.

[0150] Furthermore, the control unit 2 of the information processing device 1 outputs classification results of the number of people (number of patients, total number of people) and prescription rate, which show a comparison between all people registered in the member master table with family information and patients to whom a specific prescription drug is prescribed (target drug patients), for each of the attributes of age and sex (gender and age). This allows the control unit 2 of the information processing device 1 to identify gender and age with a high ratio of the number of patients to the total (prescription rate).

[0151] FIG. 29 is an explanatory diagram regarding the identification process (regression analysis result) of common purchase history and attribute information. The control unit 2 of the information processing device 1 extracts (identifies) subjects (patients: patient ID) to whom the prescription drug was prescribed in a predetermined period from the prescription data set, using a specific prescription drug as an extraction condition. The control unit 2 of the information processing device 1 searches the attribute data set (member master table with family information) for the extracted multiple subjects (patients: patient ID) and extracts attribute information of the patient, thereby identifying the population to be analyzed (a set of attributes of patients to whom the prescription drug was prescribed). The control unit 2 of the information processing device 1 can identify the sex and age group (gender and age group) with a high probability of being a patient by performing a regression analysis on the population to be analyzed. The regression analysis result includes a partial regression coefficient, a P value, and an odds ratio according to sex (male = 0 / female = 1), and the control unit 2 of the information processing device 1 may estimate a consideration based on these items. Furthermore, the control unit 2 of the information processing device 1 may output partial regression coefficients, P values, odds ratios, and estimated considerations according to age groups as the regression analysis results.

[0152] FIG. 30 is an explanatory diagram relating to the process of identifying common purchase history and attribute information (cluster analysis). Furthermore, the control unit 2 of the information processing device 1 may perform cluster analysis on the population to be analyzed, thereby confirming and identifying into what attribute (gender and age) the patient is classified. When classifying the attributes (gender and age), the control unit 2 of the information processing device 1 may perform classification and output the proportion (percentage) of each class. The control unit 2 of the information processing device 1 may generate and output a distribution graph according to the results of the cluster analysis.

[0153] FIG. 31 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (purchase history of a target drug patient). The control unit 2 of the information processing device 1 extracts a purchase history from the purchase data set based on a patient ID extracted from a prescription data set using any prescription drug as an extraction condition. The control unit 2 of the information processing device 1 outputs a classification result of purchased products (category / single item) of a target drug patient (a patient prescribed a prescription drug of the extraction condition) as a process of identifying common purchase history in the extracted multiple purchase histories. The control unit 2 of the information processing device 1 outputs a classification result regarding products for which a patient (target drug patient) who is prescribed a specific prescription drug is a purchase product user. As described above, the purchase data set is given the result of proxy purchase determination, and the purchase product user of the product is associated with the patient (target drug patient) who is prescribed a prescription drug.

[0154] The control unit 2 of the information processing device 1 extracts (specifies) subjects (patients: patient IDs) to whom prescription drugs have been prescribed in a predetermined period, using a specific prescription drug as an extraction condition for the prescription data set. The control unit 2 of the information processing device 1 searches the purchase data set for the extracted subjects (patients: patient IDs) and extracts the purchase history (purchase data) of the patient, thereby specifying a population to be analyzed (a set of purchase histories of patients to whom prescription drugs have been prescribed). The control unit 2 of the information processing device 1 calculates a purchase rate (a ratio of the number of purchasers to the number of visitors) for the population to be analyzed, for example, according to the product category (classification). These purchase rates can specify a category (classification) of products that are commonly purchased by at least some patients among multiple patients to whom prescription drugs have been prescribed. This makes it possible to specify a purchasing tendency common to the product category (classification). Furthermore, the control unit 2 of the information processing device 1 may calculate a purchase rate (a ratio of the number of purchasers to the number of visitors) for the population to be analyzed, for example, according to the product name. This allows for identifying common purchasing histories for product names (tendencies for each individual product). Furthermore, the control unit 2 of the information processing device 1 may calculate the purchase frequency (number of purchases per person) for the population to be analyzed according to, for example, the product category (classification).

[0155] FIG. 32 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (products that are easy for target drug patients to purchase: lift value of purchase frequency). The control unit 2 of the information processing device 1 outputs the classification result of products that are easy for target drug patients to purchase as the process of identifying common purchase history. The control unit 2 of the information processing device 1 outputs a numerical value indicating the purchase frequency by all (total) registered in the family information-attached member master table and the purchase frequency by patients (patients prescribed prescription drugs, which is the extraction condition) for each product category (classification). The purchase frequency is calculated by using the number of purchasers of the product category as the denominator and the number of purchases by purchasers of the product category as the numerator. Note that the purchase frequency by all (total) may be by all registered in the family information-attached member master table, or may be the total number of people obtained by subtracting patients (patients prescribed prescription drugs, which is the extraction condition) from all of the people.

