Information processing device, information processing method, and program

Abstract

Provides users with motivation to interact with the conversational agent. [Solution] The information processing device 2 includes a storage unit 22 that stores a user ID (identification) for identifying a user and the user's purchase history of products purchased in association with each other; a user information acquisition unit 231 that acquires a user ID from a terminal; a dialogue acquisition unit 232 that acquires the content of a dialogue between the user and a dialogue agent that converses about topics based on products included in the purchase history associated with the user ID acquired by the user information acquisition unit 231; a determination unit 234 that determines the content of a reward based on at least one of the length of the dialogue between the user and the dialogue content; and a granting unit 235 that grants the user a reward indicating the content of the reward determined by the determination unit 234.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and a program. Background Art

[0002] Conventionally, there has been known a dialogue apparatus that causes an avatar to be displayed on a terminal as a dialogue agent and makes the dialogue agent output a response based on a voice uttered by a user to thereby conduct a dialogue with the user (see, for example, Patent Document 1). Prior Art Literature Patent Literature

[0003] Patent Document 1 Japanese Unexamined Patent Application Publication No. 2024-112283 Summary of the Invention Problems to be Solved by the Invention

[0004] When a terminal is installed in a place where people come and go, there has arisen a problem that a user feels embarrassed to have a dialogue with a dialogue agent, and the user hesitates to have a dialogue with the dialogue agent.

[0005] Accordingly, the present invention has been made in view of these points, and an object of the present invention is to provide a user with motivation to have a dialogue with a dialogue agent. Means for Solving the Problems

[0006] An information processing device according to a first aspect of the present invention includes: a storage unit that stores a user ID (identification) for identifying a user and a purchase history of the user in association with the user's purchase history of products; a user information acquisition unit that acquires the user ID from a terminal; a dialogue acquisition unit that acquires the content of a dialogue between the user and a dialogue agent that converses about topics related to the products included in the purchase history associated with the user ID acquired by the user information acquisition unit; a determination unit that determines the content of a benefit based on at least one of the length of the dialogue between the user and the dialogue content; and a granting unit that grants the user a benefit indicating the benefit content determined by the determination unit.

[0007] The decision-making unit may determine the type of benefit that is more favorable the longer the conversation between the user and the dialogue agent.

[0008] The decision unit may select a recommended product from among a plurality of predetermined products that is related to the product included in the purchase history associated with the user ID acquired by the user information acquisition unit, and that was recommended by the dialogue agent in the dialogue between the user and the dialogue agent, and may determine the content of the benefit that will be preferential for purchasing the selected recommended product.

[0009] The decision unit may determine the most favorable reward content if the user utters a predetermined keyword during the conversation between the user and the dialogue agent that indicates the user may wish to purchase the recommended product.

[0010] The dialogue acquisition unit may acquire captured images of the user during a dialogue between the user and the dialogue agent, and the information processing device may further have an analysis unit that analyzes, based on the captured images, whether the user has taken a predetermined attitude indicating that they may want to purchase the recommended product after the dialogue agent has recommended the recommended product, and the decision unit may determine the content of the benefit that is more favorable if the user has taken the predetermined attitude.

[0011] The decision-making unit may determine the most favorable type of benefit if the conversational agent takes the predetermined attitude after presenting the price of the recommended product.

[0012] The decision unit may determine the most favorable reward content if the user makes a statement regarding their evaluation of the product included in the purchase history associated with the user ID acquired by the user information acquisition unit during the conversation between the user and the dialogue agent, or of a recommended product suggested by the dialogue agent.

[0013] The memory unit may further store, for each predetermined product, the reasons why a consumer does not purchase that predetermined product. The decision unit may, if the user states in a dialogue between the user and the dialogue agent why they do not purchase a recommended product suggested by the dialogue agent, determine a more favorable reward based on the amount of information stored in the memory unit regarding the user's stated reasons for not purchasing the recommended product.

