Information processing device, information processing method, and program

Abstract

To provide a technique for realizing an action design.SOLUTION: One aspect of the present disclosure relates to an information processing device including an acquisition unit that acquires an attribute of a subject person and a desired action of the subject person, and a nudge selection unit that, on the basis of correspondence information indicating nudge information corresponding to each pair of an attribute of a subject person and an action, selects nudge information corresponding to a pair of the acquired attribute and action of the subject person.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] In recent years, research has been conducted into behavioral design, which supports individuals in making proactive changes to their behavior. In 2017, Professor Richard Thaler was awarded the Nobel Prize in Economics for his research into behavioral economics. Professor Richard Thaler proposed the concept of "nudge" in his book "Nudge: Improving Decisions About Health, Wealth, and Happiness," and suggested the use of nudges in behavioral analysis and behavioral design.

[0003] Nudge is an approach that uses knowledge from behavioral science (cognitive bias) to gently encourage people to take desired actions. In other words, rather than using methods such as large economic incentives or penalties, it encourages behavioral change by designing mechanisms that make people want to act voluntarily. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-140596 A Summary of the Invention [Problem to be solved by the invention]

[0005] An object of the present disclosure is to provide technology for realizing behavioral design. [Means for solving the problem]

[0006] One aspect of the present disclosure relates to an information processing device having an acquisition unit that acquires attributes of a subject and a desired action of the subject, and a nudge selection unit that selects nudge information corresponding to each pair of attributes and actions of the subject based on correspondence information indicating nudge information corresponding to the pair of attributes and actions acquired for the subject. Effect of the Invention

[0007] According to the present disclosure, a technique for realizing behavioral design can be provided. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram illustrating a user assistance process according to one embodiment of the present disclosure. [Diagram 2] FIG. 2 is a block diagram illustrating a hardware configuration of an information processing device according to an embodiment of the present disclosure. [Diagram 3] FIG. 3 is a block diagram illustrating a functional configuration of an information processing device according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram illustrating correspondence information according to an embodiment of the present disclosure. [Diagram 5] FIG. 5 is a diagram showing an example of an email editing screen according to an embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram showing an example of an email editing screen according to an embodiment of the present disclosure. [Figure 7] FIG. 7 is a diagram showing an example of an email editing screen according to an embodiment of the present disclosure. [Figure 8] FIG. 8 is a diagram illustrating a content editing process according to an embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram illustrating a wording example generation model according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is a flowchart illustrating a nudge selection process according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0010] In the following embodiment, an information processing device that selects appropriate nudge information to assist a user's work is disclosed.

[0011] [Summary of the Disclosure] To summarize the present disclosure, when a user creates text such as an email to encourage a target person such as a customer to visit a specific site or to follow up on a purchase, an information processing device according to the following embodiment presents the user with nudge information that is considered to be effective in encouraging the target person to take a desired action (e.g., visiting a specific site, repurchasing a product, etc.) and assists the user in creating the text by referring to the presented nudge information.

[0012] 1, an information processing device 100 according to an embodiment of the present disclosure receives from a user a target person and / or a target person's attributes for a task to be supported (e.g., sending an email or a message, sending a direct mail (DM), streaming a video for each customer, etc.) and an action to be taken by the target person through the task, and presents the user with nudge information for supporting the user with the task. The user may be able to create more appealing text or video for emails, messages, DMs, etc. by referring to the presented nudge information.

[0013] Here, the information processing device 100 may have, for example, a hardware configuration as shown in Fig. 2. That is, the information processing device 100 has a drive device 101, a storage device 102, a memory device 103, a processor 104, a user interface (UI) device 105, and a communication device 106, which are interconnected via a bus B.

[0014] Programs or instructions for implementing various functions and processes in the information processing device 100 may be stored in a removable storage medium such as a CD-ROM (Compact Disk-Read Only Memory) or a flash memory. When the storage medium is set in the drive device 101, the programs or instructions are installed from the storage medium via the drive device 101 into the storage device 102 or the memory device 103. However, the programs or instructions do not necessarily have to be installed from the storage medium, and may be downloaded from any external device via a network or the like.

[0015] The storage device 102 is realized by a hard disk drive or the like, and stores installed programs or instructions as well as files, data, etc. used in executing the programs or instructions.

[0016] The memory device 103 is realized by a random access memory, a static memory, or the like, and when a program or an instruction is activated, reads and stores the program or instruction, data, or the like from the storage device 102. The storage device 102, the memory device 103, and the removable storage medium may be collectively referred to as a non-transitory storage medium.

[0017] The processor 104 may be realized by one or more CPUs (Central Processing Units), GPUs (Graphics Processing Units), processing circuitry, etc., which may be composed of one or more processor cores, and performs various functions and processes of the information processing device 100 in accordance with programs, instructions, data such as parameters necessary to execute the programs or instructions, etc. stored in the memory device 103.

