Recommendation system

The recommendation system addresses format inconsistencies by determining and generating content based on predicted behavior change effects, ensuring effective user engagement by prioritizing formats and content, thus enhancing the effectiveness of recommendation systems.

WO2024241655A1PCT designated stage expired Publication Date: 2024-11-28NTT DOCOMO INC
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2024/008316
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-19
Filing Date
2024-03-05
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

Existing recommendation systems often fail to provide content suitable for users due to format inconsistencies, even when a suitable nudge is selected, leading to ineffective behavior change.

Method used

A recommendation system that determines a predetermined number of effective formats and generates content based on predicted behavior change effects, ensuring the highest effective output for users by utilizing a first determining unit to estimate suitable formats and a recommendation generation unit to create content for each format, with a second determining unit selecting the most suitable content for output.

Benefits of technology

This approach enables efficient output of recommendation content that is highly effective in changing user behavior by prioritizing formats and content based on historical data and cognitive biases, thereby improving user engagement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2024008316_28112024_PF_FP_ABST
    Figure JP2024008316_28112024_PF_FP_ABST
Patent Text Reader

Abstract

This recommendation system comprises: a first determination unit that determines a predetermined number of recommendation formats among a plurality of recommendation formats in descending order of predicted behavior-changing effect on the user; a recommendation generation unit that generates a predetermined number of pieces of recommendation content respectively corresponding to the predetermined recommendation formats determined by the first determination unit; and a second determination unit that outputs the piece of recommendation content predicted to have the greatest behavior-changing effect on the user among the predetermined number of pieces of recommendation content generated by the recommendation generation unit.
Need to check novelty before this filing date? Find Prior Art

Description

Recommendation System

[0001] The present disclosure relates to a recommendation system.

[0002] Patent Literature 1 discloses a recommendation system that corrects biases in user behavior by prompting users to voluntarily select latent preferences and taking action. In this recommendation system, the content of recommendations is determined according to the selected nudge.

[0003] Japanese Patent Application Laid-Open No. 2022-129411

[0004] Recommendation systems are known that output recommendations to service systems. When a service system has multiple output formats, the recommendation content varies depending on the output format, even if the recommendation is based on the same nudge. For example, even if a nudge suitable for a user is selected, the output recommendation content may not be suitable for the user.

[0005] The present disclosure has been made in consideration of the above, and aims to provide a recommendation system that can efficiently output recommended content that is suitable for a user.

[0006] The recommendation system according to the present disclosure includes a first determination unit that determines, as a data output format, a predetermined number of recommendation formats from among a plurality of recommendation formats in order of predicted effectiveness in changing a user's behavior; a recommendation generation unit that generates a predetermined number of recommendation contents corresponding to the predetermined number of recommendation formats determined by the first determination unit; and a second determination unit that outputs a recommendation content that is predicted to have the greatest effectiveness in changing a user's behavior from among the predetermined number of recommendation contents generated by the recommendation generation unit.

[0007] In the above recommendation system, the first determination unit estimates a predetermined number of recommendation formats that will be effective for the user, and the recommendation generation unit generates recommendation content for each of the predetermined number of recommendation formats.The second determination unit then outputs the recommendation content that is most suitable for the user from the generated recommendation content.In this way, the system goes through a first stage in which a predetermined number of recommendation formats are determined based on the behavior change effect, and a second stage in which the recommendation content to be output from the predetermined number of recommendation contents generated based on the first stage, so that recommendation content with a high behavior change effect can be efficiently output.

[0008] According to the present disclosure, a recommendation system can be provided that can efficiently output recommended content suitable for a user.