[0014] The memory unit may further store the reason why a consumer purchased a predetermined product for each predetermined product, and the decision unit may, if the user states the reason for purchasing a product included in the purchase history associated with the user ID acquired by the user information acquisition unit during a conversation between the user and the dialogue agent, determine a more favorable reward based on the amount of information stored in the memory unit regarding the reason for purchasing the product stated by the user.

[0015] The memory unit may further store, for each predetermined benefit, a predetermined period and a predetermined benefit that is permitted to be granted after the predetermined period has elapsed, wherein the degree of preferential treatment increases with the length of the predetermined period. The information processing device may further include an output control unit that, each time the duration of the dialogue between the user and the dialogue agent exceeds the predetermined period stored in the memory unit, outputs the predetermined benefit stored in the memory unit in association with the predetermined period to the terminal.

[0016] The output control unit may further output to the terminal the predetermined benefit content stored in the storage unit in association with the unfulfilled period, which is a predetermined period longer than the duration of the dialogue between the user and the dialogue agent, and the difference between the duration of the dialogue between the user and the dialogue agent and the unfulfilled period.

[0017] The storage unit may further store, at predetermined intervals, a predetermined period and a plurality of predetermined benefit contents, each with a different degree of preferential treatment, which are permitted to be granted when the predetermined period has elapsed. The information processing device may further include an output control unit that causes the terminal to output at least the predetermined benefit content with the highest degree of preferential treatment from among the plurality of predetermined benefit contents stored in the storage unit in association with the most recent predetermined period, which is a predetermined period longer than the period of dialogue between the user and the dialogue agent.

[0018] A second aspect of the present invention relates to an information processing method, which is executed by a computer having a storage unit that stores a user ID for identifying a user and a purchase history of the user in association with the user's purchase history of products, and includes the steps of: obtaining the user ID from a terminal; obtaining the content of a conversation between the user and a conversational agent that converses about a topic based on the product included in the purchase history associated with the obtained user ID; determining the content of a reward based on at least one of the length of the conversation between the user and the conversational agent and the content of the conversation; and granting the user a reward indicating the determined reward content.

[0019] A program according to a third aspect of the present invention causes a computer having a storage unit that stores a user ID for identifying a user and a purchase history of the user in association with the user's purchase history of goods to function as a user information acquisition unit that acquires the user ID from a terminal, a dialogue unit that acquires the content of a dialogue between the user and a dialogue agent that converses with the user about topics related to the goods included in the purchase history associated with the user ID acquired by the user information acquisition unit, a determination unit that determines the content of a reward based on at least one of the length of the dialogue between the user and the dialogue agent and the content of the dialogue, and a granting unit that grants the user a reward indicating the content of the reward determined by the determination unit. [Effects of the Invention]

[0020] According to the present invention, it is possible to provide users with motivation to interact with a dialogue agent. [Brief explanation of the drawing]

[0021] [Figure 1] This is a diagram illustrating the overview of the information processing system. [Figure 2] This diagram schematically shows the functional configuration of an information processing device. [Figure 3] This diagram shows an example of the configuration of a rewards management database. [Figure 4] It is a diagram schematically showing a display screen displayed on a display of an information terminal. [Figure 5] It is a sequence diagram showing the flow of processing executed by the information processing system. Mode for Carrying Out the Invention

[0022] [Outline of Information Processing System S] Figure 1 is a diagram for explaining the outline of the information processing system S. The information processing system S is a system used to provide an information processing service. The information processing service is a service used for providing information used for promoting product sales and product marketing to business operators that sell products or services (hereinafter simply referred to as "products") (e.g., retail business operators, manufacturing business operators, etc.), and for providing benefits to consumers. The information processing system S includes an information terminal 1 and an information processing device 2.

[0023] The information terminal 1 is a computer used by a dialogue agent to conduct dialogue with a user. The information terminal 1 is installed, for example, in a store that sells products. The dialogue agent is, for example, a large-scale language model trained to conduct dialogue on topics based on products purchased by the user in the past. Topics based on products purchased by the user in the past include, for example, evaluations (impressions) of products purchased by the user in the past, recommendations of promotional products in the same genre as products previously purchased by the user among a plurality of promotional products for which the store promotes sales, and the like. The user is, for example, a member of the information processing service. The information terminal 1 includes a display that displays an avatar representing the dialogue agent, a touch panel that receives input, a speaker that outputs voice of the dialogue agent, a microphone that acquires sound around the information terminal 1, and a camera that captures images of the area around the information terminal 1.

