Information processing apparatus and information processing method

Abstract

To provide an information processor and an information processing method for supporting business to a customer belonging to an organization.SOLUTION: An information processing device (10) includes: a database (11) which stores sales information on sales to a customer, attribute information on an attribute of the customer, organization identification information capable of identifying an organization to which the customer belongs, and organization sales result information on a sales result of a predetermined commodity for the organization to which the customer belongs in association with the customer identification information capable of identifying the customer; a customer sales result prediction unit (12) which predicts a customer sales result which is a sales result of a commodity for the customer for each of the organization identification information on the basis of at least the sales information and the organization sales result information; and a use probability prediction unit (14) which predicts a probability that the customer sales result is not less than a predetermined value as a commodity use probability on the basis of the attribute information.SELECTED DRAWING: Figure 4

Description

[Technical Field]

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

[0002] Patent Document 1 discloses a sales support system. The prediction system of this sales support system includes a prediction model generation device and a prediction device. The prediction model generation device generates a prediction model used to predict customers and products with a high probability of receiving orders, based on the attributes of each of multiple customers who have been the target of sales activities in the past, i.e., multiple customers with sales results, the sales activity history for each existing customer, and the attributes of the products that have been the target of sales. An acquisition unit of the prediction model generation device acquires, as data used to generate the prediction model, identification information for each of multiple customers who have been the target of sales activities in the past, i.e., multiple customers with sales results in the past, attribute data for each customer, attribute data for the products that have been the target of sales, and data on whether the order was successful. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2021 / 192198 Summary of the Invention [Problem to be solved by the invention]

[0004] The Sustainable Development Goals (SDGs), formulated by the United Nations (UN) in September 2015, aim to realize a sustainable and equal world, and Goal 3.8 of the SDGs calls for achieving universal health coverage (UHC).

[0005] This includes financial risk protection, quality health services, and access to safe and effective essential medicines.

[0006] However, rising prices by pharmaceutical and medical device companies are putting pressure on healthcare finances, and the current situation where many people cannot receive appropriate medical care is a problem. Furthermore, the pharmaceutical industry spends a large amount of marketing money, and up to 30% of that is wasted through inefficient activities. This is because the target customers are not clearly identified.

[0007] This invention aims to improve the efficiency of marketing activities for pharmaceuticals and medical devices, reduce waste by accurately identifying target customers, and contribute to controlling pharmaceutical prices, thereby contributing to the achievement of UHC, one of the SDGs, and ensuring that more people have access to high-quality medical care.

[0008] However, there are cases where the target customer for sales belongs to an organization such as a company. In such cases, sales are made to the customer, but orders for products from the customer are made through the organization, and the organization often places orders for multiple customers at once. For this reason, it is difficult to obtain data on the success or failure of orders for each customer, making it difficult for the sales support system described in Patent Document 1 to support sales.

[0009] Therefore, an object of the present disclosure is to provide an information processing device and an information processing method that can support sales to customers who belong to an organization. [Means for solving the problem]

[0010] In order to solve the above problem, an information processing device of a first aspect of the present invention comprises: a storage means for storing sales information related to sales to customers, attribute information related to the attributes of the customers, organization identification information capable of identifying the organization to which the customers belong, and organization sales performance information related to sales performance of a specified product to the organization to which the customers belong, in association with customer identification information capable of identifying the customers; a customer sales performance prediction means for predicting customer sales performance, which is the sales performance of the specified product to the customers, for each of the organization identification information based on at least the sales information and the organization sales performance information; and a usage probability prediction means for predicting the probability that the customer sales performance will be equal to or greater than a specified value as a usage probability of the product, based on the attribute information.

[0011] A second aspect of the present invention is an information processing device of the first aspect, comprising a similarity determination means for determining, based on the attribute information, the similarity between customers who are predicted to have customer sales performance by the customer sales performance prediction means, among the customers stored in the storage means.

[0012] A third aspect of the present invention is an information processing device of the first aspect or the second aspect, wherein the usage probability prediction means predicts the usage probability using a trained model that receives input of the attribute information and outputs the probability that the customer sales performance is greater than or equal to a predetermined value.

[0013] A fourth aspect of the present invention is the information processing device according to the first or second aspect, wherein the sales information includes the number of sales made to the customer.

[0014] A fifth aspect of the present invention is an information processing method using an information processing device, wherein the information processing device executes a storage step of storing sales information related to sales to customers, attribute information related to attributes of the customers, organization identification information capable of identifying an organization to which the customers belong, and organization sales performance information related to sales performance of a predetermined product to the organization to which the customers belong, in a storage means, in association with customer identification information capable of identifying the customers; a customer sales performance prediction step of predicting customer sales performance, which is sales performance of the predetermined product to the customers, for each of the organization identification information based on at least the sales information and the organization sales performance information; and a usage probability prediction step of predicting the probability that the customer sales performance will be equal to or greater than a predetermined value as a usage probability of the product, based on the attribute information. [Effects of the Invention]

[0015] According to the present disclosure, it is possible to provide an information processing device and an information processing method that can support sales to customers who belong to an organization. [Brief explanation of the drawings]