[0009] FIG. 1 is a diagram illustrating a configuration of a recommendation system according to an embodiment of the present disclosure. FIG. 2 is a diagram illustrating an example of data input to an information receiving unit. FIG. 3 is a diagram illustrating an example of the contents of a recommendation implementation history. FIG. 4 is a diagram illustrating an example of the contents of a weight database. FIG. 5 is a diagram illustrating an example of the contents of a system database. FIG. 6 is a diagram illustrating an example of the contents of a recommendation format database. FIG. 7 is a diagram illustrating an example of recommendation data generated by a generation unit. FIG. 8 is a diagram illustrating an example of a recommendation content database. FIG. 9 is a flow chart illustrating an example of the operation of a recommendation system. FIG. 10 is a diagram illustrating a hardware configuration of a recommendation system according to an embodiment of the present disclosure.

[0010] Hereinafter, an embodiment of a recommendation system according to the present disclosure will be described in detail with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and duplicated description will be omitted.

[0011] FIG. 1 shows a recommendation system 10 according to this embodiment. The recommendation system 10 is a system (device) that determines recommendation content for encouraging a target user to take a predetermined action in a service provided to multiple users, including the target user. The service provided to the user is operated, for example, via a mobile communication network. As an example, the service may be provided to the user in a virtual space (e.g., a so-called metaverse) constructed on a computer network. The service may be provided, for example, by an external service system 20 (counter system) different from the recommendation system 10. The recommendation system 10 is capable of transmitting and receiving data to and from the service system 20 via a communication network. Note that the multiple service systems 20 shown in FIG. 1 may be systems that provide different services to users.

[0012] The service system 20 providing a service to a user transmits a request for a recommendation for the user to the recommendation system 10, for example, at a predetermined timing when the user is logged in to the service. Then, when the recommendation system 10 receives the request for a recommendation for the user from the service system 20, it outputs the generated recommendation to the service system 20. For example, the service system 20 may transmit the request for a recommendation to the recommendation system 10 at the timing when the user logs in to the service. Furthermore, the service system 20 may transmit the request for a recommendation to the recommendation system 10 based on the current time, current location, etc. The request for a recommendation may be data including at least identification information that identifies the user.

[0013] The recommendation content for the user is generated based on information including a recommendation format and a nudge type. The recommendation format is a type of output format for recommendations in the service system 20. The service system 20 in this embodiment can output recommendations to the user based on a plurality of output formats. For example, the recommendation format may be a text output that conveys the recommendation by visually displaying text, an audio output that conveys the recommendation by audio, or an object output that conveys the recommendation by making a predetermined object appear on a display device.

[0014] Recommendations to users are made, for example, by transmitting data corresponding to the recommendation content from the recommendation system 10 to the user's terminal via the service system 20. Output corresponding to the recommendation content is made on the terminal, allowing the user to recognize the recommendation.

[0015] The terminal is a device that can transmit and receive information to and from the service system 20 via a network such as a mobile communication network, and can also process information related to recommendations. The terminal may be a device such as a mobile phone, a smartphone, or a PC (personal computer). Note that the transmission and reception of information related to recommendations between the terminal and the recommendation system 10, as well as the input and output of the information, may be performed by a dedicated application installed on the terminal. Some of the information used in the recommendation system 10 may be acquired by the terminal and transmitted to the recommendation system 10.

[0016] A nudge is a mechanism or scheme based on cognitive bias that encourages a user to voluntarily (unconsciously) select a desired behavior. Nudge types may be classifications of nudges based on cognitive bias. For example, nudge types may include "conformity," which unconsciously conforms to the thoughts, actions, etc. of others, "loss aversion," which prioritizes avoiding losses over gaining benefits, and "scarcity," which increases value due to scarcity or difficulty in obtaining something.

[0017] 1 , an example recommendation system 10 includes an information receiving unit 11, an output determining unit 12 (first determining unit, second determining unit), a recommendation generating unit 13, a database group 15, and an information updating unit 16. In the recommendation system 10, when a recommendation request is input to the information receiving unit 11, the output determining unit 12 determines a predetermined number of recommendation formats. When recommendation contents corresponding to the determined recommendation formats are generated by the recommendation generating unit 13, the output determining unit 12 outputs the recommendation having the highest behavior change effect from among the generated recommendation contents to the service system 20. Details of such a recommendation system 10 will be described below.