[0024] Information processing device 2 is a computer that manages information processing services, such as a server. Information processing device 2 manages, for example, the purchase history of products purchased by a user. The user's purchase history includes information about the products purchased by the user, such as the product name, product ID to identify the product, the amount paid for the product, and the date and time of purchase. The following describes the processes performed by the information processing system S.

[0025] First, when the user performs an operation on the information terminal 1 to interact with the conversational agent, the information terminal 1 obtains the user's purchase history from the information processing device 2 (Figure 1 (1)). The information terminal 1 then has the conversational agent interact with the user about topics based on the products included in the user's purchase history (Figure 1 (2)). For example, the information terminal 1 displays an avatar corresponding to the conversational agent and the products that the conversational agent is talking about on its display, and has the conversational agent interact with the user.

[0026] When the information processing device 2 obtains dialogue information indicating the content of the conversation between the user and the dialogue agent (Figure 1, (3)), it determines the content of the reward based on at least one of the length of the conversation between the user and the dialogue agent and the content of the conversation between the user and the dialogue agent (Figure 1, (4)). The content of the reward is, for example, the content of a coupon that can be used to purchase a specified product (e.g., discount rate, amount to be deducted, etc.).

[0027] The information processing device 2 then grants the user a reward indicating the determined reward content (Figure 1, (5)). In this way, the information processing system S can provide the user with an incentive to interact with the dialogue agent. The configuration of the information processing device 2 will be described below.

[0028] [Functional configuration of the information processing device 2] Figure 2 is a schematic diagram showing the functional configuration of the information processing device 2. The information processing device 2 comprises a communication unit 21, a storage unit 22, and a control unit 23. In Figure 2, the arrows indicate the main data flow, and there may be other data flows not shown in Figure 2. In Figure 2, each functional block shows a functional unit configuration, not a hardware (device) unit configuration. Therefore, the functional blocks shown in Figure 2 may be implemented in a single device, or they may be implemented separately in multiple devices. Data exchange between functional blocks may be performed via any means, such as a data bus, network, or portable storage medium.

[0029] The communication unit 21 is a communication interface for connecting to a network and has a communication controller for receiving data from external devices.

[0030] The memory unit 22 is a large-capacity storage device such as a ROM (Read Only Memory) that stores the BIOS (Basic Input Output System) of the computer that realizes the information processing device 2, a RAM (Random Access Memory) that serves as the working area of ​​the information processing device 2, and an HDD (Hard Disk Drive) or SSD (Solid State Drive) that stores the OS (Operating System), application programs, and various information referenced when the application programs are executed.

[0031] The memory unit 22 stores information about users and information about products. User information includes, for example, a user ID to identify each user and information associated with that user's purchase history. Product information includes, for example, the name of the product, a description of the product, and information associated with consumer ratings for the product. Consumer ratings for products include, for example, reasons why consumers purchased the product and reasons why consumers did not purchase the product. The memory unit 22 also stores a rewards management database that manages the details of the rewards.

[0032] Figure 3 shows an example of the configuration of a rewards management database. In the example shown in Figure 3, the rewards management database stores the permission period, product category, eligible product, product grade, and reward details in association with each other. The permission period is the time condition under which the granting of the reward is permitted. The product category indicates the category of the product to which the reward applies. The eligible product is the product to which the reward applies. The product grade indicates, for example, the value level of the eligible product (for example, the price level of the eligible product). The product grade is expressed numerically, for example, with a higher number indicating a higher grade.

[0033] In the example shown in Figure 3, it can be confirmed that the rewards management database stores rewards that are permitted to be granted after the permission period has expired, with the degree of preferential treatment increasing with longer permission periods. Furthermore, it can be confirmed that the rewards management database stores multiple rewards that are permitted to be granted after the permission period has expired, each with a different degree of preferential treatment (multiple rewards with different product grades).