[0156] The control unit 2 of the information processing device 1 calculates a lift value (patient purchase frequency / total purchase frequency) that indicates whether a product is easy for patients to purchase for each product category (classification) based on the overall purchase frequency and the patient purchase frequency. If the lift value is, for example, 1.5 or more, the corresponding product category (classification) is deemed to be a category (classification) that is relatively likely to be commonly purchased by patients (patients who have been prescribed prescription drugs, which is the extraction condition) (the control unit 2 determines that there is a correlation), and if it is, for example, less than 0.8, it is deemed to be a category (classification) that is relatively unlikely to be commonly purchased, and a common purchasing tendency can be identified. Note that the lift value threshold of 1.5 is an example, and a value from 1.2 to 2.0 may be used as appropriate.

[0157] FIG. 33 is an explanatory diagram regarding the process of identifying common purchase history and attribute information (products that are easy for target drug patients to purchase: lift value of purchase rate). The control unit 2 of the information processing device 1 outputs the classification results of products that are easy for target drug patients to purchase, for example, by category or by individual item, as the process of identifying common purchase history. The control unit 2 of the information processing device 1 outputs, for each product category (classification) or individual item (product name), numerical values ​​indicating the purchase rate by all (total) registered in the member master table with family information and the purchase rate by patients (patients who have been prescribed prescription drugs, which is the extraction condition). This purchase rate is calculated by using the number of all (total) people or the number of all patients who have been prescribed prescription drugs, which is the extraction condition, as the denominator and the number of purchasers of the product category in question as the numerator.

[0158] The control unit 2 of the information processing device 1 calculates a lift value (patient purchase rate / total purchase rate) indicating whether a target drug patient is likely to purchase a product based on the overall purchase rate and the patient purchase rate for each product category (classification) or single product (product name). If the lift value is, for example, 1.5 or more, the corresponding product category (classification) or single product (product name) is deemed to be a category (classification) or single product (product name) that is relatively likely to be commonly purchased by patients (patients who have been prescribed prescription drugs, which are the extraction condition) (the control unit 2 determines that there is a relationship), and if it is, for example, less than 0.8, it is deemed to be a category (classification) or single product (product name) that is relatively unlikely to be commonly purchased, and a common purchasing tendency can be identified. Note that the lift value threshold of 1.5 is an example, and a value from 1.2 to 2.0 may be used as appropriate.

[0159] FIG. 34 is an explanatory diagram regarding the identification process of common purchase history and attribute information (products that the target drug patient started buying before the first consultation). The control unit 2 of the information processing device 1 outputs the analysis result of the products (category / products) that the target drug patient started buying before the first consultation as the identification process of the common purchase history. The control unit 2 of the information processing device 1 outputs, in a graph form, the transition of the number of purchasers for 26 weeks before and after the first consultation week, for example, for the product category of skin trouble care, as the purchase trend analysis of the analysis target product patient (new patient). From the analysis result, it is possible to derive that there are multiple timings where the number of purchasers peaks, for example, 3 to 6 weeks before the first consultation week and 9 to 10 weeks before the first consultation week. As a result, it is possible to grasp that the analysis target product patient (new patient) has skin trouble (eczema, dermatitis) before the first consultation as a purchasing tendency. Therefore, the control unit 2 of the information processing device 1 can estimate that a person who has started buying skin trouble care products will be prescribed the target drug in a predetermined week, that is, that there is a possibility that he or she will develop a disease in the future (potential patient).

[0160] FIG. 35 is an explanatory diagram of the process of identifying common purchase history and attribute information (decision tree analysis result). The control unit 2 of the information processing device 1 outputs the association of various products purchased by the target drug patient as the process of identifying the common purchase history. The control unit 2 of the information processing device 1 may determine the product category (display category) that is the branch when identifying the purchasing tendency from the decision tree analysis result, and may develop the decision tree by moving non-purchased (≦0.5) to True and purchased to False in each of the display categories. This allows branching depending on whether the target category has been purchased or not, and based on the decision tree analysis result, it can be estimated (derived) that, for example, the products purchased by a specific target drug patient are generally many products that evoke the image of elderly people.