[0018] The information receiving unit 11 receives various information necessary for generating recommendations from the service system 20. As an example, the information receiving unit 11 receives data related to a recommendation request from the service system 20. FIG. 2 shows an example of the data related to the recommendation request. The data related to the recommendation request includes at least identification information (user ID) for identifying a user. The data shown in FIG. 2 includes a system ID for identifying the service system 20, a user ID for identifying the user to whom the recommendation is to be made, and a recommendation format indicating the output format of the recommendation. In the example of FIG. 2, the recommendation format input from the service system 20 indicated by "Sys_0001" is "null," and no recommendation format is specified by the service system 20. In other words, the service system 20 does not specify a recommendation format for the recommendation system 10. Therefore, the recommendation system 10 outputs to the service system 20 a recommendation having a format most suitable for the user from among the recommendation formats that can be handled.

[0019] Furthermore, the information receiving unit 11 may receive data related to the recommendation result from the service system 20. The data related to the recommendation result may include information (whether or not it is effective) indicating whether or not a behavioral change has occurred in the user based on the recommendation content output from the recommendation system 10 to the service system 20. In one example, the data related to the recommendation result may include, for example, a user ID, the time of the recommendation, the recommendation format, the recommendation content, the nudge type, and whether or not it is effective.

[0020] The database group 15 stores various data necessary for the processing of the output determination unit 12 and the recommendation generation unit 13. As shown in FIG. 1 , an example of the database group 15 includes an implementation history database 15A, a weight database 15B, and a system database 15C. The implementation history database 15A stores recommendation results when a recommendation is made to a user. FIG. 3 is a diagram showing an example of the implementation history database 15A. The example of the implementation history database 15A includes a user ID, the time when the recommendation was made, the recommendation format, the nudge type of the recommendation, and whether the recommendation was effective.

[0021] FIG. 4 is a diagram showing an example of the contents of the weight database. The weight database 15B stores data indicating an effect prediction value for each recommendation format. The effect prediction value in the weight database 15B indicates the behavior change effect for each recommendation format, generated without specifying the user. The effect prediction value is an index indicating the likelihood of a user's behavior change when a recommendation is implemented. The effect prediction value may be a score value indicating the probability of a behavior change occurring, etc. The effect prediction value may be calculated based on the implementation history database 15A. For example, the effect prediction value may be calculated based on the recommendation results (effectiveness or non-effectiveness) of the same recommendation format extracted from the implementation history database 15A without specifying the user.

[0022] 5 is a diagram showing an example of the contents of the system database. The system database 15C stores the types of recommendation formats that can be handled by each service system 20. For example, as described above, the service system 20 indicated by "Sys_0001" does not specify a recommendation format in the recommendation request, but the service system 20 may be able to handle all conceivable recommendation formats.

[0023] The database group 15 may include a database storing attribute information indicating the attributes of each user. In one example, the user attributes may include information that allows for estimating the user's cognitive bias, and may include information such as gender, residential area, occupation, family structure, hobbies, and preferences.

[0024] The information update unit 16 updates the contents of the database group 15. For example, the information update unit 16 updates the contents of the implementation history database 15A based on the result of a recommendation input from the service system 20. Furthermore, when the contents of the implementation history database 15A are updated, the information update unit 16 updates the contents of the weight database 15B so that the new contents of the implementation history database 15A are reflected.

[0025] The output determination unit 12 has a function as a first determination unit and a function as a second determination unit. Here, the output determination unit 12 as the first determination unit will be described first, and the output determination unit 12 as the second determination unit will be described after the description of the recommendation generation unit 13. The output determination unit 12 as the first determination unit determines a predetermined number of recommendation formats from among a plurality of recommendation formats in order of predicted effectiveness in changing a user's behavior. For example, the output determination unit 12 determines the predetermined number of recommendation formats based on first information including at least a past recommendation implementation history in which the behavior change effect of each of the plurality of recommendation formats on the user can be confirmed. In one example, the first information includes a score indicating a weighting of the behavior change effect of each of the plurality of recommendation formats generated without specifying the user. The output determination unit 12 determines the predetermined number of recommendation formats based on the score and the user's implementation history.

