Data processing system and data processing method

Abstract

To promote health of inhabitants by allowing a private entrepreneur to utilize health data.SOLUTION: A data processing system including an arithmetic device which executes arithmetic processing and a storage device which can be accessed by the arithmetic device, has: a reception unit which receives input data; an information conversion unit which converts the input data; a health prediction model which is generated on the basis of nutrient information and outcome; and an output unit which outputs information on a target person based on a prediction result by the health prediction model. The reception unit receives the input data about a customer of an entrepreneur. The information conversion unit converts the input data into customer nutrient information indicating nutrients taken by the customer. The health prediction model predicts health from the customer nutrient information. The output unit outputs advice for health of the target person to the entrepreneur on the basis of the prediction result.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to data processing systems, and more particularly to systems that provide meaningful information based on health data to private businesses. [Background technology]

[0002] Local governments and other organizations are conducting health projects to collect and analyze health data from residents with the aim of promoting their health. These health projects are sometimes conducted as cohort studies in collaboration with universities, research institutes, and companies. The health data collected from residents through cohort studies is analyzed and utilized to identify factors such as disease and health indicators, which is the purpose of the cohort study.

[0003] The following prior art exists as background art in this technical field: Patent Document 1 (JP 2020-135720 A) describes a shopping support system that includes a management terminal that manages at least information related to food sales, a user terminal owned by a user, and a server device that can communicate with the management terminal and the user terminal, in which the management terminal generates digitized purchasing information based on information about food products purchased by the user, including the price of each food product, and transmits the digitized purchasing information to the server device, and the server device includes a food information acquisition means for acquiring food information including information about the price and quantity exchange rate for each food product, and for at least some of the food products purchased by the user, personal information of the user and their family and the digitized purchasing information received from the management terminal are transmitted to the server device. The server device estimates the amount of each food item that the user and his / her family will consume based on the price of each food item indicated in the purchased purchase information and the acquired food information, allocates the estimated amount of each food item to each individual user and his / her family member and to each day from the date of purchase, analyzes food nutrition information regarding the nutritional value of each type of nutrient contained in the food that the user and his / her family member is estimated to consume on an individual basis each day based on the results of this allocation, generates nutritional bias information indicating the nutrient bias of the user and his / her family member each day, and transmits this information to the user terminal. The user terminal receives the nutritional bias information transmitted from the server device and outputs the received nutritional bias information. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-135720 Summary of the Invention [Problem to be solved by the invention]

[0005] It is difficult for private companies to use health data held by local governments due to the need to protect personal information. If private businesses could utilize health data, they could be expected to improve the health of residents by providing various health services. However, from the perspectives of personal information protection and ethics, they must obtain the consent of the target residents for each purpose. Because it is not easy to obtain consent from tens of thousands of people for each purpose, there is a need to present meaningful information to private businesses without direct access to health data, allowing them to utilize the knowledge gained from cohort studies. [Means for solving the problem]

[0006] A representative example of the invention disclosed in this application is as follows: That is, a data processing system comprising an arithmetic unit that executes arithmetic processing and a storage device that can be accessed by the arithmetic unit, Includes purchasing information of business customers a reception unit that receives input data; a family structure estimation unit that estimates a family structure from the purchase information; and a target person identification unit that identifies a target person from the family structure and outputs target person information of the identified target person. The input data customer nutrient information indicating the nutrients taken by the customer, and an information conversion unit that converts the nutrition information and the outcome into a , predicting health from said customer nutrition information Health prediction models and an advice generation unit that generates advice based on the health prediction result and the subject information; and and an output unit for outputting the signal. [Effects of the Invention]