[0161] FIG. 36 is an explanatory diagram regarding the identification process (regression analysis result) of common purchase history and attribute information. The control unit 2 of the information processing device 1 outputs the regression analysis result (one with a statistically significant difference and a high odds ratio) of various products (categories) purchased by the target drug patient as the identification process of the common purchase history. The control unit 2 of the information processing device 1 may output the partial regression coefficient, P value, odds ratio, and estimated consideration according to gender as the regression analysis result. Furthermore, the control unit 2 of the information processing device 1 may output the partial regression coefficient, P value, odds ratio, and estimated consideration for each of various products (categories) purchased by the target drug patient as the regression analysis result. The control unit 2 of the information processing device 1 may estimate, for example, based on the odds ratio, that if the odds ratio exceeds 1, the probability of the patient making the purchase is relatively high overall, and that if the odds ratio is less than 1, the probability of the patient is relatively low.

[0162] (Supplementary Note 1) The information processing system includes an estimation unit that, based on a prescription data set describing prescription drugs prescribed to multiple subjects and a purchase data set describing the purchase history of multiple first subjects, extracts purchase data from the purchase data set using any of the prescription drugs included in the prescription data set as an extraction condition, and estimates a purchase history common to a portion of the first subjects among all the first subjects to whom any of the prescription drugs are prescribed, using the extracted purchase data; and an output unit that outputs a purchase history common to the estimated portion of first subjects, The purchase history includes a purchase history of personal purchases in which the first subject is a purchase user, and a purchase history of proxy purchases in which a family member of the first subject is a purchase user.

[0163] (Appendix 2) The information processing system includes a prescription data set describing prescription drugs prescribed to a plurality of subjects, and an attribute data set describing attribute information of the plurality of first subjects. The attribute data set is used as an extraction condition for any of the prescription drugs included in the prescription data set, and an estimation unit estimates attribute information common to a portion of the first subjects among all the first subjects to whom any of the prescription drugs are prescribed, using the extracted attribute data; and an output unit that outputs attribute information common to the estimated portion of first subjects.

[0164] (Supplementary Note 3) In the information processing system of Supplementary Note 1, the estimation unit further extracts attribute data from the attribute dataset based on a prescription dataset describing prescription drugs prescribed to multiple subjects and an attribute dataset describing attribute information of the multiple first subjects, using any of the prescription drugs included in the prescription dataset as an extraction condition, and estimates attribute information common to a portion of the first subjects among all the first subjects to which any of the prescription drugs are prescribed, using the extracted attribute data; The output unit further outputs attribute information common to the estimated portion of first subjects, The purchase history includes a purchase history of personal purchases in which the first subject is a purchase user, and a purchase history of proxy purchases in which a family member of the first subject is a purchase user.

[0165] (Appendix 4) The information processing system includes a model construction unit that constructs an estimation model for estimating a second subject who is estimated to develop a disease corresponding to any of the prescription drugs included in the prescription data set in the future, based on a prescription data set describing prescription drugs prescribed to multiple subjects and a purchase data set describing the purchase history of multiple first subjects, from the purchase history of the second subject; A data acquisition unit that acquires purchase data describing a purchase history of the second subject; an estimation unit that estimates a second subject who is expected to develop a disease corresponding to the prescription drug in the future based on a purchase history of the second subject described in the purchase data and the estimation model; The purchasing history includes purchasing history of personal purchases in which the first subject and the second subject are purchase users, and purchasing history of proxy purchases in which family members of the first subject and the second subject are purchase users.

[0166] (Supplementary Note 5) In the information processing system according to Supplementary Note 1, Supplementary Note 3, or Supplementary Note 4, the estimation unit Determining whether the purchase history is a purchase by the person himself or a purchase by proxy; A purchase history of the subject for whom the prescription drug is prescribed as a purchase user is estimated.

[0167] (Supplementary Note 6) The information processing system according to Supplementary Note 1, Supplementary Note 3, Supplementary Note 4, or Supplementary Note 5 further comprises a storage unit in which a reference table including information on a purchasing demographic for each of the daily necessities included in the purchase history is stored; The estimation unit is Based on the attributes of the subject for whom the prescription drug is prescribed, the reference table is referenced to determine whether the purchase history is a purchase by the subject or a purchase by proxy.

[0168] (Supplementary Note 7) The information processing system according to Supplementary Note 6, wherein the reference table includes information on diseases corresponding to prescription drugs; The estimation unit is Based on the prescription drugs prescribed for the first subject and the first subject's family members, the reference table is referenced to determine whether the purchase history is a personal purchase or a proxy purchase.