[0026] For example, the output determination unit 12 acquires the past implementation history of a user for whom a recommendation is to be generated from the implementation history database 15A. In one example, the output determination unit 12 may extract the implementation history of a recommendation corresponding to the target user ID and recommendation format from the implementation history database 15A. The output determination unit 12 also acquires data from the weight database 15B. Then, the output determination unit 12 creates a recommendation format database based on the data (first information) extracted from the implementation history database 15A and the data (first information) in the weight database 15B.

[0027] 6 is a diagram showing an example of the contents of a recommendation format database. The recommendation format database stores score values ​​(effectiveness prediction values) indicating the probability of a user's behavior change for each recommendation format. In other words, the recommendation format database stores data indicating the likelihood of a user's behavior change occurring for each recommendation format.

[0028] For example, the effect prediction value for each recommendation format for each user may be calculated using a machine learning technique that inputs the implementation history of past recommendations for the user and the weight database 15B. Based on the recommendation format database calculated in this way, the output determination unit 12 selects a predetermined number (e.g., three) of recommendation formats in descending order of effect prediction value for the specified user, and requests the recommendation generation unit 13 corresponding to those recommendation formats to perform recommendation generation processing.

[0029] The recommendation generation unit 13 generates a predetermined number of recommendation contents corresponding to the predetermined number of recommendation formats determined by the output determination unit 12 as a first determination unit. FIG. 7 is a diagram showing an example of recommendation data generated by the recommendation generation unit. The recommendation data generated by the recommendation generation unit 13 includes, for example, data on the recommendation format, recommendation contents, and nudge type. The recommendation generation unit 13 outputs the generated recommendation data to the output determination unit 12.

[0030] The example recommendation generator 13 has multiple generators that generate recommendation content corresponding to multiple recommendation formats. For example, in the illustrated example, the first generator 13A generates recommendation content in the "text output" recommendation format, the second generator 13B generates recommendation content in the "audio output" recommendation format, and the third generator 13C generates recommendation content in the "object output" recommendation format. In the illustrated example, generators other than the first to third generators corresponding to the text output, audio output, and object output are omitted.

[0031] As described above, the recommendation content is generated based on information including the recommendation format and the nudge type. Therefore, the recommendation generation unit 13 determines a nudge type suitable for a user based on the cognitive bias of the target user. The recommendation generation unit 13 may have information regarding the user's cognitive bias in advance. Furthermore, the recommendation generation unit 13 may estimate the user's cognitive bias. For example, the recommendation generation unit 13 may estimate the user's cognitive bias using an estimation model (e.g., a regression analysis model) that estimates the user's cognitive bias based on the user's attributes. In this case, information regarding the user's attributes may be stored in advance in the database group 15.

[0032] The recommendation generation unit 13 selects a nudge type according to the acquired cognitive bias. There may be a one-to-one correspondence between cognitive biases and nudge types. For example, if the estimation model estimates that the user's cognitive bias is conformity bias, the recommendation generation unit 13 selects "conformity" as the nudge type. Similarly, if the user's cognitive bias is estimated to be "loss aversion bias" or "scarcity bias," "loss aversion" and "scarcity" are selected as the nudge types, respectively. Each generation unit corresponding to the recommendation format generates recommendation content based on the nudge type selected in this way.

[0033] For example, a case will be illustrated in which a recommendation encouraging the use of a coupon is generated. For example, when the nudge type is "conformity," the first generation unit 13A corresponding to the text output generates a text such as "Other people are using it, too." Furthermore, when the nudge type is "loss aversion," the first generation unit 13A generates a text such as "It would be a waste not to use the coupon." The text generated by the first generation unit 13A may be selected from a plurality of texts preset for each nudge. The first generation unit 13A may select a text appropriate for the content of the recommendation, for example. Note that the generated text may be part of a sentence, such as "Other people are using it, too." In this case, the service system 20 may complete the text connected to the generated text.