[0018] The user interface (UI) device 105 may be composed of input devices such as a keyboard, a mouse, a camera, a microphone, etc., output devices such as a display, a speaker, a headset, a printer, etc., and input / output devices such as a touch panel, and realizes an interface between a user and the information processing device 100. For example, a user may operate the information processing device 100 by operating a GUI (Graphical User Interface) displayed on a display or a touch panel using a keyboard, a mouse, etc.

[0019] The communication device 106 is realized by various communication circuits that execute wired and / or wireless communication processing with an external device, the Internet, a LAN (Local Area Network), a cellular network, or other communication network.

[0020] However, the above-described hardware configuration is merely an example, and the information processing device 100 according to the present disclosure may be realized by any other appropriate hardware configuration.

[0021] [Information processing device] Next, a description will be given of the information processing device 100 according to an embodiment of the present disclosure. Fig. 3 is a block diagram showing a functional configuration of the information processing device 100 according to an embodiment of the present disclosure.

[0022] As shown in FIG. 3, the information processing device 100 includes an acquisition unit 110 and a nudge selector 120.

[0023] The acquisition unit 110 acquires the attributes of a target person and a desired action of the target person. For example, when a user uses the information processing device 100 to create an email encouraging a target person with attribute #i to perform action #j, the user instructs the information processing device 100 of the target person's target attribute #i and the desired target action #j. Upon receiving the instructed target person attribute #i and target person action #j, the acquisition unit 110 passes the received target person attribute #i and target person action #j to the nudge selection unit 120.

[0024] The nudge selection unit 120 selects nudge information corresponding to the pair of attributes and actions acquired for the subject based on correspondence information indicating nudge information corresponding to each pair of the subject's attribute and action. For example, as shown in Fig. 4, the nudge selection unit 120 may select nudge information corresponding to the pair of subject attributes and subject actions acquired from the acquisition unit 110 by referring to correspondence information in a table format indicating nudge information corresponding to each pair of attributes and actions. Such correspondence information may be created in advance by any appropriate method and made available to the information processing device 100.

[0025] For example, it is assumed that the correspondence information referred to by the nudge selection unit 120 is defined in a table format as shown in Fig. 4. In this case, when a target person attribute #i and a target person action #j are acquired from the acquisition unit 110, the nudge selection unit 120 may refer to the correspondence information, select nudge information #ij corresponding to the pair of the target person attribute #i and the target person action #j, and present the selected nudge information #ij to the user.

[0026] For example, when a user creates an email to a customer with the customer attributes of "name: Taro Sato, age: 62, address: Minato-ku, Tokyo, roommate: wife, real estate: owned, hobby: yacht, other: participation in local community" as shown in FIG. 5, requesting "cooperation in a customer satisfaction survey," the acquisition unit 110 acquires from the user a target person attribute #i corresponding to the customer attributes and a target person action #j corresponding to the "cooperation in a customer satisfaction survey" desired to be taken by the customer.

[0027] The target attribute #i may be stored in a customer database in association with registered customer attributes corresponding to each customer, and may be configured so that when a user inputs a customer's name, the target attribute #i corresponding to that customer is specified. In this case, the acquisition unit 110 can acquire the target attribute #i of the customer simply by the user specifying the name of the customer to whom the email is to be sent.

[0028] Also, each target person action #j may be registered in advance, and the user may be able to specify a desired target person action #j from among the registered target person action candidates. For example, when the user specifies a target person action #j of "cooperating in a customer satisfaction survey" from among the target person action candidates, the acquisition unit 110 can acquire the specified target person action #j.

[0029] In the example shown in Fig. 5, when the acquisition unit 110 acquires the target attribute #i and the target action #j, the nudge selection unit 120 refers to the correspondence information to identify the nudge information #ij corresponding to the pair of the target attribute #i and the target action #j. For example, when the nudge information #ij indicates the nudge information #4 and #24, the nudge selection unit 120 may present the nudge information #4 and the nudge information #24 to the user as shown in Fig. 5. This allows the user to create a more appealing message addressed to the target by referring to the presented nudge information #4 and #24.

[0030] In one embodiment, the nudge selection unit 120 may present a wording example corresponding to the selected nudge information. Specifically, the nudge selection unit 120 may present to the user, in addition to or instead of the selected nudge information, one or more wording examples that can be used for the support target task (e.g., sending emails or messages, sending direct mail (DM), video distribution for each customer, etc.) based on the selected nudge information. Such wording examples may be prepared in correspondence with the target person's action and / or the support target task and the nudge information, and may be stored in a wording example database or the like.