[0016] [Figure 1] FIG. 10 is an explanatory diagram showing an example of sales by a user. [Figure 2] 1 is a schematic diagram of an information processing system including an information processing device according to an embodiment of the present invention. [Figure 3] FIG. 2 is an explanatory diagram illustrating an example of a hardware configuration. [Figure 4] 1 is a block diagram of an information processing apparatus according to an embodiment of the present invention; [Figure 5] FIG. 2 is an explanatory diagram showing an example of organization information and organization sales performance information stored in a database. [Figure 6] FIG. 2 is an explanatory diagram showing an example of a customer's specialty field among the customer attribute information stored in the database. [Figure 7] FIG. 2 is an explanatory diagram showing an example of customer membership information among customer attribute information stored in a database. [Figure 8]FIG. 10 is an explanatory diagram showing an example of customer's attending academic societies among the customer's attribute information stored in the database. [Figure 9] FIG. 10 is an explanatory diagram illustrating an example of a prediction result of customer sales performance. [Figure 10] FIG. 10 is an explanatory diagram showing an example of similarity between customers. [Figure 11] FIG. 10 is an explanatory diagram showing an example of a prediction result of a use probability of a customer using a product. [Figure 12] 10 is a flowchart illustrating an example of processing executed by an information processing device. [Figure 13] FIG. 10 is an explanatory diagram showing an example of a screening result. DETAILED DESCRIPTION OF THE INVENTION

[0017] An embodiment of the present invention will be described with reference to the drawings.

[0018] An information processing device 10 according to an embodiment of the present disclosure is an information processing device 10 capable of supporting sales to customers belonging to an organization. In the following description, the information processing device 10 is described as being capable of supporting sales from a company (user) 30, such as a pharmaceutical company or a medical device manufacturer, to a doctor (customer) 20a belonging to a hospital (affiliated organization) 20. Note that organizations, customers, and users are not limited to hospitals, doctors, pharmaceutical companies, and medical device manufacturers. In other words, the information processing device and information processing method according to the present disclosure can support sales in various fields other than the medical field.

[0019] (sales) 1 is an explanatory diagram showing an example of sales by a user. In FIG. 1, three hospitals 20 are shown as business partners of a company 30.

[0020] As shown in FIG. 1, doctor 20a, who is the target of sales from company 30, belongs to hospital 20. Company 30 has multiple hospitals 20 (three in FIG. 1) as its business partners. Company 30 may sell certain products (such as certain medicines or certain medical devices in this embodiment) to hospital 20, but may also make sales X1 directly to doctor 20a who belongs to hospital 20. Even when company 30 makes sales X1 directly to doctor 20a, orders for the products from doctor 20a are received via hospital 20. In this case, if multiple doctors 20a belong to hospital 20, hospital 20 places orders X2 for multiple doctors 20a collectively with company 30. After receiving order X2 from hospital 20, company 30 delivers products X3 to hospital 20.

[0021] (system) FIG. 2 is a schematic diagram of a system including an information processing device according to an embodiment of the present invention. As shown in FIG. 2, the information processing device 10 may constitute a part of an information processing system 100. This information processing system 100 includes the information processing device 10 and a user terminal 30a of a company 30 connected to the information processing device 10 via a communication network NW. The user terminal 30a is not particularly limited and may be, for example, a desktop or laptop personal computer or a tablet terminal. The communication network NW may be wired or wireless. Note that the information processing device 10 does not have to constitute a part of the information processing system 100. For example, the information processing device 10 may be directly operated and used by the company 30 or a service provider that provides sales support.

[0022] (Hardware configuration) Fig. 3 is an explanatory diagram showing an example of a hardware configuration. As shown in Fig. 3, information processing device 10 is a device that performs calculations such as a computer, and includes a CPU (Central Processing Unit) 210, a ROM (Read-Only Memory) 220, a RAM (Random Access Memory) 230, an auxiliary storage device 240, a communication I / F 250, an input device 260, a display device 270, a storage medium I / F 280, etc. Note that user terminal 30a of company 30 may also have a similar configuration.

[0023] The CPU 210 is a device that executes programs stored in the ROM 220, performs arithmetic processing on data loaded into the RAM 230 in accordance with instructions from the programs, and controls the entire information processing device 10. The ROM 220 stores the programs and data to be executed by the CPU 210. When the CPU 210 executes a program stored in the ROM 220, the programs and data to be executed are loaded into the RAM 230, and the RAM 230 temporarily holds the arithmetic data during the calculation.

[0024] The auxiliary storage device 240 is a device that stores the OS (Operating System), which is basic software, the application program according to this embodiment, and other related data. The auxiliary storage device 240 is, for example, a hard disk drive (HDD) or flash memory.

[0025] The communication I / F 250 is an interface for connecting to a communication network NW such as a wired or wireless LAN (Local Area Network) or the Internet, and for transmitting and receiving data to and from other devices that provide communication functions.