[0034] For example, when the nudge type is "tune-in," the second generation unit 13B, which corresponds to the voice output, generates voice data containing phrases such as "Other people are also using this service." The phrases constituting the voice data may be generated in a manner similar to that of the first generation unit 13A. The second generation unit 13B may select a voice type depending on the content of the recommendation. The voice type may be set according to the speaker, such as "male voice," "female voice," or "child's voice," or may be set more specifically, such as "slow male voice." Note that the second generation unit 13B may generate only parameters for generating voice data, rather than voice data. In this case, the service system 20 may generate voice data according to the generated parameters.

[0035] When the nudge type is "synchronization," the third generation unit 13C corresponding to the object output generates an object in which a phrase such as "Other people are also using it" is integrated with an image representing a coupon. The third generation unit 13C may select the content of the object according to the content of the recommendation. For example, the phrase as the object may be selected from characters written on a signboard, a person's lines (speech bubble), etc. Furthermore, the coupon as the object may be selected from a two-dimensional image, a three-dimensional image, etc.

[0036] The output determination unit 12, which serves as a second determination unit, outputs to the service system 20 the recommendation content predicted to have the greatest effect on behavior change for the user from among the predetermined number of recommendation contents generated by the recommendation generation unit 13. For example, the output determination unit 12 outputs the recommendation content predicted to have the greatest effect on behavior change for the user based on second information including at least a past recommendation implementation history in which the behavior change effect of each nudge type of the recommendation content on the user can be confirmed. In one example, the second information includes a score indicating a weighting of the behavior change effect for each of multiple recommendation formats generated without specifying a user, and the output determination unit 12 outputs the recommendation content predicted to have the greatest effect on behavior change for the user based on the score and the user's implementation history.

[0037] For example, the output determination unit 12 acquires the past implementation history of the user to whom the recommendation is to be output from the implementation history database 15A. That is, the output determination unit 12 extracts the implementation history of the recommendation for the target user ID from the implementation history database 15A. The output determination unit 12 also acquires data from the weight database 15B. Then, the output determination unit 12 creates a recommendation content database based on the data (second information) extracted from the implementation history database 15A and the data (second information) in the weight database 15B.

[0038] 8 is a diagram showing an example of the contents of a recommendation content database. The recommendation content database stores effect prediction values ​​indicating the probability of a target user's behavior changing when receiving a recommendation based on a certain nudge type in a certain recommendation format. In other words, the recommendation content database stores data indicating the likelihood of a target user's behavior changing for a recommendation based on each nudge type in each recommendation format.

[0039] For example, a machine learning technique may be used to calculate the predicted effect value for each nudge type in each recommendation format for each user using inputs of the user's past recommendation implementation history and the weight database 15B. Based on the recommendation content database calculated in this way, the output determination unit 12 selects the recommendation content with the highest predicted effect value for the specified user and outputs the selected recommendation content to the service system 20.

[0040] FIG. 9 is a flowchart illustrating the operation of the recommendation system 10. As shown in FIG. 9, when recommendation generation is performed in the recommendation system 10, a recommendation request is first output from the service system 20 to the information receiving unit 11 (step S1), and the output determination unit 12 accepts the recommendation request (step S2). Next, the output determination unit 12 selects a generation unit that will generate the recommendation (step S3). That is, the output determination unit 12 extracts recommendation implementation histories corresponding to the user ID and recommendation format from the implementation history database 15A. The database group 15, including the implementation history database 15A, is periodically updated by the information update unit 16 (step S10). The output determination unit 12 generates a recommendation format database based on the extracted data and determines a predetermined number of recommendation formats based on the generated recommendation format database. The output determination unit 12 requests the generation units corresponding to the determined predetermined number of recommendation formats to generate recommendation contents. Next, recommendations are generated by the selected generation units (in the example of FIG. 9 , the first generation unit 13A, the second generation unit 13B, and the third generation unit 13C) (step S4). Each generation unit outputs the generated recommendation to the output determination unit 12. Note that the output recommendation may be data in which a recommendation format, recommendation content, and nudge type are associated with each other. Next, the output determination unit 12 selects a recommendation to be output to the service system 20 from the predetermined number of generated recommendations (step S5). That is, the output determination unit 12 extracts from the implementation history database 15A past recommendation implementation histories corresponding to the user ID, recommendation format, and nudge type related to the recommendation generated by the recommendation generation unit. Then, the output determination unit 12 generates a recommendation content database based on the extracted data and the weight database, and determines, based on the generated recommendation content database, an output format of the recommendation that is predicted to have the greatest behavioral change effect on the user. The output determination unit 12 outputs the determined recommendation content to the service system 20. This allows the service system 20 to output the recommendation to the terminal of the target user.The result of the recommendation (for example, information on whether or not a coupon was used) is transmitted from the service system 20 to the information receiving unit 11 and can be used by the information updating unit 16 to update the database group 15 .