[0031] For example, as shown in Fig. 6, the nudge selection unit 120 may present to the user nudge information #4 and its corresponding example wording, "Mr. Sato, this is Tanaka in charge," and nudge information #24 and its corresponding example wording, "In addition, if you respond to our service evaluation, we will make a donation to our marine conservation plan, one of our sustainability efforts, according to the number of people who respond." Using the presented example wording, the user can create an email message as shown in Fig. 7.

[0032] According to this embodiment, not only nudge information but also example wording corresponding to the nudge information is presented to the user, and the user can use the presented example wording to more easily perform the task for which support is being provided, such as composing email text.

[0033] In one embodiment, the nudge selection unit 120 may add example wording to the content information presented to the subject. In the embodiment described above with reference to Figs. 5 to 7, the nudge selection unit 120 presented the user with nudge information and / or example wording that can be used for creating email text, but the presentation of nudge information, etc. according to the present disclosure is not limited to this. For example, information based on nudge information, etc. may be added to content such as an image. Specifically, an example wording such as "Get 1000 yen off if you use it for 2 hours or more now!" corresponding to nudge information #5 may be inserted into content for direct mail as shown in Fig. 8. Such example wording may be prepared in correspondence with the subject's action and / or the work to be supported and the nudge information, and stored in an example wording database, etc.

[0034] When the nudge selection unit 120 acquires the target attribute of the direct mail destination and the desired target action (such as visiting a site from a QR code (registered trademark) printed on the direct mail in the illustrated example) from the user, the nudge selection unit 120 refers to the correspondence information stored in advance to identify the nudge information #5 corresponding to the pair of the target attribute and the target address. Then, the nudge selection unit 120 may suggest to the user that the nudge information #5 and / or the wording example corresponding to the nudge information #5 be inserted into the content of the direct mail. In the illustrated example, the wording example corresponding to the nudge information #5, "Get 1000 yen off if you use it for 2 hours or more now!", is inserted into the content of the direct mail. Note that, in the illustrated example, the wording example is added to the content, but the present disclosure is not limited to this, and multi-modality data such as images, videos, and audio may be presented to the user.

[0035] According to this embodiment, it is possible to present to the user not only text data such as emails, but also multi-modality data such as nudge information and / or wording, images, videos, and audio based on the nudge information for content such as image data, making it possible to support tasks with a wider range of applications.

[0036] Furthermore, in one embodiment, the nudge selector 120 may generate the wording examples to be presented by using a machine learning model trained to receive the subject's attributes and the desired subject's actions as inputs and generate the wording examples to be presented to the subject. Specifically, a wording example generation model 200 may be prepared and made available to the information processing device 100 by using a training data set of training input data consisting of pairs of subject attributes and desired subject actions, and training output data consisting of wording examples created based on nudge information corresponding to the input pairs. For example, the wording example generation model 200 may be realized by a neural network. In this case, the neural network model may be trained by inputting training input data to a neural network model to be trained, and adjusting parameters of the neural network model according to an error backpropagation method according to an error between an output result from the neural network model and the training output data.

[0037] The nudge selector 120 may use the thus trained wording example generation model 200 to input the target person attributes and the desired target person actions acquired from the acquisition unit 110 to the wording example generation model 200 as shown in FIG. 9, and acquire wording examples from the wording example generation model 200. The nudge selector 120 may present the acquired wording examples to the user. Note that such a wording example generation model 200 may be composed of any appropriate general-purpose generative model, such as a GPT-based generative model. For example, the nudge selector 120 may generate prompt data to be input to the general-purpose generative model based on the target person attributes, the desired target person actions, and the corresponding nudge information, and input the generated prompt data to the general-purpose generative model to acquire wording examples.

[0038] According to this embodiment, it is possible to acquire and generate wording examples based on nudge information corresponding to target user attributes and desired target user actions without preparing a wording example database.

[0039] Furthermore, in one embodiment, the nudge selector 120 may select a plurality of nudge information, present a plurality of wording examples corresponding to each of the selected plurality of nudge information to the subject, and obtain feedback from the subject for each of the presented plurality of wording examples. For example, the nudge selector 120 may select two pieces of nudge information, and perform an A / B test using wording examples based on these two pieces of nudge information. By feedback from such an A / B test, it is possible to measure the effect of the selected nudge information, and more effective nudge information can be provided.

[0040] For example, the nudge selection unit 120 selects nudge information #5 and nudge information #43 for a pair of a target attribute and a desired target action based on the correspondence information prepared in advance, and presents the user with the A pattern corresponding to the nudge information #5 and the B pattern corresponding to the nudge information #43. The user creates email text corresponding to each of the A pattern and the B pattern, and sends each email to the target to collect feedback on the target action. For example, if the desired target action is a visit to a specific site, the number of visits to the site by the target may be counted, and it may be determined whether the A pattern or the B pattern has achieved a higher visit rate. It may be determined that the nudge information corresponding to the pattern that has achieved a higher visit rate is the more effective nudge information. At this time, the nudge selection unit 120 may update the correspondence information based on the feedback. That is, it becomes possible to delete nudge information whose visit rate is less than a predetermined threshold from the correspondence information, and present only the more effective nudge information to the user.