[0026] The input device 260 is a device such as a keyboard for inputting data to the information processing device 10. The display device 270 is a device formed of an LCD (Liquid Crystal Display) or the like, and functions as a user interface when using the functions of the information processing device 10 or when making various settings. The storage medium I / F 280 is an interface for transmitting and receiving data to and from storage media such as CD-ROM, DVD-ROM, and USB memory. If the display device 270 is a touch panel type, it may function as an input device for inputting various types of data in addition to its display function.

[0027] The information processing device 10 functions as a storage means, a customer sales performance prediction means, a similarity determination means, and a usage probability prediction means by the CPU 210 executing information processing in cooperation with software such as a program stored in the ROM 220 or the auxiliary storage device 240. Note that some of the functions of the CPU 210 of the information processing device 10 may be extracted and provided in another information processing device, and processing may be executed using a plurality of information processing devices connected to each other.

[0028] (Information processing device) Fig. 4 is a block diagram of an information processing device according to one embodiment of the present invention. As shown in Fig. 4, information processing device 10 of this embodiment includes database (storage means) 11, customer sales performance prediction unit (customer sales performance prediction means) 12, and use probability prediction unit (use probability prediction means) 14. In addition, information processing device 10 of this embodiment further includes similarity determination unit (similarity determination means) 13.

[0029] (Database) FIG. 5 is an explanatory diagram showing an example of organizational information and organizational sales performance information stored in the database. FIG. 6 is an explanatory diagram showing an example of a customer's specialty field among the customer attribute information stored in the database. FIG. 7 is an explanatory diagram showing an example of customer membership information among the customer attribute information stored in the database. FIG. 8 is an explanatory diagram showing an example of a customer's participating academic societies among the customer attribute information stored in the database. As shown in FIGS. 6 to 8, qualitative data is converted into quantitative data (for example, "applicable: 1", "not applicable: 0", etc.) and stored in the database.

[0030] As shown in FIGS. 5 to 8, the database 11 stores sales information 600, attribute information 700, organization information 400, and organization sales performance information 500 in association with customer identification information 300.

[0031] (Identification information) As shown in FIGS. 5 to 8, the customer identification information 300 is information that can identify (specify) a specific doctor 20a from among multiple doctors 20a stored in the database 11. When information about a new doctor 20a is registered in the database 11, unique customer identification information 300 is attached and stored. As shown in FIGS. 5 to 8, in this embodiment, an ID number (customer identification information 300) associated with the doctor 20a is attached as the customer identification information 300. For example, FIG. 5 illustrates information about 20 doctors 20a with ID numbers "2585" to "2604." Note that the names of the doctors 20a (not shown) are also registered in the database 11 in association with the ID numbers (customer identification information 300).

[0032] (Organization information) As shown in FIG. 5, organizational information 400 regarding the hospital 20 to which the doctor 20a belongs includes at least organizational identification information 401 ("facility code" in this embodiment) capable of identifying the hospital 20. That is, the database 11 stores organizational identification information capable of identifying the organization to which the customer belongs. When information about a new hospital 20 is registered in the database 11, the information is stored with unique organizational identification information 401. In this embodiment, the organizational information 400 includes, in addition to the organizational identification information 401, location information 402 and size information 403 of the hospital 20. In FIG. 5, the location information 402 is a "prefecture code" associated with each prefecture, and the size information 403 is a "hospital type (code)" associated with each size ("small hospital," "medium-sized hospital," and "large hospital") according to the number of beds of the hospital 20. Such organizational information 400 may be obtained and registered when the doctor 20a is registered in the database 11, or may be obtained and registered after the doctor 20a is registered in the database 11.

[0033] For example, three doctors 20a (ID numbers "2585" to "2587") belong to the hospital 20 with facility code "110015" shown in FIG. 5, and the "prefecture code" of the hospital 20 is "1 (e.g., Hokkaido)" and the "hospital type" is "1 (e.g., large hospital)." Note that the name of the hospital 20 (not shown) is also registered in the database 11 in association with the facility code (organization identification information 401). Furthermore, the organization information 400 is not limited to the above, and may include, for example, the "number of staff members" and the "number of medical departments."

[0034] (Organization sales performance information) The organizational sales performance information 500 is information regarding the sales performance of a predetermined product (hereinafter referred to as "product Z") of the company 30 to the hospital 20 to which the doctor 20a belongs. The organizational sales performance information 500 may be the organizational sales performance itself (sales performance of product Z to the affiliated organization) or information from which the organizational sales performance can be calculated (for example, the unit price and order quantity of product Z). The organizational sales performance information 500 may also be information regarding the organizational sales performance for a predetermined period. Although accurate values ​​are preferable for the organizational sales performance information 500, approximate values ​​may also be used. The organizational sales performance information 500 may be registered in the database 11 together with the organization information 400 and the doctor 20a belonging to the hospital 20 when organizational sales performance occurs. Alternatively, the organizational sales performance information 500 may be additionally registered in the database 11 in association with a hospital 20 already registered in the database 11 when organizational sales performance occurs.

[0035] For example, Fig. 5 illustrates organizational sales performance (yen) as organizational sales performance information 500. Specifically, the "organization sales performance" of product Z of company 30 to the hospital with "facility code: 110015" shown in Fig. 5 is "1,791,360 (yen)."