[0041] As described above, the example recommendation system 10 includes a first determination unit (output determination unit 12) that determines a predetermined number of recommendation formats from a plurality of recommendation formats in order of predicted effectiveness in changing user behavior as the data output format, a recommendation generation unit 13 that generates a predetermined number of recommendation contents corresponding to the predetermined number of recommendation formats determined by the first determination unit, and a second determination unit (output determination unit 12) that outputs the recommendation content that is predicted to have the greatest effectiveness in changing user behavior from the predetermined number of recommendation contents generated by the recommendation generation unit 13.

[0042] In the recommendation system 10 described above, the first determination unit estimates a predetermined number of recommendation formats that will be effective for the user, and the recommendation generation unit 13 generates recommendation content for each of the predetermined number of recommendation formats. The second determination unit then outputs the recommendation content that is most suitable for the user from the generated recommendation content. In this way, in the recommendation system 10 of this embodiment, recommendations are determined through a first stage in which a predetermined number of recommendation formats are determined based on the behavior change effect, and a second stage in which recommendation content to be output from a predetermined number of recommendation contents generated based on the first stage, so that recommendation content with a high behavior change effect can be efficiently output.

[0043] The first determination unit may determine the predetermined number of recommendation formats based on first information including at least a past implementation history of recommendations that can confirm the behavioral change effects of each of the plurality of recommendation formats on the user. In this configuration, since the first information includes the past implementation history of the user, it is possible to efficiently estimate a recommendation format that is suitable for each user.

[0044] The first information may include scores indicating weightings of behavior change effects for each of the plurality of recommendation formats generated without specifying the user, and the first determination unit may determine a predetermined number of recommendation formats based on the scores and the user's implementation history. In this configuration, the first determination unit estimates the recommendation formats based not only on the user's implementation history but also on the score that does not specify the user, thereby preventing bias in the estimation result.

[0045] The second determination unit may output the recommendation content predicted to have the greatest effect on behavioral change for the user based on second information including at least a past implementation history of recommendations that allows confirmation of the behavioral change effect of each nudge type of the recommendation content for the user. In this configuration, since the second information includes the user's past implementation history, it is possible to appropriately select the recommendation content that is appropriate for each user.

[0046] The second information may include a score indicating a weighting of the behavior change effect for each of the plurality of recommendation formats generated without specifying the user, and the second determination unit may output the recommendation content predicted to have the greatest behavior change effect for the user based on the score and the user's implementation history. In this configuration, the second determination unit determines the recommendation content based not only on the user's implementation history but also on the score that does not specify the user, thereby preventing bias in the determination result.

[0047] In the above embodiment, an example has been described in which the service system 20 can handle all recommendation formats that can be generated by the recommendation system 10. However, in one example, the recommendation system 10 can also output recommendations to service systems that can only support specific recommendation formats. For example, if a service system supports only some recommendation formats, the service system may transmit data specifying the types of multiple supported recommendation formats to the recommendation system 10 when requesting a recommendation from the recommendation system 10. In this case, the recommendation system 10 can select the optimal recommendation for the user from the specified multiple recommendation formats. Furthermore, if the type of recommendation format is not specified, the output determination unit 12 may access the system database 15C to acquire the types of recommendation formats that can be supported by the service system.

