Information processing device

Abstract

In order to realize effective marketing in the medical field, the present invention generates data for accurately finding a feature of a prospective customer.　The present invention comprises: a factor analysis processing means that calculates a prescribed number of common factors by applying factor analysis processing to user action information; a user characteristics determination means that calculates, regarding the user action information, a factor score based on the prescribed number of common factors for each of user identification information, and determines one common factor having the highest score as user characteristics indicating a feature of a user identified by the user identification information; and a user integrated information generation means that integrates user attribute information and the user characteristics on the basis of the user identification information, and generates user integrated information for performing causal factor analysis by means of multivariate analysis of events which satisfy prescribed viewing or reading states regarding specified content information.

Description

Information processing device

[0001] Digital marketing techniques in the medical field.

[0002] Whether in manufacturing or service, marketing is an extremely important activity in corporate activities in demonstrating and maintaining a company's competitive advantage.

[0003] Meanwhile, in recent years, corporate advertising and sales activities have often been carried out making full use of digital technologies such as the Web, the Internet, and AI (Artificial Intelligence), and corporate marketing activities are also tending to be based on digital technology.

[0004] Against this background, technical proposals related to marketing have been actively made in various industries. For example, Patent Document 1 proposes a technology that collects a wide range of user behavior logs and performs highly accurate access analysis, and Patent Document 2 proposes an information processing device that displays information that allows the effects of learning to be appropriately grasped.

[0005] Furthermore, Patent Document 3 proposes a technology for improving advertising effectiveness and analytical accuracy in web advertising delivery according to user characteristics, and Patent Document 4 proposes an information delivery server that can improve advertising effectiveness through delivered information.

[0006] Japanese Patent Application Laid-Open No. 2022-009936 Japanese Patent Application Laid-Open No. 2021-056364 Japanese Patent No. 5878218 Japanese Patent Application Laid-Open No. 2010-178176

[0007] However, the above-mentioned conventional technology does not take into account the characteristics of customers in the medical field, and therefore has the problem of being difficult to apply to marketing in the medical field.

[0008] In view of the above problems, the present invention aims to provide an information processing device that generates data for accurately identifying the characteristics of potential customers in order to realize effective marketing in the medical field.

[0009] A first aspect of the disclosed information processing device includes a content information storage means for storing, in association with each other, content information related to medical care that can be viewed or browsed on a website and tag information for classifying the content information based on its content; a user behavior information storage means for storing user behavior information that associates user identification information, the tag information corresponding to the content information viewed or browsed by a user identified by the user identification information, and the number of times the content information has been viewed or browsed for each of the tag information; a user attribute information storage means for storing user attribute information that associates the user identification information with attribute information including information regarding the viewing or browsing status of specific content information for each of the users; a normalization means for normalizing the number of times the tag information has been viewed or browsed to represent the frequency of viewing or browsing for the user; a factor analysis processing means for applying factor analysis processing to the normalized user behavior information to calculate a predetermined number of common factors; and a factor analysis processing means for calculating, for each of the user identification information, a factor analysis of the normalized user behavior information based on the predetermined number of common factors. and determining that the common factor with the highest score is the user characteristic representing the characteristics of the user identified by the user identification information; user integrated information generation means for integrating the user attribute information and the user characteristics based on the user identification information and generating user integrated information for performing factor analysis by multivariate analysis of the phenomenon of meeting a predetermined viewing / viewing situation with respect to the specific content information; multivariate analysis processing means for specifying, from the user integrated information, attribute information items including information on the viewing / viewing situation with respect to the specific content information that contribute to the phenomenon of meeting the predetermined viewing / viewing situation from which it can be inferred that the user has a deep interest in the specific content information; and user extraction means for extracting, based on the user integrated information, the user identification information that has the predetermined user characteristic and satisfies the conditions related to the attribute information specified by the multivariate analysis processing means.A second aspect of the disclosed information processing device includes a content information storage means for storing, in association with each other, content information related to medical care that can be viewed or browsed on a website and tag information for classifying the content information based on its content; a user behavior information storage means for storing user behavior information that associates user identification information, the tag information corresponding to the content information viewed or browsed by a user identified by the user identification information, and the number of times the content information has been viewed or browsed for each of the tag information; a user attribute information storage means for storing user attribute information that associates the user identification information with a plurality of pieces of attribute information including information regarding the viewing or browsing status of specific content information for each of the users; a normalization means for normalizing the number of times the tag information has been viewed or browsed to represent the frequency of viewing or browsing for the user; a factor analysis processing means for applying factor analysis processing to the normalized user behavior information to calculate a predetermined number of common factors; The system is characterized by having: a user characteristic determination means for calculating, for each of the user identification information, a factor score based on the predetermined number of common factors for the behavioral information, and determining the common factor with the highest score as the user characteristic representing the characteristics of the user identified by the user identification information; a product usage information storage means for storing product usage information that associates the user identification information, the plurality of attribute information of the user identified by the user identification information, and usage information for a plurality of target usages of a plurality of medical products with the same effect that are used by the user identified by the user identification information; a correspondence storage means for storing correspondence between the plurality of target usages and the plurality of attribute information, and the user characteristics; and a factor extraction means for applying multivariate analysis based on the product usage information and extracting factors related to the user characteristics regarding the usage rate of a predetermined product from among the plurality of target usages and the plurality of attribute information.

[0010] The disclosed information processing device generates data for accurately identifying the characteristics of potential customers in order to realize effective marketing in the medical field.