[0036] (Business information) The sales information 600 is at least one piece of information related to sales of Product Z to each doctor 20a, such as the number of sales made to that doctor 20a, the type of sales, and whether or not samples were provided. The sales information 600 also includes information that sales have not yet been made to that doctor 20a. The sales information 600 may be all information related to past sales of Product Z, or may be information related to sales of Product Z during the specified period (the period for which the organizational sales performance is calculated). The number of sales is the number of sales made to the doctor 20a (including 0). The type of sales is the type of sales made to the doctor 20a, such as visits (face-to-face), telephone sales, sales via web meetings, sales via email (including direct mail and email newsletters), and sales via lectures. The presence or absence of sample provision is information related to whether or not product samples were provided to the doctor 20a. Among these, it is preferable that the sales information 600 include the number of sales made to that doctor 20a, from the viewpoint of improving the accuracy of predicting the customer sales performance 800 described below. This "number of sales visits" may be the number for each of the sales modes, or the total number of sales visits including all the sales modes. In this embodiment, as shown in FIG. 5, the database 11 stores, as sales information 600, a number of sales visits 601 including the number of sales visits and the sales mode. The "number of sales visits" is the number of times that salespeople have visited the doctor 20a for product Z. After a sales visit to the doctor 20a, such sales information 600 may be additionally registered in the database 11 in association with the ID number (customer identification information 300) of the doctor 20a that is already registered in the database 11. Note that the sales information 600 is not limited to the number of sales visits, the sales mode, and whether or not samples were provided, but may also include various information related to sales (e.g., the sales representative, etc.).

[0037] For example, the company 30 has made one sales visit (number of sales visits: 1) regarding product Z to a doctor with "ID number: 2585" who belongs to a hospital with "facility code: 110015" shown in FIG.

[0038] (Customer attribute information) The attribute information 700 is a plurality of pieces of information (including cases where the attributes are unknown) relating to the attributes of each doctor 20a, and there is no particular limitation on how it is obtained. The attribute information 700 is not particularly limited as long as it is information relating to the attributes of the doctor 20a, and examples thereof include the information (items) shown in Figures 6 to 8. Even if specific information relating to the attributes is not available, the attribute information 700 of "Unknown: 0" is stored. In other words, the attribute information 700 is always stored in association with the doctor 20a registered in the database 11.

[0039] (Information about specialization) As shown in FIG. 6 , the attribute information 700 may include information 701 about the specialty of the doctor 20a. In this embodiment, the information 701 about the specialty of the doctor 20a includes the following items: “cardiologist,” “arrhythmia specialist,” “hypertension specialist,” “arteriosclerosis specialist,” “CVIT (Cardiovascular Intervention and Therapeutics) certified physician,” “CVIT specialist,” “DM (Diabetes) specialist,” and “gastroenterologist.” For example, the doctor with “ID number: 2585” shown in FIG. 6 has a value of “1” in the “cardiologist” and “arrhythmia specialist” fields, and is therefore both a “cardiologist” and an “arrhythmia specialist.” Note that items with a value of “0” are items that indicate “not applicable” or “unknown.” Such information 701 about the specialty of the doctor 20a may be obtained and registered when the doctor 20a is registered in the database 11, or may be obtained and additionally registered after the doctor 20a is registered in the database 11.

[0040] (Information about the designated website) As shown in FIG. 7, the attribute information 700 may also include information 702 about the doctor 20a related to a predetermined information providing website (hereinafter referred to as a "predetermined medical information site").

[0041] In this embodiment, the information 702 of the doctor 20a regarding the predetermined medical information site includes the following items: "Member," "F0" to "F5," "Paid," and "Newsletter." The "Member" item indicates whether the doctor is a member of the predetermined medical information site. The "F1" to "F5" items are, for example, five doctor characteristics described below, and are determined based on the viewing and browsing history of articles (either video articles or text articles) on the predetermined medical information site. If the doctor does not view or browse any articles on the predetermined medical information site (or only a very small number of articles), the doctor is classified as "F0," which does not fall under any of the "F1" to "F5" items. The "Paid" item indicates whether the doctor is a paid member of the predetermined medical information site. "0" is entered for a free member, "1" for a regular paid member, and "2" for a premium paid member. The "Newsletter" item indicates whether the doctor is subscribed to the e-mail newsletter sent by the predetermined medical information site.

[0042] The doctor characteristics "F1" to "F5" included in the information 702 of doctor 20a regarding a predetermined medical information site may be, for example, "cardiologist (specialty) interested in cardiac catheterization treatment: F1," "cardiologist interested in the general treatment of ischemic heart disease: F2," "cardiologist interested in the general treatment of structural heart disease: F3," "cardiologist interested in the cardiovascular system in general (interested in drug therapy rather than catheterization): F4," "cardiologist interested in peripheral intravascular treatment: F5," etc. The number and content of the doctor characteristics are not limited to these. Note that a method for determining doctor characteristics based on the viewing and browsing history of articles on a predetermined medical information site is, for example, the technology disclosed in Japanese Patent Publication No. 7418877.