[0007] According to one aspect of the present invention, the health of residents can be improved. Objects, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a physical configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a configuration diagram of a data processing system according to a first embodiment. [Figure 3] FIG. 1 is a diagram in which the nutrient intake information of each subject in the analysis result database of Example 1 is mapped in a multidimensional space. [Figure 4] FIG. 2 is a diagram illustrating an example of the configuration of an analysis result database according to the first embodiment. [Figure 5] FIG. 10 is a configuration diagram of a data processing system according to a second embodiment. [Figure 6] FIG. 10 is a configuration diagram of a purchase information correction unit according to the second embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of a threshold value in a factor determining unit according to the second embodiment. [Figure 8] FIG. 10 is a configuration diagram of a data processing system according to a third embodiment. [Figure 9] FIG. 10 is a configuration diagram of a nutrient information comparison and correction unit 323 in Example 3. DETAILED DESCRIPTION OF THE INVENTION

[0009] In the following examples, when necessary for convenience, the description will be divided into multiple sections or examples, but unless otherwise specified, they are not unrelated to each other, and one is related to the other as a partial or complete modification, detail, supplementary explanation, etc. Furthermore, in the following examples, when the number of elements, etc. (including the number, numerical value, amount, range, etc.) is mentioned, it is not limited to that specific number, and may be more or less than the specific number, unless otherwise specified or when it is clearly limited in principle to a specific number, etc.

[0010] Furthermore, in the following examples, it goes without saying that the components (including element steps, etc.) are not necessarily essential unless otherwise specified or considered to be clearly essential in principle. Similarly, in the following examples, when referring to the shape, positional relationship, etc. of components, etc., it is intended to include those that are substantially similar or similar to the shape, etc., unless otherwise specified or considered to be clearly not essential in principle. The same applies to the aforementioned numerical values ​​and ranges.

[0011] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In all drawings for explaining the embodiments, the same elements are generally designated by the same reference numerals, and repeated explanations thereof will be omitted.

[0012] Example 1 FIG. 1 is a block diagram showing the physical configuration of a data processing system 30 according to a first embodiment of the present invention.

[0013] The data processing system 30 of this embodiment is configured by a computer having a processor (CPU) 1, a memory 2, an auxiliary storage device 3, and a communication interface 4. The data processing system 30 may also have an input interface 5 and an output interface 6.

[0014] The processor 1 is a computing device that executes programs stored in the memory 2. The processor 1 executes various programs to realize functional units (a correction unit 320, an intervention proposal / effect assessment unit 330, and an input / output unit 340) provided by the data processing system 30. Note that some of the processing performed by the processor 1 by executing the programs may be executed by other computing devices (for example, hardware such as ASIC or FPGA).

[0015] The memory 2 includes a ROM, which is a non-volatile storage element, and a RAM, which is a volatile storage element. The ROM stores unchanging programs (e.g., BIOS), etc. The RAM is a high-speed, volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores programs executed by the processor 1 and data used when the programs are executed.

[0016] The auxiliary storage device 3 is a large-capacity, non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD), and constitutes the database unit 310. The auxiliary storage device 3 also stores data (such as an analysis result database 311) used by the processor 1 when executing a program, and the program executed by the processor 1. That is, the program is read from the auxiliary storage device 3, loaded into the memory 2, and executed by the processor 1, thereby realizing each function of the data processing system 30.

[0017] The communication interface 4 is a network interface device that controls communication with other devices (for example, the terminal 500) in accordance with a predetermined protocol.

[0018] The input interface 5 is an interface to which input devices such as a keyboard 7 and a mouse 8 are connected and which receives input from an operator. The output interface 6 is an interface to which output devices such as a display device 9 and a printer (not shown) are connected and which outputs the results of program execution in a format that can be viewed by an operator. Note that a user terminal (not shown) connected to the data processing system 30 via a network may provide the input and output devices. In this case, the data processing system 30 may have a web server function, and the user terminal may access the data processing system 30 using a predetermined protocol (for example, http).

[0019] The programs executed by the processor 1 are provided to the data processing system 30 via removable media (CD-ROM, flash memory, etc.) or a network, and are stored in a non-volatile auxiliary storage device 3, which is a non-transitory storage medium. For this reason, the data processing system 30 should preferably have an interface for reading data from removable media.