[0011] FIG. 1 is a diagram illustrating an overview of an information processing device according to the present embodiment. FIG. 2 is a functional block diagram of an information processing device according to the present embodiment. FIG. 3 is a diagram illustrating an example of user behavior information storage means according to the present embodiment. FIG. 4 is a diagram illustrating an example of user attribute information storage means according to the present embodiment. FIG. 5 is a diagram illustrating processing by factor analysis processing means according to the present embodiment. FIG. 6 is a diagram illustrating an example of user integrated information generation means according to the present embodiment. FIG. 7 is a diagram illustrating an example of a hardware configuration of an information processing device according to the present embodiment. FIG. 8 is a flowchart illustrating a flow of a processing example (part 1) by the information processing device according to the present embodiment. FIG. 9 is a flowchart illustrating a flow of a processing example (part 2) by the information processing device according to the present embodiment. FIG. 10 is a functional block diagram of an information processing device according to a second embodiment. FIG. 11 is a diagram illustrating an example of factor extraction means according to the second embodiment. FIG. 12 is a flowchart illustrating a flow of a processing example by the information processing device according to the second embodiment.

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described with reference to the accompanying drawings.

[0013] The operating principle of an information processing device 100 according to this embodiment (hereinafter simply referred to as "the device") will be described using Figures 1 to 6. Figure 1 is a diagram showing the connection relationship between the device 100 and other devices, and Figure 2 is a functional block diagram of the device 100.

[0014] 1, the device 100 is connected to a user terminal 440 operated by a user 380 via a communication network 450. The communication network 450 may be wired or wireless. The user terminal 440 may be a desktop or laptop personal computer, or may be a mobile information terminal such as a smartphone.

[0015] As shown in FIG. 2, the device 100 includes a content information storage means 110, a user behavior information storage means 120, a user attribute information storage means 130, a normalization means 140, a factor analysis processing means 150, a user characteristic determination means 160, a user integrated information generation means 170, an exclusion determination means 180, a multivariate analysis processing means 190, a user extraction means 200, and a second user extraction means 210.

[0016] The content information storage unit 110 stores content information 310 relating to medical care (particularly cardiology) that can be viewed or read on a website, in association with tag information 320 for classifying the content information 310 based on its content. The content information 310 may be a text article or a video article.

[0017] The tag information 320 includes, for example, acute coronary syndrome, arrhythmia, literature, complex PCI (Percutaneous Coronary Intervention), peripheral endovascular therapy, coronary flow reserve, guidelines, heart failure, ischemic heart disease, diagnostic imaging, live performance, drug therapy, academic conferences, structural heart disease, studying abroad, medical management, and other content related to cardiology. The tag information 320 can be changed, added, or deleted.

[0018] The user behavior information storage means 120 stores user behavior information 400 that associates user identification information 390, tag information 320 corresponding to content information 310 viewed or browsed by a user 380 identified by the user identification information 390, and the number of views or browsing times 330 for each tag information 320. The number of views or browsing times 330 may be the number of accesses by a user terminal 440, or may be the length of time the content was viewed or browsed.

[0019] 3 is a diagram showing an example of the user behavior information storage means 120. As shown in Fig. 3, the user behavior information storage means 120 stores user behavior information 390 that associates, for example, user identification information 390:11111, (tag information 320, number of views / views 330) = (acute coronary syndrome, 5 times), (arrhythmia, 10 times), ...

[0020] In addition, the user behavior information storage means 120 stores, for example, user behavior information 400 that associates (tag information 320, number of views / views 330) = (acute coronary syndrome, 0 times), (arrhythmia, 0 times), ... for user identification information 390:11115.

[0021] The user attribute information storage means 130 stores user attribute information 410 that associates user identification information 390 with attribute information 350 that includes information 340 about the viewing / browsing status of each user 380 regarding specific content information 310 .

[0022] Attribute information 350 includes, for example, information regarding the location of work, age, gender, membership type, email newsletter registration status, whether the person is a specialist in an academic society, whether the person is certified by an academic society, participation in events, viewing and viewing status of articles (either video articles or written articles), etc.

[0023] The information 340 relating to the viewing / viewing status of the specific content information 310 is information relating to whether or not the specific content information 310 has been viewed / viewed, the time and number of times the specific content information 310 has been viewed / viewed, and the like.

[0024] Fig. 4 is a diagram showing an example of the user attribute information storage means 130. As shown in Fig. 4, the user attribute information storage means 130 stores user attribute information 410 that associates, for example, user identification information 390:11111, workplace location: Tokyo (metropolitan area), age: 30 (years old), gender: male, membership type: paid member, ..., whether specific content information 310 has been viewed / bought: yes, time spent viewing / bought specific content information 310: 5 minutes 0 seconds, ...

[0025] Furthermore, the user attribute information storage means 130 stores, for example, for user identification information 390:11112, user attribute information 410 that associates workplace location: Kanagawa (prefecture), age: 35 (years old), gender: female, membership type: paid member, ..., whether specific content information 310 has been viewed / viewed: no, time spent viewing / viewing specific content information 310: 0 seconds, ...

[0026] The normalization means 140 normalizes the number of views 330 for each piece of tag information 320 stored in the user behavior information storage means 120 so as to represent the frequency of views by the user 380. The normalization method used by the normalization means 140 is, for example, to divide the number of views 330 by the number of all pieces of content information 310.