[0034] Returning to Figure 2, the control unit 23 is a processor such as the CPU (Central Processing Unit), GPU (Graphics Processing Unit), or NPU (Neural Network Processing Unit) of the information processing device 2. By executing the program stored in the memory unit 22, it functions as the user information acquisition unit 231, dialogue acquisition unit 232, analysis unit 233, decision unit 234, assignment unit 235, and output control unit 236.

[0035] The user information acquisition unit 231 acquires the user ID from the information terminal 1. For example, a user terminal (not shown) owned by the user has a dedicated application program (hereinafter referred to as "dedicated app") installed for providing information processing services, and the dedicated app has a user ID set.

[0036] In this case, first, the information terminal 1 obtains a user ID. The information terminal 1 obtains the user ID by, for example, reading a code image (e.g., a QR code (registered trademark), etc.) displayed on the user terminal. The information terminal 1 may also obtain the user ID from the user terminal via short-range wireless communication, or the user may obtain the user ID by entering it on the touch panel of the information terminal 1. Then, the user information acquisition unit 231 obtains the user ID by transmitting the user ID acquired by the information terminal 1 to the information processing device 2.

[0037] The dialogue acquisition unit 232 acquires dialogue information that shows the content of the conversation between the user and a dialogue agent that converses about topics based on products included in the user's purchase history, which are associated with the user ID acquired by the user information acquisition unit 231. For example, the dialogue agent is provided in the information terminal 1.

[0038] In this case, first, the dialogue acquisition unit 232 transmits the user's purchase history associated with the user ID acquired by the user information acquisition unit 231 to the information terminal 1, thereby allowing the dialogue agent to refer to the user's purchase history and initiate a dialogue with the user. Then, the dialogue acquisition unit 232 acquires dialogue information from the information terminal 1, including the user's utterances and the dialogue agent's output.

[0039] The conversational agent may be provided in the information processing device 2. In this case, the conversation acquisition unit 232, via the information terminal 1, causes the conversational agent to refer to the user's purchase history associated with the user ID acquired by the user information acquisition unit 231, and allows the conversational agent to interact with the user. If the user's purchase history is stored in the user terminal, the conversation acquisition unit 232 may also cause the conversational agent to refer to the user's purchase history acquired from the user terminal via the information terminal 1, and allow the conversational agent to interact with the user.

[0040] The decision unit 234 determines the content of the benefits to be granted to the user in response to the interaction between the user and the conversational agent. Specifically, the decision unit 234 determines the content of the benefits based on the length of the interaction between the user and the conversational agent.

[0041] For example, the information processing device 2 has defined benefits that are permitted to be granted on the condition that a predetermined period of interaction has elapsed. In this case, first, the analysis unit 233 measures the duration of the interaction between the user and the interaction agent when the interaction between the user and the interaction agent begins. Then, the decision unit 234 compares the duration of the interaction from the time the interaction between the user and the interaction agent began to the present time with the predetermined period, and if the interaction period is equal to or greater than the predetermined period, it determines that the benefits defined for that predetermined period will be granted to the user.

[0042] The decision unit 234 may determine that the longer the dialogue between the user and the dialogue agent, the greater the degree of preferential treatment. For example, at predetermined intervals (e.g., every second, every minute, etc.), the decision unit 234 compares the dialogue period from the time the dialogue between the user and the dialogue agent started to the current time with the permission period stored in the benefit management database. If the dialogue period is equal to or greater than the permission period, the decision unit 234 determines the benefit associated with that permission period in the benefit management database as the benefit to be granted to the user.

[0043] The decision unit 234, for example, if there are multiple permission periods in the benefits management database that are less than or equal to the dialogue period, determines the benefit associated with the longest permission period among those multiple permission periods (for example, the benefit with the greatest degree of preferential treatment) to be granted to the user. Alternatively, if there are multiple permission periods in the benefits management database that are less than or equal to the dialogue period, the decision unit 234 may determine the multiple benefit items associated with each of those permission periods to be granted to the user. In this way, the information processing device 2 can provide the user with an incentive to continue interacting with the dialogue agent.