[0169] (Supplementary Note 8) In the information processing system according to Supplementary Note 6 or Supplementary Note 8, the reference table associates a plurality of records corresponding to a family structure of the first subject with each of the daily necessities included in the purchase history; Each of the records includes information regarding the probability of a personal purchase for the first subject and the probability of a proxy purchase for a family member of the first subject.

[0170] (Supplementary Note 9) The information processing system according to any one of Supplementary Note 1 or Supplementary Note 3 to Supplementary Note 8, further comprising a generating unit configured to generate the purchase data set, The generation unit is Duplicating the purchase history of the first subject for the number of family members of the first subject; The purchase history of the duplicated number of people is included in the purchase data set; A determination result as to whether the purchase history is a personal purchase or a proxy purchase is given to either the purchase history of the first subject or the duplicated purchase history.

[0171] (Appendix 10) The information processing method includes a prescription data set describing prescription drugs prescribed to a plurality of subjects, a purchasing data set describing the purchasing history of a plurality of first subjects, and an attribute data set describing attribute information of the plurality of subjects, and includes: extracting purchasing data and attribute data from the purchasing data set and the attribute data set using any of the prescription drugs included in the prescription data set as an extraction condition; and using the extracted purchasing data and attribute data, causing an estimation unit to estimate purchasing history and attribute information common to a portion of the first subjects among all the first subjects to whom any of the prescription drugs are prescribed; outputting purchase history and attribute information common to the estimated portion of first subjects to an output unit; The purchase history includes a purchase history of a personal purchase made by the first subject, the purchaser being a purchaser, and a purchase history of a proxy purchase made by a family member of the first subject, the purchaser being a purchaser. The processing is executed by a computer.

[0172] (Appendix 11) The information processing method includes constructing an estimation model in a model construction unit based on a prescription data set describing prescription drugs prescribed to a plurality of subjects and a purchase data set describing purchase histories of a plurality of first subjects, for estimating a second subject who is estimated to develop a disease corresponding to any of the prescription drugs included in the prescription data set in the future from the purchase history of the second subject; causing a data acquisition unit to acquire purchase data describing a purchase history of the second subject; causing an estimation unit to estimate a second subject who is estimated to develop a disease corresponding to the prescription drug in the future based on a purchase history of the second subject described in the purchase data and the estimation model; The purchase history includes a purchase history of a personal purchase in which the first subject and the second subject are purchase users, and a purchase history of a proxy purchase in which a family member of the first subject and the second subject is a purchase user. The processing is executed by a computer.

[0173] The matters described in each embodiment can be combined with each other. In addition, the independent claims and dependent claims described in the claims can be combined with each other in any and all combinations regardless of the citation format. Furthermore, the claims use a format in which a claim cites two or more other claims (multiple claim format), but this is not limited to this. A multiple claim (multi-multi claim) that cites at least one multiple claim may also be used. [Explanation of symbols]

[0174] S Purchasing and dispensing system (information processing system) N External Network TS store server HS Insurance Pharmacy Server GS External Server 1. Information processing device 2. Control section 21 Acquisition Department 22 Disease Identification Department 23 DB Registration Department 24 Daily necessities analysis model 25 Disease Report Generation Unit 26 Output section 27 Disease Assumption Person Determination Department 28 Consumer Report Generation Department 201 First Learning Model 202 Second Learning Model 3 Storage section 31 Recording media P Program (Program Product) 300 Purchasing and dispensing DB 4. Communications Department

Claims

1. an estimation unit that extracts purchase data from a prescription data set describing prescription drugs prescribed to a plurality of subjects and a purchase data set describing the purchase histories of a plurality of first subjects, using any one of the prescription drugs included in the prescription data set as an extraction condition, and estimates a purchase history common to a portion of the first subjects among all the first subjects to whom any one of the prescription drugs is prescribed, using the extracted purchase data; an output unit that outputs a purchase history common to the estimated portion of first subjects; The purchase history includes a purchase history of a personal purchase made by the first subject, the purchaser being a purchaser, and a purchase history of a proxy purchase made by a family member of the first subject, the purchaser being a purchaser. Information processing system.

2. An estimation unit that extracts attribute data from a prescription data set describing prescription drugs prescribed to a plurality of subjects and an attribute data set describing attribute information of the plurality of first subjects, using any one of the prescription drugs included in the prescription data set as an extraction condition, and estimates attribute information common to a portion of the first subjects among all the first subjects to whom any one of the prescription drugs is prescribed, using the extracted attribute data; and an output unit that outputs attribute information common to the estimated portion of the first subjects. Information processing system.