[0043] For example, the doctor with "ID number: 2585" shown in Figure 7 is not a member of the specified medical information site, so he is classified as "F0:1." Also, the doctor with "ID number: 2587" shown in Figure 7 is a member of the specified medical information site ("Member: 1"), but has no (or very little) viewing or browsing history for articles on the specified medical information site, so he is also classified as "F0:1." Also, the doctor with "ID number: 2592" shown in Figure 7 is a member of the specified medical information site ("Member: 1"), and the doctor characteristics based on his viewing or browsing history for articles on the specified medical information site are "F5:1." Note that items with a value of "0" are items that are "not applicable" or "unknown."

[0044] Such information 702 about doctor 20a related to a predetermined medical information site may be obtained and registered when doctor 20a is registered in database 11, or may be obtained and additionally registered after doctor 20a is registered in database 11. Furthermore, the method for obtaining information 702 about doctor 20a related to a predetermined medical information site is not particularly limited, but may be obtained, for example, by forming a business partnership with a management company that operates the predetermined medical information site, or by operating the predetermined medical information site itself.

[0045] (Information about participating academic societies) Furthermore, as shown in FIG. 8, the attribute information 700 may include information 703 regarding the academic societies attended by doctor 20a. In this embodiment, the information 703 regarding the academic societies attended includes items related to participation in "Academy A," "Academy B," "Academy C," "Academy D," and "Academy E." For example, the doctor with "ID number: 2585" shown in FIG. 8 is not attending any of the academic societies "Academy A," "Academy B," "Academy C," "Academy D," and "Academy E." On the other hand, the doctor with "ID number: 2587" shown in FIG. 8 is attending "Academy B." Note that items with a value of "0" indicate "not participating" or "unknown."

[0046] Such information 703 regarding the academic conferences attended by doctor 20a may be obtained and registered when doctor 20a is registered in database 11, or may be obtained and additionally registered after doctor 20a is registered in database 11. Furthermore, the method for obtaining information 703 regarding the academic conferences attended by doctor 20a is not particularly limited, but may be, for example, information provided by doctor 20a, or obtained by forming a business partnership with a company that organizes an academic conference, or by organizing an academic conference.

[0047] (Other attribute information) 6 to 8, the attribute information 700 may include other information. For example, the attribute information 700 may include, as an attribute of the doctor 20a, information about the hospital 20 to which the doctor 20a belongs (information similar to the organizational information 400). The attribute information 700 may also include information about the doctor 20a's use of the product Z (usage confirmation information), the doctor 20a's age, sex, medical department, alma mater, event participation status, viewing status of articles (content) on a predetermined medical information site, etc.

[0048] When the information processing device 10 can be directly operated, the information stored in the database 11 (the name of the doctor 20a, the organizational information 400, the organizational sales performance information 500, and the variable information; hereinafter, these may be collectively referred to as "registered information") may be input from the input device 260 of the information processing device 10 and stored in the database 11. When the information processing device 10 is used as the information processing system 100 shown in FIG. 2, some or all of the registered information may be acquired from the user terminal 30a of the company 30 via the communication network NW and stored in the database 11, or may be acquired from an external information processing device different from the user terminal 30a of the company 30 via the communication network NW and stored in the database 11.

[0049] (Customer Sales Performance Forecasting Department) 9 is an explanatory diagram showing an example of a prediction result of customer sales performance. As shown in FIG. 9, the customer sales performance prediction unit 12 predicts customer sales performance 800, which is the sales performance of product Z to doctor 20a, for each organization identification information 401 (i.e., for each hospital 20), based on at least sales information 600 and organization sales performance information 500. The customer sales performance prediction unit 12 stores the predicted customer sales performance 800 in the database 11 in association with the customer identification information 300. Note that in this embodiment, the customer sales performance prediction unit 12 predicts customer sales performance 800 based on sales information 600 and organization sales performance information 500, but the present invention is not limited to this. The customer sales performance 800 may be predicted based on attribute information 700, sales information 600, and organization sales performance information 500.

[0050] The customer sales performance 800 is the sales performance of the product Z to each doctor 20a (the order amount or usage amount for each doctor 20a) among the organizational sales performance of the product Z, and it is difficult for an outsider (e.g., the company 30) to know the accurate value. For this reason, in the information processing device 10 according to the present disclosure, the customer sales performance prediction unit 12 predicts the customer sales performance 800 for each organization identification information 401 based on at least the sales information 600 and the organization sales performance information 500. The more independent variables there are for calculating the customer sales performance 800, which is the dependent variable, the better. In other words, it is preferable that the customer sales performance prediction unit 12 predicts the customer sales performance 800 for each organization identification information 401 based on both the attribute information 700 and the sales information 600, and the organization sales performance information 500.

[0051] For example, if three doctors 20a belong to a hospital 20, the customer sales performance prediction unit 12 predicts the customer sales performance 800 of each of the three doctors 20a in the hospital 20 from the organizational sales performance of the hospital 20 based on the business information 600 of each of these three doctors 20a. Note that in this case, the customer sales performance 800 of each doctor 20a is a predicted value predicted based on the attribute information 700 of each doctor 20a, so the sum of the customer sales performance 800 of the three doctors 20a does not have to match the organizational sales performance of the hospital 20 (see the hospital 20 with facility code: 110015 in FIG. 9).