[0027] For example, for the user identification information 390:11111 in FIG. 3, if the number of all content information 310 is 500, the normalization means 140 performs normalization such as acute coronary syndrome: 5÷500=0.01, arrhythmia: 10÷500=0.02, literature: 0÷500=0, complex PCI: 20÷500=0.04, etc.

[0028] The factor analysis processing means 150 applies factor analysis processing to the normalized user behavior information 400 to calculate a predetermined number of common factors 360. The number of common factors 360 calculated by the factor analysis processing is not particularly limited.

[0029] 5 is a diagram for explaining the processing by the factor analysis processing means 150, and is a diagram schematically showing the factor loadings obtained by the factor analysis processing. In FIG. 5, common factors 360 are plotted horizontally, and tag information 320 is plotted vertically. As shown in FIG. 5, the factor analysis processing means 150 calculates, for example, five common factors 360 and defines the content indicated (represented) by each common factor 360 based on the tag information 320 that shows a relatively large value in the factor loading for each common factor 360 and common knowledge in the medical industry.

[0030] The user characteristic determination means 160 calculates a factor score 370 for each piece of user identification information 390 in the normalized user behavior information 400 based on a predetermined number of common factors 360 calculated by the factor analysis processing means 150. The user characteristic determination means 160 then determines the common factor 360 with the highest score as the user characteristic 420 that represents the characteristics of the user 380 identified by the user identification information 400.

[0031] As shown in Figure 5, the user characteristics 420 include, 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 with a comprehensive interest in the circulatory system (more interested in drug therapy than catheterization): F4," and "cardiologist interested in peripheral intravascular treatment: F5."

[0032] The user integrated information generating means 170 integrates the normalized user behavior information 400, user attribute information 410, and user characteristics 420 based on the user identification information 390. As a result, the user integrated information generating means 170 generates user integrated information 430 for performing a factor analysis by multivariate analysis of the phenomenon that a predetermined viewing / browsing situation is satisfied for specific content information 310.

[0033] 6 is a diagram showing an example of the user integrated information generation means 170. As shown in FIG. 6, the user integrated information generation means 170 integrates the user attribute information 410 in FIG. 4 with the user characteristics 420 determined by the user characteristic determination means 160 based on the user identification information 390. For example, for user identification information 390:11111, the user integrated information generation means 170 generates user integrated information 430 that associates workplace location: Tokyo (metropolitan area), age: 30 (years old), gender: male, membership type: paid member, ..., and user characteristic 420: F1.

[0034] If the attribute information 350 includes information regarding the time spent watching or viewing specific content information 310, the exclusion determination means 180 determines whether or not to exclude each user attribute information 410 from being processed by the device 100 based on the length of the watching or viewing time for the specific content information 310.

[0035] For example, if the viewing / viewing time for specific content information 310 is shorter or longer than a predetermined time, the exclusion determination means 180 determines that the user attribute information 410 should be excluded from processing by the device 100. If the viewing / viewing time for the content information 310 is extremely short or long, it is determined that the user 380 is not interested in viewing or viewing the content information 310, and determines that the content information 310 should be excluded from processing by the device 100. The processing by the exclusion determination means 180 improves the accuracy and reliability of the analysis results by the device 100.

[0036] 4, for example, the exclusion determination means 180 determines that user attribute information 410 for which user identification information 390 is "11111" or "11113" has a viewing / viewing time of "5 minutes" and "5 minutes 30 seconds," respectively, and therefore should be subject to processing by the device 100. On the other hand, for example, the exclusion determination means 180 determines that user attribute information 410 for which user identification information 390 is "11115" has an extremely short viewing / viewing time of "5 seconds," and therefore should be excluded from processing by the device 100. The threshold value used for determination by the exclusion determination means 180 can be set as appropriate.

[0037] The multivariate analysis processing means 190 uses multivariate analysis processing to identify, for the user integrated information 430, items of the attribute information 350 that contribute to the event of satisfying a predetermined viewing / viewing situation with respect to specific content information 310. The event of satisfying a predetermined viewing / viewing situation is assumed to be, but is not limited to, having viewed / viewed the specific content information 310, having viewed / viewed the specific content information 310 to the end, or having viewed / viewed the specific content information 310 for longer than a predetermined time.

[0038] As shown in Figure 6, the multivariate analysis processing means 190, for example, performs multivariate analysis processing on the user integrated information 430, and identifies items of attribute information 350 that significantly contribute to the viewing or browsing of specific content information 310, such as membership type: paid membership, email newsletter registration status: yes, etc.

[0039] The user extraction means 200 extracts user identification information 390 that has predetermined user characteristics 420 and satisfies the conditions related to the attribute information 350 specified by the multivariate analysis processing means 190, based on the user integrated information 430. This processing makes it possible to effectively narrow down targets to which event participation invitations or advertisements are sent.

[0040] 6 , for example, when the multivariate analysis processing means 190 identifies "membership type: paid" and the predetermined user characteristic 420 is "F1," the user extraction means 200 extracts "11111" as the user identification information 390. On the other hand, when the multivariate analysis processing means 190 identifies "membership type: paid" and the predetermined user characteristic 420 is "F2," the user extraction means 200 extracts "11112" as the user identification information 390.

[0041] The second user extraction means 210 extracts user identification information 390 that has predetermined user characteristics 420 and satisfies predetermined viewing / viewing conditions for the specific content information 310, based on the user integrated information 430. Satisfying the predetermined viewing / viewing conditions may include, but is not limited to, having viewed / viewed the specific content information 310, having viewed / viewed the specific content information 310 to the end, or having viewed / viewed the specific content information 310 for a longer period of time than a predetermined period of time. This process makes it possible to effectively narrow down targets for sending event participation invitations or placing advertisements.