3. The estimation unit further extracts attribute data from the attribute dataset using any one of the prescription drugs included in the prescription dataset as an extraction condition based on a prescription dataset describing prescription drugs prescribed to multiple subjects and an attribute dataset describing attribute information of the multiple first subjects, and estimates attribute information common to a portion of the first subjects among all the first subjects to which any one of the prescription drugs is prescribed, using the extracted attribute data; The output unit further outputs attribute information common to the estimated portion of first subjects. The information processing system according to claim 1 .

4. a model construction unit that constructs an estimation model for estimating a second subject who is estimated to develop a disease corresponding to any of the prescription drugs included in the prescription data set in the future, based on a prescription data set describing prescription drugs prescribed to multiple subjects and a purchase data set describing the purchase history of multiple first subjects, from the purchase history of the second subject; A data acquisition unit that acquires purchase data describing a purchase history of the second subject; an estimation unit that estimates a second subject who is expected to develop a disease corresponding to the prescription drug in the future based on a purchase history of the second subject described in the purchase data and the estimation model; The purchase history includes a purchase history of a personal purchase in which the first target person and the second target person are purchase users, and a purchase history of a proxy purchase in which a family member of the first target person and the second target person are purchase users. Information processing system.

5. The estimation unit is Determining whether the purchase history is a purchase by the person himself or a purchase by proxy; A purchase history of the subject for whom the prescription drug is prescribed as a purchase user is estimated.

5. An information processing system according to claim 1, 3 or 4.

6. A storage unit stores a reference table including information on a purchasing demographic for each of the daily necessities included in the purchase history, The estimation unit is Based on the attributes of the subject for whom the prescription drug is prescribed, the reference table is referenced to determine whether the purchase history is a purchase by the subject or a purchase by proxy.

5. An information processing system according to claim 1, 3 or 4.

7. The reference table includes information regarding diseases corresponding to prescription drugs; The estimation unit is Based on the prescription drugs prescribed to the first subject and the family of the first subject, by referring to the reference table, it is determined whether the purchase history is a purchase by the person himself or a purchase by proxy.

7. The information processing system according to claim 6.

8. the reference table associates a plurality of records corresponding to a family structure of the first subject with each of the daily necessities included in the purchase history, Each of the records includes information regarding a probability of personal purchase for the first subject and a probability of proxy purchase for a family member of the first subject.

7. The information processing system according to claim 6.

9. A generation unit that generates the purchase data set, The generation unit is Duplicating the purchase history of the first subject for the number of family members of the first subject; The purchase history of the duplicated number of people is included in the purchase data set; A determination result is given to either the purchase history of the first target person or the duplicated purchase history as to whether the purchase history is a purchase by the first target person or a purchase by a proxy.

5. An information processing system according to claim 1, 3 or 4.

10. Based on a prescription dataset describing prescription drugs prescribed to a plurality of subjects, a purchasing dataset describing the purchasing histories of a plurality of first subjects, and an attribute dataset describing attribute information of the plurality of subjects, purchasing data and attribute data are extracted from the purchasing dataset and the attribute dataset using any one of the prescription drugs included in the prescription dataset as an extraction condition, and an estimation unit is caused to estimate purchasing history and attribute information common to a portion of the first subjects among all the first subjects to whom any one of the prescription drugs is prescribed, using the extracted purchasing data and the attribute data; outputting purchase history and attribute information common to the estimated portion of first subjects to an output unit; The purchase history includes a purchase history of a personal purchase made by the first subject, the purchaser being a purchaser, and a purchase history of a proxy purchase made by a family member of the first subject, the purchaser being a purchaser. An information processing method for causing a computer to execute processing.

11. a model construction unit is caused to construct an estimation model for estimating a second subject who is estimated to develop a disease corresponding to any of the prescription drugs included in the prescription data set in the future, based on a prescription data set describing prescription drugs prescribed to a plurality of subjects and a purchase data set describing the purchase history of a plurality of first subjects, from the purchase history of the second subject; causing a data acquisition unit to acquire purchase data describing a purchase history of the second subject; causing an estimation unit to estimate a second subject who is estimated to develop a disease corresponding to the prescription drug in the future based on a purchase history of the second subject described in the purchase data and the estimation model; The purchase history includes a purchase history of a personal purchase in which the first target person and the second target person are purchase users, and a purchase history of a proxy purchase in which a family member of the first target person and the second target person are purchase users. An information processing method for causing a computer to execute processing.

Images