[0044] The decision unit 234 may determine the reward content based on the content of the conversation between the user and the conversational agent. Specifically, first, the analysis unit 233 analyzes the content of the conversation between the user and the conversational agent, as indicated by the conversation information acquired by the conversation acquisition unit 232. The analysis unit 233 analyzes the content of the conversation between the user and the conversational agent using, for example, known natural language processing. The analysis unit 233 may also analyze the content of the conversation between the user and the conversational agent using the conversational agent. Then, the decision unit 234 determines the reward content based on the conversation content analyzed by the analysis unit 233.

[0045] The decision unit 234 determines the reward content, for example, when the user utters a predetermined keyword during a conversation between the user and the conversational agent. The predetermined keyword is a keyword that indicates the user may want to purchase the recommended product, and is a positive keyword such as "That's good" or "I want it." The recommended product is, for example, a promotional product from the same category as a product the user has previously purchased, among several promotional products that the store promotes, and is a promotional product recommended by the conversational agent.

[0046] For example, the information processing device 2 has defined rewards that are permitted to be granted on the condition that a predetermined keyword is spoken. In this case, the decision unit 234 determines the rewards defined for the speaking of the predetermined keyword as the rewards to be granted to the user. By doing so, the information processing device 2 can increase the likelihood that the user will purchase the recommended product.

[0047] The decision unit 234 may determine the reward content when the user makes a statement regarding their evaluation of a predetermined product. The predetermined product is, for example, a product included in the user's purchase history. Specifically, the decision unit 234 determines the reward content when the user makes a statement regarding their evaluation of a product included in the user's purchase history associated with the user ID acquired by the user information acquisition unit 231 during a conversation between the user and the dialogue agent.

[0048] For example, the information processing device 2 has defined rewards that are permitted to be granted on the condition that an evaluation of a specific product is expressed. In this case, if the content expressed by the user after the dialogue agent has heard the user's opinion on a product included in the user's purchase history is a sentence, the decision unit 234 determines that the rewards to be granted to the user are those defined for evaluations of products included in the user's purchase history.

[0049] On the other hand, the decision unit 234 does not determine the reward content if the content spoken by the user after the dialogue agent has heard the user's opinion on the products included in the user's purchase history is not a sentence (for example, if it is an interjection, exclamation, or other word such as "yes," "no," or "that's right"). In this way, the information processing device 2 can give preferential treatment to users who have provided information that is useful as information used for product marketing.

[0050] The decision unit 234 may determine the content of the reward based on the rarity of the reason given by the user for purchasing the products included in the user's purchase history, as an evaluation of the products included in the user's purchase history. For example, the information processing device 2 has defined rewards that are permitted to be granted on the condition that the reason for purchasing a certain product is stated.

[0051] In this case, if the user states the reason for purchasing an item included in the purchase history associated with the user ID acquired by the user information acquisition unit 231 during the interaction between the user and the dialogue agent, the decision unit 234 determines the reward content according to the amount of information stored in the product information of the storage unit 22 that is related to the reason the user stated for purchasing the item. The decision unit 234 determines the reward content according to the amount of information stored in the product information of the storage unit 22 that is related to the reason the user stated for purchasing the item, for example, by performing the following three steps.

[0052] As the first step, the decision unit 234 calculates the similarity between the stored vector data, which is obtained by converting each reason for purchasing the target product into a vector, and the spoken vector data, which is obtained by converting each reason for purchasing the product stated by the user into a vector, for each reason included in the product information stored in the storage unit 22. The decision unit 234 calculates the similarity between the two vector data using, for example, a known method such as cosine similarity.

[0053] In the second step, the determination unit 234 identifies memory vector data whose similarity to the speech vector data is within a predetermined similarity threshold. The predetermined similarity threshold is a value determined to determine whether two vector data are similar or not.