[0052] When predicting the customer sales performance 800, the customer sales performance prediction unit 12 performs an analysis process of the correlation between the items included in the sales information 600 and the organizational sales performance, based on at least the sales information 600 and the organizational sales performance information 500 of the multiple doctors 20a stored in the database 11. As a result, the customer sales performance prediction unit 12 detects the item from the sales information 600 that contributes most to improving the organizational sales performance (the item with the highest correlation coefficient), and uses it to predict the customer sales performance 800. Next, the customer sales performance prediction unit 12 predicts the customer sales performance 800 for each hospital 20 based on the organizational sales performance of the hospital 20 and the above items (the items from the sales information 600 that contribute most to improving the organizational sales performance) of the doctors 20a belonging to the hospital 20. For example, if the item that contributes most to improving the organizational sales performance is the number of sales calls, the customer sales performance prediction unit 12 calculates a customer sales performance prediction value from the organizational sales performance according to the number of sales calls.

[0053] (Similarity determination unit) Fig. 10 is an explanatory diagram showing an example of the similarity between customers. In Fig. 10, the similarity between the doctors 20a in the horizontal row and the doctors 20a in the vertical row is shown in a frame at the intersection.

[0054] 10, the similarity determination unit 13 determines the similarity between doctors 20a who are predicted by the customer sales performance prediction unit 12 to have customer sales performance 800 (not zero) among the multiple doctors 20a stored in the database 11, based on the attribute information 700. Note that the similarity determination unit 13 may also determine the similarity between doctors 20a who have customer sales performance 800 and who are predicted to have customer sales performance 800 equal to or greater than a predetermined value.

[0055] The similarity between doctors 20a is a value that serves as an index when extracting doctors 20a who are presumed to have similar interests or concerns, and is determined based on the attribute information 700. The similarity determination unit 13 performs correlation analysis and similarity analysis based on the attribute information 700 of each doctor 20a to determine the similarity between each doctor 20a. For example, the similarity determination unit 13 vectorizes the attribute information 700 of each doctor 20a and calculates the cosine similarity between these vectors. Specifically, the similarity determination unit 13 can determine the similarity using the following procedure. The similarity determination unit 13 defines the attribute information 700 of each doctor 20a as an N-dimensional vector. For example, if the attribute information 700 is composed of 38 attribute values, the vector of each doctor 20a will be a 38-dimensional vector. Next, the similarity determination unit 13 normalizes the length of each vector to 1. This eliminates the effect of the vector size and enables the directional similarity between vectors to be measured. Then, the similarity determination unit 13 determines the similarity between the doctors 20a based on the calculated cosine similarity. For example, if the cosine similarity exceeds a certain threshold, it is determined that the doctors 20a have similar interests or concerns.

[0056] In FIG. 10, it can be seen that the doctor with the highest similarity to "Doctor A" of "Doctor A Medical Association Hospital" is "Doctor D" of "Doctor B Mutual Aid Hospital," and the similarity is "95.6%." On the other hand, the doctor with the lowest similarity to "Doctor A" is "Doctor F" of "Convalescent Hospital," and the similarity is "23.9%." When outputting (displaying) the similarity on the display device 270 or the like, it may be shown in "%" units as shown in FIG. 10, or simply as a numerical value, or may be shown using criteria such as "high," "medium," and "low." Note that in FIG. 10, "facility code," "ID number," etc. are converted and displayed as "facility name (name of hospital 20)," "doctor name," etc., respectively. "A to G" shown in FIG. 10 are assumed to be the "names" of doctors 20a, respectively.

[0057] (Usage probability prediction section) FIG. 11 is an explanatory diagram showing an example of a prediction result of the usage probability of a customer using a product. As shown in FIG. 11, the usage probability prediction unit 14 predicts the usage probability 900 (hereinafter, may be simply referred to as the "usage probability 900") that a doctor 20a will use product Z based on attribute information 700. The usage probability 900 is the probability that the customer sales record 800 is equal to or greater than a predetermined value. Note that in FIG. 11, "facility code," "ID number," etc. are converted and displayed as "facility name (name of hospital 20)," "doctor name," etc. Each of "A to N" shown in FIG. 11 is assumed to be the "name" of the doctor 20a.

[0058] When predicting the use probability 900, for example, the use probability prediction unit 14 classifies the customer sales records 800 of the multiple doctors 20a stored in the database 11 by defining "0" when the customer sales records 800 are lower than a predetermined value and "1" when the customer sales records 800 are higher than the predetermined value. The use probability prediction unit 14 then performs multivariate analysis (e.g., logistic regression analysis) using the attribute information 700 of the multiple doctors 20a stored in the database 11 as an independent variable and the probability that the customer sales records 800 will be classified as "1" (use probability 900) as a dependent variable. Examples of the predetermined value include the median of the customer sales records 800 of the multiple doctors 20a stored in the database 11 or the average of the customer sales records 800 of the multiple doctors 20a. In this embodiment, the median of the customer sales records 800 of the multiple doctors 20a stored in the database 11 is used as the predetermined value, and classification is performed by defining "0" when the customer sales records 800 are lower than the median and "1" when the customer sales records 800 are higher than the median.