[0041] [Nudge selection process] Next, a nudge selection process according to an embodiment of the present disclosure will be described. Fig. 10 is a flowchart showing the nudge selection process according to an embodiment of the present disclosure. The nudge selection process may be executed by, for example, the information processing device 100, and more specifically, may be realized by the processor 104 of the information processing device 100 executing a computer program or instructions stored in the memory device 103.

[0042] In step S101, the information processing device 100 acquires attributes of a target person and a desired action of the target person. Specifically, the information processing device 100 receives the target person attributes and the desired target person action from a user who intends to use the information processing device 100 to perform a support target task such as sending an email or a message, sending a direct mail, or distributing a video to a target person such as a customer.

[0043] The target attribute may be, for example, a female customer in her 30s who has purchased children's clothes, a male customer in his 70s who has purchased health foods, etc., and a female customer in her 30s who has purchased children's clothes may be labeled with the target attribute "housewife," and a male customer in his 70s who has purchased health foods may be labeled with the target attribute "elderly man." In addition, the desired target action may be, for example, a site visit or a repurchase.

[0044] In step S102, the information processing device 100 selects nudge information corresponding to the pair of attributes and actions acquired for the subject based on correspondence information indicating nudge information corresponding to each pair of the subject's attributes and actions. That is, the information processing device 100 refers to correspondence information prepared in advance, identifies nudge information corresponding to the pair of the subject's attributes acquired in step S101 and the desired subject's action, and presents the identified nudge information and / or example wording based on the nudge information to the user.

[0045] For example, when the target attribute is "housewives" and the desired target action is "site visit", the information processing device 100 refers to the correspondence information to identify nudge information corresponding to the pair of the target attribute "housewives" and the desired target action "site visit". For example, the identified nudge information indicates "scarcity heuristic", and the information processing device 100 may present nudge information related to "scarcity heuristic" to the user. In addition to / instead of the nudge information, the information processing device 100 may extract a wording example "10% OFF campaign now on!!" corresponding to the desired target action "site visit" and "scarcity heuristic" from the wording example database and present the extracted wording example to the user. When the nudge information and / or wording example are presented, the user can use / refer to the presented nudge information and / or wording example to create a more appealing email or message.

[0046] According to the above-described embodiment, the information processing device 100 can present to the user nudge information corresponding to the subject attributes and the desired subject action, and the user can refer to the presented nudge information to more effectively encourage the subject's behavior.

[0047] Although the examples of the present disclosure have been described in detail above, the present disclosure is not limited to the specific embodiments described above, and various modifications and variations are possible within the scope of the gist of the present disclosure described in the claims. [Explanation of symbols]

[0048] 100 Information processing device 110 Acquisition Department 120 Nudge Selection Section

Claims

1. An acquisition unit that acquires attributes of a subject and a desired action of the subject; a nudge selection unit that selects nudge information corresponding to each pair of an attribute and an action of a subject based on correspondence information indicating nudge information corresponding to the pair of the attribute and the action acquired for the subject; An information processing device having the above configuration.

2. The information processing device according to claim 1 , wherein the nudge selector presents example text corresponding to the selected nudge information.

3. The information processing apparatus according to claim 2 , wherein the nudge selector extracts the wording example to be presented from a wording example database that stores wording examples corresponding to the action and the nudge information.

4. The information processing device according to claim 2 , wherein the nudge selection unit receives as input attributes of a subject and a desired action of the subject, and generates the wording examples to be presented to the subject by utilizing a machine learning model trained to generate wording examples to be presented to the subject.

5. The information processing device according to claim 2 , wherein the nudge selector adds the example wording to content information to be presented to the subject person.

6. The information processing device according to claim 1 , wherein the nudge selection unit selects a plurality of pieces of nudge information, presents a plurality of wording examples corresponding to each of the selected plurality of pieces of nudge information to the subject, and obtains feedback from the subject for each of the presented plurality of wording examples.

7. The information processing device according to claim 6 , wherein the nudge selector updates the correspondence information based on the feedback.

8. Obtaining attributes of a subject and a desired action for said subject; selecting nudge information corresponding to each pair of an attribute and an action of a subject based on correspondence information indicating nudge information corresponding to the pair of the attribute and the action acquired for the subject; An information processing method implemented by a computer.

9. Obtaining attributes of a subject and a desired action for said subject; selecting nudge information corresponding to each pair of an attribute and an action of a subject based on correspondence information indicating nudge information corresponding to the pair of the attribute and the action acquired for the subject; A program that causes a computer to execute the following.

Images