[0042] In FIG. 6 , for example, if the predetermined viewing / viewing situation is “viewed / viewed” and the predetermined user characteristic 420 is “F5”, the second user extraction means 210 extracts “11115” as the user identification information 390.

[0043] 6 , it is assumed that the attribute information 350 includes information regarding the time spent viewing or watching specific content information 310. In this case, the second user extraction means 210 may extract user identification information 390 that identifies users 380 who have predetermined user characteristics 420 and who have viewed or watched the specific content information 310 for a longer period of time, based on the user integrated information 430. Users 380 who have viewed or watched the specific content information 310 for a longer period of time are presumed to have a deep interest in the specific content information 310, and such users 380 can be targeted for event participation invitations or advertisements, thereby enabling effective marketing activities.

[0044] As shown in Figure 6, for example, if the specified viewing / viewing situation is "viewing / viewing time is 5 minutes or more" and the specified user characteristic 420 is "F1", the second user extraction means 210 extracts "11111" as the user identification information 390.

[0045] Based on the above-described operational principle, the device 100 generates data 430 for accurately identifying the characteristics of potential customers in order to realize effective marketing in the medical field.

[0046] Furthermore, based on the above-described operating principle, the device 100 can accurately extract potential customers with a high response rate in order to realize effective marketing in the medical field. (Hardware Configuration of the Information Processing Device According to the Present Embodiment)

[0047] An example of the hardware configuration of the device 100 will be described using Fig. 7. Fig. 7 is a diagram showing an example of the hardware configuration of the device 100. As shown in Fig. 7, the device 100 includes a CPU (Central Processing Unit) 510, a ROM (Read-Only Memory) 520, a RAM (Random Access Memory) 530, an auxiliary storage device 540, a communication I / F 550, an input device 560, a display device 570, and a storage medium I / F 580.

[0048] The CPU 510 is a device that executes a program stored in the ROM 520, performs arithmetic processing on data loaded into the RAM 530 in accordance with program instructions, and controls the entire device 100. The ROM 520 stores the programs and data to be executed by the CPU 510. When the CPU 510 executes a program stored in the ROM 520, the programs and data to be executed are loaded into the RAM 530, and the RAM 530 temporarily holds the arithmetic data during the calculation.

[0049] The auxiliary storage device 540 is a device that stores the basic software, such as an operating system (OS), the application programs according to the present embodiment, and other related data. The auxiliary storage device 540 is, for example, a hard disk drive (HDD) or a flash memory.

[0050] The communication I / F 550 is an interface for connecting to a communication network 430 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.

[0051] The input device 560 is a device such as a keyboard for inputting data into the device 100. The display device (output device) 570 is a device formed of an LCD (Liquid Crystal Display) or the like, and functions as a user interface when the user uses the functions of the device 100 or when making various settings. The storage medium I / F 580 is an interface for sending and receiving data to and from a storage medium 590 such as a CD-ROM, DVD-ROM, or USB memory.

[0052] Each of the means included in the device 100 may be realized by the CPU 510 executing a program corresponding to each of the means stored in the ROM 520 or the auxiliary storage device 540. Furthermore, each of the means included in the device 100 may be realized by hardware that performs the processing associated with the respective means. Furthermore, the device 100 may be configured to execute the program by loading the program according to the present invention from an external server device via the communication I / F 550 or by loading the program according to the present invention from the storage medium 590 via the storage medium I / F 580. (Processing Example by the Information Processing Device According to the Present Embodiment) (1) Processing Example (Part 1) by the Device 100 A processing example (Part 1) by the device 100 will be described using FIG. 8 . FIG. 8 is a flowchart showing the flow of the processing example (Part 1) by the device 100.

[0053] In S10, the normalization means 140 normalizes the number of views 330 for each piece of tag information 320 stored in the user behavior information storage means 120 so as to represent the frequency of views by the user 380. The normalization method used by the normalization means 140 is, for example, to divide the number of views 330 by the number of all pieces of content information 310.

[0054] For example, for the user identification information 390:11111 in FIG. 3, if the number of all content information 310 is 500, the normalization means 140 performs normalization such as acute coronary syndrome: 5÷500=0.01, arrhythmia: 10÷500=0.02, literature: 0÷500=0, complex PCI: 20÷500=0.04, etc.

[0055] Furthermore, in S10, the factor analysis processing means 150 applies factor analysis processing to the normalized user behavior information 400 to calculate a predetermined number of common factors 360. The number of common factors 360 calculated by the factor analysis processing is not particularly limited.

[0056] As shown in FIG. 5, the factor analysis processing means 150 calculates, for example, five common factors 360, and defines the content indicated (represented) by each common factor 360 based on tag information 320 that indicates a relatively large value in the factor loading for each common factor 360 and common knowledge in the medical industry.

[0057] In S20, the user characteristic determination means 160 calculates a factor score 370 for each piece of user identification information 390 in the normalized user behavior information 400 based on a predetermined number of common factors 360 calculated by the factor analysis processing means 150. Then, the user characteristic determination means 160 determines the common factor 360 with the highest score as the user characteristic 420 that represents the characteristic of the user 380 identified by the user identification information 400.

[0058] As shown in Figure 5, the user characteristics 420 include, 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 with a comprehensive interest in the circulatory system (more interested in drug therapy than catheterization): F4," and "cardiologist interested in peripheral intravascular treatment: F5."