[0020] The data processing system 30 is a computer system configured on a single physical computer or on multiple logically or physically configured computers, and may operate on a virtual computer constructed on multiple physical computer resources. For example, the correction unit 320, intervention proposal / effect assessment unit 330, and input / output unit 340 may each operate on separate physical or logical computers, or multiple units may be combined to operate on a single physical or logical computer.

[0021] FIG. 2 is a configuration diagram of a data processing system 30 according to the first embodiment of the present invention.

[0022] The data processing system 30 of the first embodiment includes a database unit 310, a correction unit 320, an intervention proposal / effect assessment unit 330, and an input / output unit 340. The input / output unit 340 includes a reception unit 341 that receives purchase information (so-called ID-POS data) from a private business operator 40 such as a retailer, a family structure estimation unit 343 that estimates a family structure for each of the received purchase data, a subject identification unit 344 that identifies a subject from the estimated family structure and outputs information for identifying the subject, such as family structure, age, and gender, a purchase information selection unit 342 that selects purchase information for the identified subject, a result selection unit 345 that selects information on the identified subject from the output result of the intervention proposal / effect assessment unit 330, and an output unit 346 that outputs information on the subject and advice on product sales.

[0023] The private business operator 40 uses the POS system to advertise to encourage the purchase of a product suitable for the target person in accordance with the advice output from the output unit 346.

[0024] The database unit 310 has an analysis results database 311. The analysis results database 311 stores the analysis results of health data 210 held by local governments and the like, which are provided by the local government health data system 20. The correction unit 320 has an information conversion unit 322 that converts purchase information into nutrient information. The intervention proposal and effect assessment unit 330 has a health prediction model 331, an advice generation unit 332, and an intervention effect assessment unit 333. The intervention proposal and effect assessment unit 330 has a health prediction model 331, an advice generation unit 332, and an intervention effect assessment unit 333.

[0025] The municipal health data system 20 collects health data 210 of residents 10, and includes a data analysis and health prediction unit 220 that analyzes the health data 210 and predicts their future health status, and an advice generation unit 230 that generates advice for residents 10 based on the prediction results of their future health status.

[0026] When the input / output unit 340 receives the selected purchasing information, the correction unit 320 converts the received purchasing information into nutrient information. The health prediction model 331 predicts the subject's health using the nutrient information. The advice generation unit 332 generates advice based on the health prediction and the subject information. The intervention effect assessment unit 333 assesses the effect of changes based on time-series changes in the purchasing information. The intervention effect assessment unit 333 may be configured, for example, based on a model. The input / output unit 340 selects a subject for the generated advice and intervention effect, and outputs the generated advice and intervention effect to the selected subject.

[0027] It is desirable for the health prediction model 331 to be generated based on machine learning or the like from the health data 210, but as mentioned above, it is difficult to utilize the health data 210 held by a local government. In this embodiment, the results of statistically analyzing the health data 210 and anonymized data are stored in the analysis result database 311, and the health prediction model 331 is created based on the analysis result database 311. Because the analysis result database 311 stores statistical information and anonymized data that do not contain personal information, there is no need to obtain consent from residents and the like.

[0028] Next, the analysis result database 311 will be described. First, as shown in FIG. 3, the nutrient intake information for each subject in the health data 210 is mapped to an N-dimensional space (N is a positive integer) and clustered. The nutrient intake information may be reduced in dimensionality using principal component analysis (PCA) or other methods to group closely related nutrients and reduce computational costs. Next, the partial regression coefficients and intercepts of each nutrient in the multiple regression model for outcomes are calculated for each cluster (CL-1, CL-2, CL-3, CL-4, and CL-5 in FIG. 3). Outcomes are factors that affect the health of the subject. For example, outcomes for pregnant women include the birth weight of a child and the diversity of intestinal microbiota, while outcomes for elderly people include the risk of frailty, dementia, and heart disease. Note that a trained neural network may be used instead of a multiple regression model.

[0029] The health prediction model 331 determines, from the subject's nutrient information, which of the above-mentioned clusters the nutrient information belongs to, and applies the multiple regression model of the cluster to which the nutrient information belongs.