[0059] For example, as shown in FIG. 2, the information processing device 10 may include a prediction model generation unit 15 and a prediction model storage unit 16. The prediction model generation unit 15 receives attribute information 700 of a doctor 20a and generates a prediction model (trained model) that outputs a use probability 900. The prediction model is generated by machine learning the relationship between the attribute information 700 of a plurality of doctors 20a stored in the database 11 and the class (“0” or “1”) of customer sales performance 800. The prediction model generated by the prediction model generation unit 15 is stored in the prediction model storage unit 16. The use probability prediction unit 14 may input the attribute information 700 to the prediction model stored in the prediction model storage unit 16 and predict the use probability 900 of product Z by the doctor 20a.

[0060] Note that the prediction of the use probability 900 by the use probability prediction unit 14 is not limited to the prediction of the use probabilities 900 of multiple doctors 20a stored in advance in the database 11. For example, the use probability prediction unit 14 can also output (predict) the use probability 900 of the product Z in response to input of attribute information 700 of a doctor 20a who is not registered in the database 11.

[0061] (Information processing method) Next, an information processing method according to an embodiment of the present disclosure will be described with reference to Fig. 12. Fig. 12 is a flowchart of an example of processing executed by an information processing device.

[0062] 12, in this process, first, organizational information 400 regarding the hospital 20 to which the doctor 20a belongs, organizational sales performance information 500 of product Z for the hospital 20, attribute information 700 of the doctor 20a, and sales information 600 for the doctor 20a are acquired, and stored in the database 11 in association with the customer identification information 300 (storage step (step S1)). Note that these pieces of information do not have to be acquired simultaneously, and each piece of information may be stored in the database 11 in association with the customer identification information 300 as it is acquired.

[0063] Next, the customer sales performance prediction unit 12 predicts the customer sales performance 800 for each organization identification information 401 (hospital 20) based on at least the sales information 600 and the organization sales performance information 500 (customer sales performance prediction step (step S2)).

[0064] Next, the similarity determination unit 13 determines the similarity between the doctors 20a who are predicted to have customer sales records 800 in step S2, among the multiple doctors 20a stored in the database 11 in step S1, based on the attribute information 700 (similarity determination step (step S3)).

[0065] Next, the use probability prediction unit 14 predicts the use probability 900 based on the attribute information 700 (step S4). Then, the information processing device 10 ends this process.

[0066] The order of the processing of step S3 and the processing of step S4 may be reversed. Also, in this embodiment, the processing of step S3 is executed, but it is not necessary to execute the processing of step S3, and the processing may proceed to step S4 after the completion of step S2. Also, the processing of steps S2, S3, and S4 may be executed automatically after the information is input in step S1, or may be executed after receiving an external command.

[0067] (Example of use of information processing equipment) Next, a usage example of the information processing device 10 according to this embodiment will be described with reference to Fig. 13. Fig. 13 is an explanatory diagram showing an example of a screening result.

[0068] For example, when the company 30 receives an order for product Z from a predetermined hospital 20, the company 30 inputs organizational sales performance information 500 into the information processing device 10 and stores it in the database 11 in association with the organization identification information 401. At this time, in addition to the organizational sales performance information 500, organizational information 400 of the hospital 20, sales information 600 for the hospital 20, and information on the doctor 20a belonging to the hospital 20 (including attribute information 700) may also be input into the information processing device 10 and stored in the database 11. Alternatively, the organizational information 400, sales information 600, and information on the doctor 20a belonging to the hospital 20 may be stored in the database 11 in advance.

[0069] The user of the information processing device 10 screens out the doctors 20a stored in the database 11 for doctors 20a who have made sales of product Z few times (including zero; the same applies below), outputs the screened doctors 20a to the display device 270, and checks the usage probability 900 of product Z for the output doctors 20a. Alternatively, the user screens out the doctors 20a who have made sales of product Z few times and a high usage probability 900 of product Z (top 10, etc.), and outputs the screened doctors 20a to the display device 270. This makes it possible to extract doctors 20a who potentially have a high usage probability 900 of product Z and few sales visits, so that the extracted doctors 20a can be used as the next sales target, enabling efficient sales. Note that this "sales target" is not limited to targets for door-to-door sales, but may also be potential participants in a sales seminar or study group.

[0070] Furthermore, when the attribute information 700 of an unregistered doctor 20a who is not registered in the database 11 is available, by inputting the attribute information 700 of this unregistered doctor 20a, it is possible to predict the probability 900 of the doctor 20a using product Z and output it to the display device 270. This makes it possible to target the doctor 20a with a high probability 900 of the doctor 20a using product Z as the next sales target, thereby enabling efficient sales.

[0071] Furthermore, the user of the information processing device 10 extracts, from the doctors 20a stored in the database 11, doctors 20a who have a high degree of similarity (a predetermined value or more) with the doctor 20a who is likely to have ordered product Z (doctors 20a who belong to the above-mentioned predetermined hospital 20), and outputs this to the display device 270. This makes it possible to extract doctors 20a who are predicted to have customer sales records 800 and who have a high degree of similarity with the doctor 20a who is likely to have ordered product Z, so that doctors 20a who are likely to receive orders for product Z can be targeted for sales next, enabling efficient sales.