[0059] In S30, the user integrated information generating means 170 integrates the normalized user behavior information 400, user attribute information 410, and user characteristics 420 based on the user identification information 390. As a result, the user integrated information generating means 170 generates user integrated information 430 for performing factor analysis by multivariate analysis of the phenomenon that a predetermined viewing / browsing situation is satisfied for specific content information 310.

[0060] 6, the user integrated information generating means 170 integrates the user attribute information 410 in FIG. 4 with the user characteristics 420 determined by the user characteristic determining means 160 based on the user identification information 390. For example, for user identification information 390:11111, the user integrated information generating means 170 generates user integrated information 430 that associates workplace location: Tokyo (metropolitan area), age: 30 (years old), gender: male, membership type: paid member, ..., and user characteristic 420: F1.

[0061] Furthermore, in S30, if the attribute information 350 includes information regarding the time spent watching or viewing specific content information 310, the exclusion determination means 180 determines whether or not to exclude each user attribute information 410 from being processed by the device 100 based on the length of the watching or viewing time for the specific content information 310.

[0062] For example, if the viewing / viewing time for specific content information 310 is shorter or longer than a predetermined time, the exclusion determination means 180 determines that the user attribute information 410 should be excluded from processing by the device 100. If the viewing / viewing time for the content information 310 is extremely short or long, it is determined that the user 380 is not interested in viewing or viewing the content information 310, and determines that the content information 310 should be excluded from processing by the device 100. The processing by the exclusion determination means 180 improves the accuracy and reliability of the analysis results by the device 100.

[0063] 4, for example, the exclusion determination means 180 determines that user attribute information 410 for which user identification information 390 is "11111" or "11113" has a viewing / viewing time of "5 minutes" and "5 minutes 30 seconds," respectively, and therefore should be subject to processing by the device 100. On the other hand, for example, the exclusion determination means 180 determines that user attribute information 410 for which user identification information 390 is "11115" has an extremely short viewing / viewing time of "5 seconds," and therefore should be excluded from processing by the device 100. The threshold value used for determination by the exclusion determination means 180 can be set as appropriate.

[0064] In S40, the multivariate analysis processing means 190 identifies, by multivariate analysis processing, the items of the attribute information 350 that contribute to the event that a predetermined viewing / browsing situation is satisfied for the specific content information 310, for the user integrated information 430.

[0065] As shown in Figure 6, the multivariate analysis processing means 190, for example, performs multivariate analysis processing on the user integrated information 430, and identifies items of attribute information 350 that significantly contribute to the viewing or browsing of specific content information 310, such as membership type: paid membership, email newsletter registration status: yes, etc.

[0066] In S50, the user extraction means 200 extracts user identification information 390 that has predetermined user characteristics 420 and satisfies the conditions related to the attribute information 350 specified by the multivariate analysis processing means 190, based on the user integrated information 430. This processing makes it possible to effectively narrow down targets to which event participation invitations or advertisements are sent.

[0067] 6 , for example, when the multivariate analysis processing means 190 identifies "membership type: paid" and the predetermined user characteristic 420 is "F1," the user extraction means 200 extracts "11111" as the user identification information 390. On the other hand, when the multivariate analysis processing means 190 identifies "membership type: paid" and the predetermined user characteristic 420 is "F2," the user extraction means 200 extracts "11112" as the user identification information 390.

[0068] By performing the above-described processing, the device 100 generates data 430 for accurately identifying the characteristics of potential customers in order to realize effective marketing in the medical field.

[0069] Furthermore, by performing the above-described processing, the device 100 can accurately extract customer candidates with a high response rate in order to realize effective marketing in the medical field. (2) Processing Example (Part 2) by the Device 100 A processing example (Part 2) by the device 100 will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the flow of the processing example (Part 2) by the device 100.

[0070] Note that steps S110 to S130 are the same as steps S10 to S30, and therefore a description thereof will be omitted. Below, a description will be given of the processing after steps S110 to S130 (S10 to S30) have been performed.

[0071] In S140, the second user extraction means 210 extracts user identification information 390 that has predetermined user characteristics 420 and satisfies predetermined viewing / viewing conditions for specific content information 310, based on the user integrated information 430. This process makes it possible to effectively narrow down targets for sending event participation invitations or placing advertisements.

[0072] In FIG. 6 , for example, if the predetermined viewing / viewing situation is “viewed / viewed” and the predetermined user characteristic 420 is “F5”, the second user extraction means 210 extracts “11115” as the user identification information 390.

[0073] 6 , it is assumed that the attribute information 350 includes information regarding the time spent viewing or watching specific content information 310. In this case, the second user extraction means 210 may extract user identification information 390 that identifies users 380 who have predetermined user characteristics 420 and who have viewed or watched the specific content information 310 for a longer period of time, based on the user integrated information 430. Users 380 who have viewed or watched the specific content information 310 for a longer period of time are presumed to have a deep interest in the specific content information 310, and such users 380 can be targeted for event participation invitations or advertisements, thereby enabling effective marketing activities.

[0074] As shown in Figure 6, for example, if the specified viewing / viewing situation is "viewing / viewing time is 5 minutes or more" and the specified user characteristic 420 is "F1", the second user extraction means 210 extracts "11111" as the user identification information 390.

[0075] By performing the above-described processing, the device 100 generates data 430 for accurately identifying the characteristics of potential customers in order to realize effective marketing in the medical field.