[0030] Figure 4 is a diagram showing an example of partial regression coefficients and intercepts for each cluster for outcomes recorded in the analysis result database 311, and shows the partial regression coefficients and intercepts for ingested nutrients in a multiple regression model when gut microbiota diversity is the outcome. The analysis result database 311 registers the cluster information in Figure 3 (surface coordinate information and center of gravity information for each cluster, etc.) and the partial regression coefficients and intercept information for each outcome in Figure 4. The partial regression coefficients and intercepts are explanatory variables of the multiple regression model, and the outcome is the target variable of the multiple regression model.

[0031] A multiple regression model can be created using the following procedure. First, the subject's nutritional intake information is mapped to identify the corresponding cluster. If the mapped coordinates are located in the gap between clusters or outside a cluster and do not belong to any cluster, the situation of not belonging to any cluster can be avoided by assigning the mapped coordinates to the cluster closest to the center of gravity. Alternatively, clusters can be identified by assigning the mapped coordinates to the cluster with the closest distance to the center of gravity based on the center of gravity information of each cluster. In this case, surface coordinate information of the cluster is not required, thereby reducing data volume and computational costs. A multiple regression model that predicts outcomes is created based on the partial regression coefficients and intercepts of the identified clusters. If a multiple regression model were created using all elements, the model would be inaccurate for elements that are quadratic functions, for example. However, by dividing the data into clusters, the likelihood of linear approximation within the cluster increases, allowing for the creation of a more accurate model and the generation of appropriate advice that takes diversity into account.

[0032] The data processing system 30 in Example 1 includes a computing device (processor 1) that executes computations and storage devices (memory 2, auxiliary storage device 3) accessible by the processor 1. It also includes a reception unit 341 that receives input data, an information conversion unit 322 that converts the input data, a health prediction model 331 generated based on nutrient information and outcomes, and an output unit 346 that outputs subject information based on prediction results from the health prediction model 331. The reception unit 341 receives input data related to the business's customers, the information conversion unit 322 converts the input data into customer nutrient information indicating the nutrients consumed by the business's customers, the health prediction model 331 predicts health from the customer nutrient information, and the output unit 346 outputs health advice or subject information to the business based on the prediction results. This allows private businesses to improve the health of residents and reduce medical costs. Private businesses can utilize knowledge gained from cohort studies without directly accessing health data held by local governments. This data can be used to develop health services, which is expected to increase the number of users by expanding services and optimize inventory by predicting purchases, thereby improving profits.

[0033] <Example 2> In the first embodiment described above, the nutrient information obtained from the purchasing information is treated as the total nutrient intake of the subject during a certain period. However, in reality, the subject purchases food from multiple retailers and eats out, so they also consume nutrients that are not included in the purchasing information. Therefore, there is a problem that accurate nutrient intake cannot be obtained using only the purchasing information of a specific retailer. In the second embodiment, this problem is solved by providing a purchasing information correction unit 321 in the correction unit 320. In the second embodiment, differences from the first embodiment described above will be mainly explained, and explanations of the same configurations and functions as in the first embodiment will be omitted.

[0034] FIG. 5 is a configuration diagram of a data processing system 30 according to the second embodiment.

[0035] The data processing system 30 of the second embodiment includes a database unit 310, a correction unit 320, an intervention suggestion and effect assessment unit 330, and an input / output unit 340. The correction unit 320 includes a purchase information correction unit 321 and an information conversion unit 322 that converts purchase information into nutrient information.

[0036] FIG. 6 is a configuration diagram of the purchase information correction unit 321 according to the second embodiment.

[0037] The purchase information correction unit 321 includes an average purchase per capita calculation unit 3211 , a comparator 3210 , a factor determination unit 3216 , a correction value generation unit 3217 , multipliers 3212 , 3213 , 3214 , and an adder 3215 .