[0048] Furthermore, the service system that provides services to users in a virtual space constructed on a computer network has been described, but the services provided by the service system are not limited to the above.

[0049] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0050] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0051] For example, the recommendation system 10 according to an embodiment of the present disclosure may function as a computer that performs information processing according to the present disclosure. Fig. 10 is a diagram illustrating an example of the hardware configuration of the recommendation system 10 according to an embodiment of the present disclosure. The recommendation system 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. The hardware configuration of the service system 20 may also be as described here.

[0052] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the recommendation system 10 may be configured to include one or more of the apparatuses shown in the figure, or may be configured to exclude some of the apparatuses.

[0053] Each function in the recommendation system 10 is realized by loading specific software (programs) onto hardware such as a processor 1001 and a memory 1002, causing the processor 1001 to perform calculations, control communication via a communication device 1004, and control at least one of reading and writing data in the memory 1002 and the storage 1003.

[0054] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, each function in the recommendation system 10 described above may be realized by the processor 1001.

[0055] Furthermore, the processor 1001 reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes in accordance with these. The program used is a program that causes a computer to execute at least some of the operations described in the above-described embodiments. For example, each function in the recommendation system 10 may be realized by a control program stored in the memory 1002 and running on the processor 1001. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0056] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for performing information processing according to an embodiment of the present disclosure.

[0057] The storage 1003 is a computer-readable recording medium and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. The storage 1003 may also be referred to as an auxiliary storage device. The storage medium provided in the recommendation system 10 may be, for example, a database, a server, or other appropriate medium including at least one of the memory 1002 and the storage 1003.

[0058] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0059] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0060] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0061] The recommendation system 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0062] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0063] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0064] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0065] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0066] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0067] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0068] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0069] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0070] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0071] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0072] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0073] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0074] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0075] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0076] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0077] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0078] 10...Recommendation system, 11...Information receiving unit, 12...Output determination unit, 13...Recommendation generation unit, 15...Database group, 16...Information update unit, 20...Service system, 1001...Processor, 1002...Memory, 1003...Storage, 1004...Communication device, 1005...Input device, 1006...Output device, 1007...Bus.

Claims

1. A recommendation system comprising: a first determination unit that determines a predetermined number of recommendation formats from a plurality of recommendation formats in order of predicted effectiveness in changing a user's behavior as a data output format; a recommendation generation unit that generates a predetermined number of recommendation contents corresponding to the predetermined number of recommendation formats determined by the first determination unit; and a second determination unit that determines a recommendation content that is predicted to have the greatest effectiveness in changing a user's behavior from the predetermined number of recommendation contents generated by the recommendation generation unit.

2. The recommendation system of claim 1, wherein the first determination unit determines the predetermined number of recommendation formats based on first information including at least a history of past recommendation implementation that enables confirmation of the behavioral change effect of each of the multiple recommendation formats on the user.

3. The recommendation system described in claim 2, wherein the first information includes a score indicating a weighting of the behavior change effect for each of the multiple recommendation formats generated without identifying a user, and the first determination unit determines the predetermined number of recommendation formats based on the score and the implementation history of the user.

4. The recommendation system of claim 1, wherein the second determination unit determines the recommendation content that is predicted to have the greatest effect on behavior change for the user based on second information including at least a history of past recommendation implementation that allows confirmation of the behavior change effect of the recommendation content for each nudge type on the user.

5. The recommendation system described in claim 4, wherein the second information includes a score indicating a weighting of the behavior change effect for each of the multiple recommendation formats generated without identifying a user, and the second determination unit determines the recommendation content that is predicted to have the greatest behavior change effect for the user based on the score and the implementation history of the user.

Citation Information

Patent Citations

  • Content generation device, content generation method and content generation program

    JP2017191615A