[0076] Furthermore, by performing the above-described processing, the device 100 can accurately extract potential customers with a high response rate in order to realize effective marketing in the medical field.

[0077] Next, an information processing device according to a second embodiment of the present invention will be described. The information processing device 600 according to the second embodiment of the present invention (hereinafter simply referred to as "the device") differs from the above-described embodiment of the present invention (hereinafter sometimes referred to as "the first embodiment") in the processing performed after the user characteristics are determined by the user characteristics determination means 160. Note that components similar to those in the first embodiment of the present invention will be assigned the same reference numerals and descriptions thereof will be omitted.

[0078] (Operational Principle of Information Processing Device According to Second Embodiment) The operational principle of the device 600 will be described with reference to Fig. 10. Fig. 10 is a functional block diagram of the device 600.

[0079] As in the first embodiment, the device 600 is connected to a user terminal 440 operated by a user 380 via a communication network 450. The device 600 also includes a CPU 510, a ROM 520, a RAM 530, an auxiliary storage device 540, a communication I / F 550, an input device 560, a display device 570, and a storage medium I / F 580.

[0080] As shown in Figure 10, this device 600 has a content information storage means 110, a user behavior information storage means 120, a user attribute information storage means 130, a normalization means 140, a factor analysis processing means 150, a user characteristic determination means 160, a product usage information storage means 610, a correspondence relationship storage means 620, and a factor extraction means 630.

[0081] The product usage information storage means 610 stores product usage information that associates user identification information 390, multiple attribute information 350 of the user identified by the user identification information 390, and usage information for multiple target uses of multiple medical products with the same effect that are used by the user identified by the user identification information 390. Medical products include pharmaceuticals and medical devices. In the following explanation, "pharmaceuticals" will be used as an example of a medical product. In the following explanation, "medical products" may also be simply referred to as "products."

[0082] The multiple user attribute information 350 is information stored in the user attribute information storage means 130, and includes information on various user attributes such as the above-mentioned workplace location, age, sex, membership type, email newsletter registration status, whether the person is a specialist in an academic society, whether the person is certified by an academic society, event participation status, article viewing / status, as well as the number of specified surgeries etc. performed, the number of times information has been provided by medical information providers (MRs), etc.

[0083] "Multiple medical products with the same effect" refers to, for example, "drugs" that are manufactured by different pharmaceutical companies or have different product names, but have the same efficacy, effectiveness, and pharmacology. Also, in the case of "medical devices," it refers to medical devices that have the same function, but are manufactured by different pharmaceutical companies or medical device manufacturers and distributors, or have different product names. In other words, "the same effect" does not mean exactly the same effect. For example, multiple direct anticoagulants (DOACs) distributed by multiple pharmaceutical companies are multiple medical products (drugs) that have the "same effect" of suppressing the activity of various coagulation factors that cause blood to clot, preventing blood clots caused by blood stagnation in blood vessels with slow blood flow. The following explanation focuses on the case where the drug is a "direct anticoagulant," but the drug is not limited to "direct anticoagulants" and can be any drug that falls under the category of "multiple drugs with the same effect."

[0084] "Multiple target users" refers to information about target users (patients) who use multiple products (drugs) separately. For example, in the case of direct oral anticoagulants (DOACs), the multiple target users include "chronic kidney disease (CKD) patients," "liver disease patients," "diabetic patients," "patients after lower limb revascularization," "patients after TAVI (transcatheter aortic valve replacement)," "deep vein thrombosis patients," "pulmonary embolism patients," "patients with a high tendency to bleed," "elderly people," "young people," and "patients with dementia."

[0085] In other words, "information on different uses" is information on how users use multiple products with the same effect for various different uses. For example, User X may use drugs A, B, and C with the same effect, and the user may use drug A for "patients with high bleeding tendency," drug B for "patients after lower limb revascularization," and drug C for "patients with dementia." "Information on different uses" may be obtained, for example, by conducting a survey of users of a website that allows viewing or browsing of content information 310. Specifically, the survey lists multiple different uses of direct anticoagulants in advance, and website users are asked to respond to the survey by indicating which direct anticoagulant they use for each different use, among direct anticoagulants from multiple pharmaceutical companies. The different uses can be changed, added, or deleted.

[0086] In this way, the "product usage information" is information that associates (correlates) user identification information 390, multiple pieces of user attribute information 350, and information on how to use multiple products for multiple target uses.

[0087] The correspondence storage means 620 stores correspondences between the multiple target users and the multiple pieces of attribute information 350 and the user characteristics 420. For example, a predetermined number of common factors 360 are specified in advance when the factor analysis processing means 150 applies factor analysis processing, and these common factors 360 correspond to the user characteristics 420. Therefore, the correspondence storage means 620 stores in advance correspondences between these common factors 360 and both the multiple target users and the multiple pieces of attribute information 350, thereby storing correspondences between the multiple target users and the multiple pieces of attribute information 350 and the user characteristics 420. For example, the user characteristic 420 of "cardiologist interested in peripheral endovascular treatment: F5" is associated with "patients after lower limb revascularization" among the multiple target users. Furthermore, if "PCI (percutaneous transluminal coronary intervention (prescribed surgery))" is included in the plurality of pieces of attribute information 350, the user characteristic 420 of "cardiologist interested in cardiac catheter treatment (specialty area): F1" is associated with the attribute information 350. Note that a plurality of user characteristics 420 may be associated with one target of use or one piece of attribute information 350.