[0038] The average purchase per person calculation unit 3211 calculates a reference value using the purchase information and family composition information of multiple subjects. The family composition information may be provided by the subjects or may be inferred from the purchase information. The average purchase per person calculation unit 3211 classifies the input purchase information by purchase item using a classifier, and calculates the average purchase amount per person for each purchase item, which serves as a reference value, from the purchase information and family composition information for each purchase item. Purchase items include, for example, grains, meat, fish, soy products, dairy products, vegetables, potatoes, seaweed, fruits, oils and fats, and seasonings, and generally have the distribution shown in Figure 7. The average purchase amount is the purchase amount or weight.

[0039] There are several possible reasons why a subject's purchase volume is low. These include: (1) purchasing from other retailers; (2) purchasing some foods from other retailers (e.g., buying vegetables from a greengrocer and rice online); and (3) not purchasing certain foods due to hobbies or preferences. While there is no need to correct for factor (3), in order to correct for the decrease in purchase volume due to factors (1) and (2), the comparator 3210 first compares the calculated reference value with the subject's purchase information. Based on the calculated reference value and the subject's family composition, reference purchase information is calculated and compared with the subject's purchase information. Factor (1) results in a decrease in overall purchase volume. Therefore, the factor determination unit 3216 determines that factor (1) is the cause if the ratio (k1) of the average purchase volume of each purchase item in the subject's purchase information to the reference purchase information is equal to or less than threshold 1 (th1). Threshold 1 (th1) is calculated by subtracting the standard deviation from the average of the purchasing information of multiple subjects used to calculate the reference value, resulting in a statistically significant threshold. The purchasing information of subjects determined to be affected by factor (1) is corrected by multiplying all items by th1 / k1. Specifically, the correction value generator 3217 generates a correction value, and the multiplier 3214 multiplies the generated correction value by the subject's purchasing information and outputs the result. This correction corrects for the decrease in purchasing volume due to factor (1) and prevents discontinuous purchasing volume relative to k1. Furthermore, when k1 is extremely small, the correction may result in large errors. Therefore, if k1 is below a certain threshold 2 (th2), correction is deemed unacceptable and the subject is excluded from subsequent processing, thereby preventing low-accuracy health predictions. Threshold 2 (th2) is calculated by subtracting 2 × the standard deviation from the average of the purchasing information of multiple subjects used to calculate the reference value, resulting in a statistically significant threshold.

[0040] Although it is difficult to distinguish between factors (2) and (3), extremely low amounts of grains and vegetables can be determined to be factor (2). If factor (1) is not met and the purchase volume of grains and vegetables is below a predetermined threshold 3 (th3), the factor determination unit 3216 determines that factor (2) is the cause. Threshold 3 (th3) is a statistically significant threshold value obtained by subtracting 2 × standard deviation from the average of the purchase information of multiple subjects used to calculate the reference value. Purchase volumes of grains and vegetables below threshold 3 are corrected to the average purchase information × th3 / average value, thereby preventing excessive correction and ensuring continuity. Specifically, the correction value generation unit 3217 generates a correction value, and the multiplier 3213 multiplies the generated correction value by the average purchase volume per person and the subject's family composition and outputs the result.

[0041] If the factor determining unit 3216 determines that correction is not necessary or that the factor is unknown, it outputs a correction value of 1 to the multipliers 3213 and 3114 .

[0042] Adder 3215 adds the output of multiplier 3213 and the output of multiplier 3214 and outputs the result as corrected nutrient information. In this way, a decrease in purchase volume due to purchases at another retail store can be corrected.

[0043] The data processing system 30 of Example 2 has a purchase information correction unit 321 that corrects data input to the information conversion unit 322, and the reception unit 341 receives purchase information of the business's customers. The purchase information correction unit 321 corrects purchase information whose purchase volume is smaller than a predetermined threshold by multiplying it by a correction value, thereby making it possible to predict the health of a wide range of users and accurately predict the health of a larger number of subjects.

[0044] In addition, the purchasing information correction unit 321 has a comparator 3210 that compares the purchasing information of the business's customers with the purchasing information of multiple customers of the business, a factor determination unit 3216 that determines the factor behind the low purchasing volume of the purchasing information of the business's customers based on the comparison result by the comparator 3210, and a correction value generation unit 3217 that generates a correction value corresponding to the determined factor.The purchasing information correction unit 321 corrects the purchasing information by multiplying the generated correction value by the purchasing information, so that it is possible to correct the purchasing volume for each inferred factor, and appropriate correction can be made to suit the characteristics of the subject, allowing for accurate health prediction.