[0072] In addition, doctors 20a who have a high degree of similarity to the doctor 20a who is likely to have ordered product Z and who have a high probability 900 of using product Z may be extracted. This allows doctors 20a who are even more likely to order product Z to be the next target of sales, making sales even more efficient.

[0073] Further screening may be performed using other information stored in the database 11. For example, as shown in FIG. 13, doctors 20a may be extracted based on conditions such as the location (area) of the hospital 20 and the medical department. This allows doctors 20a who are likely to receive orders for product Z and who meet the desired conditions to be extracted, thereby enabling more efficient sales. When outputting the extracted information to the display device 270, it is preferable to convert the "prefecture code," "facility code," "ID number," etc. into "area (prefecture name)," "facility name (name of the hospital 20)," and "doctor name," respectively, as shown in FIG. 13, for easier recognition. Note that "O to T" shown in FIG. 13 are assumed to represent the "names" of the doctors 20a, respectively.

[0074] In another example of use of the information processing device 10, after receiving an order for product Z from the predetermined hospital 20, if it is confirmed that the doctor 20a has used product Z (if use confirmation information is obtained), the information processing device 10 extracts doctors 20a who have a high similarity (a predetermined value or more) to the doctor 20a who used product Z and outputs the extracted information to the display device 270. This makes it possible to extract doctors 20a who are predicted to have customer sales records 800 and who have a high similarity to the doctor 20a who has actually been confirmed to have used product Z, thereby making it possible to target doctors 20a who are more likely to receive an order for product Z as the next sales target. Furthermore, if the use confirmation information of product Z by the doctor 20a is stored in the database 11 as one of the attribute information 700, doctors 20a who have a high similarity to the doctor 20a for whom use confirmation information has been obtained may be extracted from doctors 20a for whom use confirmation information has not been obtained or doctors 20a who have not yet made sales for product Z. This allows for more efficient sales.

[0075] Another example of use of the information processing device 10 is that it can extract doctors 20a who are highly similar to the doctor 20a who is likely to have ordered product Z (or the doctor 20a from whom usage confirmation information has been obtained), so it can also be used to target communities between doctors 20a.

[0076] As described above, according to this embodiment, it is possible to provide the information processing device 10 and the information processing method that are capable of supporting sales to customers who belong to an organization.

[0077] In this embodiment, the description has been given for one product Z, but even if there are a plurality of products, sales support for each product can be provided by storing data for each product.

[0078] Although the present invention has been described above based on the above embodiment, the present invention is not limited to the content of the above embodiment, and can be modified as appropriate without departing from the scope of the present invention. In other words, all other embodiments, examples, operational techniques, etc. made by those skilled in the art based on this embodiment are naturally included in the scope of the present invention. [Explanation of symbols]

[0079] 10: Information processing device 11: Database (storage means) 12: Customer sales performance forecasting unit (customer sales performance forecasting means) 13: Similarity determination unit (similarity determination means) 14: Use probability prediction unit (use probability prediction means) 300: Customer Identification Information 400:Organization information 401: Organization Identification Information 500: Organization sales performance information 600: Business Information 700: Attribute information 800: Customer sales performance 900: Usage probability

Claims

1. a storage means for storing sales information relating to sales to a customer, attribute information relating to attributes of the customer, organization identification information for identifying the organization to which the customer belongs, and organization sales performance information relating to sales performance of a predetermined product to the organization to which the customer belongs, in association with customer identification information for identifying the customer; a customer sales performance forecasting means for forecasting customer sales performance, which is sales performance of the predetermined product to the customer, for each of the organization identification information based on at least the business information and the organization sales performance information; and a usage probability prediction means for predicting the probability that the customer sales performance will be equal to or greater than a predetermined value as the usage probability of the product based on the attribute information.

1. An information processing device comprising:

2. a similarity determination means for determining, based on the attribute information, a similarity between customers who are predicted to have a sales record by the customer sales record prediction means, among the customers stored in the storage means.

2. The information processing apparatus according to claim 1, wherein:

3. The usage probability prediction means predicts the usage probability using a trained model that receives the attribute information and outputs the probability that the customer sales performance is equal to or greater than a predetermined value.

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

4. The sales information includes the number of sales made to the customer.

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

5. An information processing method using an information processing device, The information processing device, a storage step of storing sales information relating to sales to a customer, attribute information relating to attributes of the customer, organization identification information capable of identifying an organization to which the customer belongs, and organization sales performance information relating to sales performance of a predetermined product to the organization to which the customer belongs in a storage means in association with customer identification information capable of identifying the customer; a customer sales performance prediction step of predicting customer sales performance, which is sales performance of the predetermined product to the customer, for each of the organization identification information based on at least the sales information and the organization sales performance information; a usage probability prediction step of predicting the probability that the customer sales performance will be equal to or greater than a predetermined value as a usage probability of the product based on the attribute information.

1. An information processing method comprising:

Images