[0088] The factor extraction means 630 applies multivariate analysis based on the product differentiation information to extract factors (hereinafter referred to as "usage rate factors") related to the user characteristics 420 for the usage rate of a specific product from among the multiple differentiation targets and multiple attribute information 350. In this embodiment, an example will be described in which the factor extraction means 630 applies decision tree analysis. Note that the multivariate analysis is not limited to decision tree analysis, and may be, for example, Cox regression proportional hazard analysis, multiple regression analysis, or the like.

[0089] In this embodiment, when extracting usage rate factors related to user characteristics 420 from multiple usage targets and multiple attribute information 350, the factor extraction means 630 first divides all users into top users whose usage rate of the target product (e.g., "Drug A") is equal to or greater than a predetermined value (e.g., 10% or greater) and bottom users whose usage rate is less than the predetermined value (e.g., less than 10%). Then, based on the product usage information, the factor extraction means 630 performs multivariate analysis on the multiple usage targets and multiple attribute information 350 to extract usage rate factors related to user characteristics 420 for the usage rate of Drug A. Usage rate factors related to user characteristics 420 indicate which user characteristics 420 are associated with a high (or low) usage rate of Drug A. Note that the predetermined value is not limited to 10%.

[0090] FIG. 11 is a diagram showing an example of the factor extraction means according to the second embodiment.

[0091] As shown in FIG. 11 , the factor extraction means 630 applies (executes) multivariate analysis (decision tree analysis in this embodiment) to multiple target users and multiple attribute information 350 based on the product usage information, extracting usage rate factors related to user characteristics 420 for the usage rate of Drug A. In FIG. 11 , the top users of "node 2," which has a high number of PCI (percutaneous coronary intervention) procedures performed annually for Drug A, are 99 people, and since there are many users with high usage rates, "number of PCI procedures performed annually" is extracted as a factor for the high usage rate of Drug A. The user characteristic 420 corresponding to "PCI" is associated with "cardiologists (specialty area): F1" in the correspondence storage means 620. As a result, the user characteristic 420 (F1) is extracted as a factor for the high usage rate of Drug A. In this embodiment, decision tree analysis is applied to one item ("number of PCIs performed per year") (see FIG. 11), but decision tree analysis may also be applied to other items (target of use and attribute information 350) for each of "node 1" and "node 2." Also, in FIG. 11, "node 0" is branched into two nodes ("node 1" and "node 2") based on the "number of PCIs performed per year," but this is not limited to this and may be branched into three or more nodes. Also, in this embodiment, factors for a high usage rate of drug A are extracted, but factors for a low usage rate of drug A may also be extracted.

[0092] (Processing example by information processing device according to this embodiment) A processing example by the device 600 will be described with reference to Fig. 12. Fig. 12 is a flowchart showing the flow of a processing example by the information processing device according to the second embodiment. Note that S210 and S220 are the same as the processing in S10 and S20 in the first embodiment, and therefore a description thereof will be omitted here. Below, a description will be given of processing after the processing in S210 and S220 (S10 and S20) has been performed.

[0093] In S230, the factor extraction means 630 applies at least decision tree analysis based on the product usage information to extract usage rate factors related to the user characteristics 420 for the usage rate of a specific product (drug) from among the multiple usage targets and multiple attribute information 350. For example, as shown in FIG. 11 , the factor extraction means 630 extracts the user characteristics 420 (F1) as a factor for the high usage rate of Drug A. This process makes it possible to effectively narrow down the user demographic (user characteristics 420) to whom event participation invitations or advertisements are to be sent.

[0094] In the device 600 configured as described above, the user characteristic determination means 160 determines the user characteristics 420 based on the normalized user behavior information 400, so it is possible to determine whether the articles on the website are reaching (or are of interest to) the specific user group (user characteristics 420) that is the target of marketing.

[0095] For example, a pharmaceutical company may target a specific user demographic (user characteristics 420) and conduct sales activities aimed at that user demographic. Specifically, the pharmaceutical company may provide advertising articles (articles that are likely to be of interest to the specific user demographic) targeted at the specific user demographic as content information 310 on a website. The device 600 normalizes user behavior information 400 based on the number of views 330 for each tag information 320 of the website, and determines user characteristics 420 based on the normalized user behavior information 400. Then, by checking the access logs of the articles provided by the pharmaceutical company and confirming the user characteristics 420 of the users accessing the articles, it is possible to determine whether the articles on the website are reaching (or are of interest to) the specific user demographic (user characteristics 420) targeted by the pharmaceutical company. This allows the content of the articles to be appropriately changed based on the results of the determination of the user characteristics 420, thereby improving the effectiveness of advertising and promotion aimed at the desired user demographic (user characteristics 420).

[0096] Furthermore, the factor extraction means 630 extracts usage rate factors related to the user characteristics 420 for the usage rate of a specific product from among the multiple target users and the multiple attribute information 350 based on the product usage information. This makes it possible to extract the user demographic (user characteristics 420) that will be a factor in increasing the usage rate of the product, allowing pharmaceutical companies to determine whether the user demographic they are targeting for marketing is truly a user demographic that will be a factor in increasing the usage rate of the product. This makes it possible to clarify the marketing target and improve marketing efficiency.

[0097] In this way, according to this embodiment, it is possible to clearly narrow down the user group (user characteristics 420) to be targeted for marketing, and to determine whether the advertising and promotion is accurately reaching the desired user group (user characteristics 420).

[0098] By performing the above-described processing, the device 600 can generate data for accurately identifying the characteristics of potential customers in order to realize effective marketing in the medical field.