[0045] Example 3 In the first embodiment described above, the nutrient information extracted from the purchase information and the nutrient information in the analysis result database 311 are treated in the same way. This treatment is possible if both types of nutrient information are extracted from the same type of information, but in many cases they are different. The BDHQ (Brief-type self-administered Diet History Questionnaire) is a widely used form of nutrient information in the local government health data 210. The BDHQ quantitatively examines the intake status of nutrients and foods based on a questionnaire given to subjects. Treating nutrient information obtained by different methods, such as the BDHQ and purchase information, as the same nutrient information reduces accuracy. In the third embodiment, this problem is solved by providing a nutrient information comparison and correction unit 323 in the correction unit 320. In the third embodiment, differences from the first embodiment described above will be mainly described, and descriptions of the same configurations and functions as those in the first embodiment will be omitted.

[0046] FIG. 8 is a configuration diagram of a data processing system 30 according to the third embodiment.

[0047] The data processing system 30 of the third embodiment has a database unit 310, a correction unit 320, an intervention proposal and effect assessment unit 330, and an input / output unit 340. The database unit 310 has an analysis result database 311 and a nutrition survey database 312. The nutrition survey database 312 stores nutrition survey data from the Ministry of Health, Labor and Welfare. The nutrition survey database 312 may be configured to be referenced online. The correction unit 320 has an information conversion unit 322 that converts purchase information into nutrient information, and a nutrient information comparison and correction unit 323. The intervention proposal and effect assessment unit 330 has a health prediction model 331, an advice generation unit 332, and an intervention effect assessment unit 333.

[0048] FIG. 9 is a configuration diagram of the nutrient information comparison and correction unit 323 in the third embodiment.

[0049] The nutrient information comparison and correction unit 323 has a comparator 3230 and a multiplier 3231, and uses the results of a nutrition survey conducted by the Ministry of Health, Labor and Welfare as the reference value for correction. The nutrition survey is conducted by BDHQ and is suitable as the reference value. The comparator 3230 compares the intake of various nutrients in the nutrition survey results of the Ministry of Health, Labor and Welfare with the intake of various nutrients calculated from the purchasing information, and calculates the ratio of the latter to the former for each intake nutrient (kk1 to kkn, where n is the total number of nutrients). The multiplier 3231 multiplies kk1 to kkn as a correction value to correct the nutrient information of the subject. The nutrition survey results of the Ministry of Health, Labor and Welfare are surveyed by prefecture, and can be corrected taking into account regional characteristics.

[0050] Although the second and third embodiments have been described separately above, the second and third embodiments may be combined to form a data processing system including elements of both the second and third embodiments.

[0051] The data processing system 30 of Example 3 has a nutrient information comparison and correction unit 323 that corrects the customer nutrient information input to the health prediction model based on the results of comparing the data obtained from the nutrition survey database with the customer nutrient information, thereby eliminating mismatches between purchasing information and nutrient information and improving prediction accuracy.

[0052] The present invention is not limited to the above-described embodiments, but includes various modifications and equivalent configurations within the spirit and scope of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to configurations including all of the described configurations. Furthermore, part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, part of the configuration of each embodiment may be added, deleted, or replaced with other configurations.

[0053] Furthermore, the aforementioned configurations, functions, processing units, processing means, etc. may be realized in part or in whole in hardware, for example by designing them as integrated circuits, or may be realized in software by having a processor interpret and execute a program that realizes each function.

[0054] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC card, an SD card, or a DVD.