[0099] Furthermore, by performing the above-described processing, the device 600 can accurately extract potential customers with a high response rate in order to realize effective marketing in the medical field.

[0100] In addition to the first and second forms, other analyses may be performed. For example, in the second form, the product usage information to be analyzed includes information on how to use multiple products with the same effect for "multiple target users." These "multiple target users" are information about the target users (patients) for whom multiple products are used. However, in other analyses, other reasons for using multiple products (reasons other than for patients) may also be included in the product usage information. Examples of "other reasons" include "because it is a drug adopted by the clinic where I work," "because I received information at an academic conference," and "because my superiors or colleagues gave me opinions." In this way, the "other reasons" may be included in the product usage information, and then the "other reasons" that contribute to improving product usage rates may be extracted using logistic regression analysis or the like.

[0101] In this embodiment, the device 600 does not include the user integrated information generating means 170, the exclusion determination means 180, the multivariate analysis processing means 190, the user extraction means 200, and the second user extraction means 210 of the first embodiment, but may include these. That is, the device 600 may perform the processing executed by the factor extraction means 630 in addition to all the processing of the first embodiment. Furthermore, in addition to all the processing of the first embodiment and the processing executed by the factor extraction means 630 of the second embodiment, the device 600 may perform the other analysis processing described above (analysis including the above "other reasons").

[0102] Furthermore, in the first and second forms described above, an example of cardiology, a medical specialty, is explained, but the medical specialty is not limited to cardiology, and the present invention can be applied to various medical specialty.

[0103] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims.

[0104] 100, 600 Information processing device 110 Content information storage means 120 User behavior information storage means 130 User attribute information storage means 140 Normalization means 150 Factor analysis processing means 160 User characteristic determination means 170 User integrated information generation means 180 Exclusion determination means 190 Multivariate analysis processing means 200 User extraction means 210 Second user extraction means 310 Content information 320 Tag information 330 Number of times content information has been viewed / viewed 340 Information on viewing / viewing status 350 Attribute information 360 Common factor by factor analysis processing 370 Factor score based on common factor 380 User 390 User identification information 400 User behavior information 410 User attribute information 420 User characteristics 430 User integrated information 440 User terminal 450 Communication network 510 CPU 520 ROM 530 RAM 540 Auxiliary storage device 550 Communication interface 560 Input device 570 Output device 580 Storage medium interface 590 Storage medium 610 Product usage information storage means 620 Correspondence relationship storage means 630 Factor extraction means

Claims

1. a content information storage means for storing medical content information that can be viewed or read on a website and tag information for classifying the content information based on its content in association with each other; a user behavior information storage means for storing user behavior information that associates user identification information, the tag information corresponding to the content information viewed / browsed by a user identified by the user identification information, and the number of views / browsings for each tag information; a user attribute information storage means for storing user attribute information that associates the user identification information with a plurality of pieces of attribute information including information regarding a viewing / browsing situation of each of the users with respect to the specific content information; A normalization means for normalizing the number of times of viewing / browsing for each tag information item so as to represent the frequency of viewing / browsing by the user; A factor analysis processing means for applying a factor analysis process to the normalized user behavior information to calculate a predetermined number of common factors; a user characteristic determination means for calculating a factor score based on the predetermined number of common factors for each of the user identification information regarding the user behavior information after normalization, and determining one of the common factors with the highest score as a user characteristic representing a feature of the user identified by the user identification information; a product usage information storage means for storing product usage information that associates the user identification information, the multiple attribute information of the user identified by the user identification information, and usage information for multiple medical products having the same effect and used by the user identified by the user identification information, for multiple usage targets; A correspondence relationship storage means for storing a correspondence relationship between the plurality of objects of distinguishing use and the plurality of pieces of attribute information and the user characteristics; and a factor extraction means for applying multivariate analysis based on the product usage information and extracting factors related to the user characteristics regarding the usage rate of a specified product from among the multiple target usages and the multiple attribute information.

2. a content information storage means for storing, in association with each other, content information related to medical care that can be viewed or read on a website, and tag information for classifying the content information based on its contents; a user behavior information storage means for storing user behavior information that associates user identification information, the tag information corresponding to the content information viewed or read by a user identified by the user identification information, and the number of times each of the tag information has been viewed or read; a user attribute information storage means for storing user attribute information that associates the user identification information with a plurality of attribute information including information regarding the viewing or reading status of a specific piece of content information of each of the users; a product differentiation information storage means for storing product differentiation information that associates the user identification information, the plurality of attribute information of the user identified by the user identification information, and differentiation information for a plurality of differentiation targets of a plurality of medical care products having the same effect that are used by the user identified by the user identification information; and a correspondence storage means for storing a correspondence relationship between the plurality of differentiation targets and the plurality of attribute information, and a user characteristic; A normalization step of normalizing the number of times of viewing / browsing for each tag information item so as to represent the frequency of viewing / browsing by the user; A factor analysis processing means applies a factor analysis process to the normalized user behavior information to calculate a predetermined number of common factors; A user characteristic determination means calculates a factor score based on the predetermined number of common factors for each of the user identification information regarding the normalized user behavior information, and determines one of the common factors with the highest score as the user characteristic identified by the user identification information; a step of a factor extraction means applying multivariate analysis based on the product differentiation information to extract factors related to the user characteristics for the usage rate of a specified product from among the multiple differentiation targets and the multiple attribute information.

3. An information processing program for causing a computer to execute the method according to claim 2.