[0055] In addition, the control lines and information lines shown are those that are considered necessary for explanation, and do not necessarily represent all the control lines and information lines that are necessary for implementation. In reality, it can be assumed that almost all components are interconnected. [Explanation of symbols]

[0056] 1: Processor (CPU) 2: Memory 3:Auxiliary storage device 4: Communication interface 5: Input interface 6: Output interface 7: Keyboard 8: Mouse 9: Display device 10: Residents 20: Municipal Health Data System 30: Data Processing System 40:Private business operator 210: Health Data Database 220: Data Analysis and Health Prediction Department 230: Advice generation unit 310: Database Department 311: Analysis results database 312: Nutrition Survey Database 320: Correction unit 321:Purchase information correction department 322: Information conversion unit 323: Nutrition information comparison and correction section 330: Intervention proposal and effectiveness assessment department 331: Health Prediction Model 332: Advice generation unit 333: Intervention Effect Assessment Department 340: Input / output section 341: Reception 342: Purchasing Information Selection Department 343:Family Information Inference Department 344: Target Identification Department 345: Result selection section 346: Output section 3210: Comparator 3211: Average per capita purchase amount calculation section 3212, 3213, 3214: Multipliers 3215: Adder 3216: Factor determination unit 3217: Correction value generation unit 3230: Comparator 3231: Multiplier

Claims

1. 1. A data processing system comprising: A computing device that executes computational processing and a storage device that can be accessed by the computing device, a reception unit that receives input data including purchase information of customers of the business; a family structure estimation unit that estimates a family structure from the purchasing information; a subject identification unit that identifies a subject based on the family structure and outputs subject information of the identified subject; an information conversion unit that converts the input data into customer nutrient information indicating nutrients taken by the customer; A health prediction model generated based on nutrient information and outcomes, which predicts health from the customer's nutrient information; an advice generation unit that generates advice based on the health prediction result and the subject information; and an output unit that outputs the generated advice for the subject to the business operator.

2. 2. The data processing system of claim 1, A data processing system characterized by having a nutrient information comparison and correction unit that corrects the customer nutrient information input into the health prediction model based on the results of comparing data obtained from a nutrition survey database with the customer nutrient information.

3. A data processing system according to claim 2, an information correction unit that corrects data input to the information conversion unit; The data processing system is characterized in that the information correction unit corrects purchase information in which the purchase amount is smaller than a predetermined threshold by multiplying the purchase information by a correction value.

4. A data processing system according to claim 1, an information correction unit that corrects data input to the information conversion unit; The data processing system is characterized in that the information correction unit corrects purchase information in which the purchase amount is smaller than a predetermined threshold by multiplying the purchase information by a correction value.

5. A data processing system according to claim 3 or 4, The information correction unit a comparator for comparing the customer's purchasing information with the purchasing information of a plurality of customers; a factor determining unit that determines a factor of a low purchase volume of the customer's purchase information based on the comparison result by the comparator; a correction value generating unit that generates a correction value corresponding to the determined factor; A data processing system, comprising: a data processing unit for correcting the purchasing information by multiplying the purchasing information by the generated correction value.

6. 2. The data processing system of claim 1, It has an analysis result database that stores the analysis results showing the relationship between nutritional information and outcomes based on the analysis results of residents' health data, A data processing system characterized in that the health prediction model is generated based on analysis results stored in the analysis result database.

7. 7. The data processing system of claim 6, The health prediction model is composed of a multiple regression model, A data processing system characterized in that the analysis result database includes partial regression coefficients and intercepts of nutrients in a multiple regression model for the outcome.

8. A computer-implemented data processing method, comprising: the computer includes an arithmetic unit that executes arithmetic processing and a storage device that can be accessed by the arithmetic unit; The data processing method includes: a receiving procedure for receiving input data including purchase information of the business's customers; a family structure estimation step of estimating a family structure from the purchasing information; a subject identification step of identifying a subject from the family structure and outputting subject information of the identified subject; an information conversion step of converting the input data into customer nutrient information indicating nutrients ingested by the customer; a prediction step of predicting health from the customer's nutrient information using a health prediction model generated based on nutrient information and outcomes and predicting health from the customer's nutrient information; an advice generation step of generating advice based on the health prediction result in the prediction step and the subject information; and an output step of outputting the generated advice for the subject to the business operator.

Images