[0054] In the third step, the decision unit 234 determines the reward content to be granted to the user based on the reward content defined for the reasons for purchasing the product included in the user's purchase history, if the number of reasons for purchasing the product corresponding to the identified memory vector data is less than or equal to the first quantity threshold. The first quantity threshold is a value determined to determine whether the degree of rarity of the reasons for purchasing the product stated by the user is high or low.

[0055] On the other hand, the decision unit 234 does not determine the content of the benefits to be given to the user if the number of reasons for purchasing the product corresponding to the identified memory vector data, which is the number of pieces of information contained in the product information of the memory unit 22, is not less than or equal to the first threshold. In this way, the information processing device 2 can give preferential treatment to users who have provided information that is useful as information used for product marketing.

[0056] The specified product may be a recommended product suggested by the conversational agent. In this case, the decision unit 234 may, as an evaluation of the recommended product suggested by the conversational agent, determine the content of the reward based on the rarity of the reason given by the user for not purchasing the recommended product suggested by the conversational agent. For example, the information processing device 2 has defined rewards that are permitted to be granted on the condition that a reason for not purchasing the specified product is stated.

[0057] In this case, if the user states a reason for not purchasing the recommended product suggested by the dialogue agent, the decision unit 234 determines the reward content according to the amount of information stored in the product information of the memory unit 22 that relates to the reason the user stated for not purchasing the product. The decision unit 234 determines the reward content according to the amount of information stored that relates to the reason the user stated for not purchasing the product, for example, by performing the same process as the process that determines the reward content according to the amount of information stored that relates to the reason the user stated for purchasing the product.

[0058] Furthermore, the decision unit 234 may, as an evaluation of the recommended product suggested by the conversational agent, determine the content of the reward based on the rarity of the reason given by the user for purchasing the recommended product. In this way, the information processing device 2 can give preferential treatment to users who provide information that is useful for marketing the product.

[0059] The decision unit 234 may determine the reward content based on the length of the conversation between the user and the dialogue agent and the content of the conversation between the user and the dialogue agent. Specifically, when the decision unit 234 determines the reward content based on the length of the conversation between the user and the dialogue agent, it determines a reward content that is more favorable if the user makes a predetermined statement during the conversation between the user and the dialogue agent. The predetermined statement may be, for example, a predetermined keyword, the reason for purchasing a product included in the user's purchase history, the reason for not purchasing a recommended product suggested by the dialogue agent, or the reason for purchasing a recommended product suggested by the dialogue agent.

[0060] For example, if the user makes a predetermined statement during a conversation between the user and the dialogue agent, the decision unit 234 determines that the highest-grade reward among multiple rewards associated with an permission period that is less than or equal to the conversation period in the reward management database will be granted to the user. If the user does not make a predetermined statement during a conversation between the user and the dialogue agent, the decision unit 234 determines that the lowest-grade reward among multiple rewards associated with an permission period that is less than or equal to the conversation period in the reward management database will be granted to the user.

[0061] In this way, the information processing device 2 can give preferential treatment to users who provide information useful for marketing products. Furthermore, if the user does not make a predetermined statement during the dialogue between the user and the dialogue agent, the decision unit 234 may determine, in the benefits management database, to be the benefit with the highest product grade among multiple benefit options associated with a permission period that is less than or equal to the dialogue period, as the benefit to be granted to the user.

[0062] The decision unit 234 may determine the reward content based on the user's state while interacting with the dialogue agent. Specifically, the information processing device 2 determines the reward content based on the user's state while interacting with the dialogue agent by performing the following three steps.

[0063] As the first step, the dialogue acquisition unit 232 acquires captured images of the user during a conversation between the user and the dialogue agent. Specifically, the dialogue acquisition unit 232 acquires captured images from the information terminal 1 that are captured by the camera of the information terminal 1 while the user and the dialogue agent are having a conversation.

[0064] In the second step, the analysis unit 233 analyzes, based on the captured image, whether the user took a predetermined attitude after the conversational agent recommended a product. The predetermined attitude is one that indicates the user may be interested in purchasing the recommended product, and may include, for example, a hesitant attitude, a happy attitude, a smiling attitude, an exaggerated reaction, an attitude of consulting with those around him, or an attitude of continuing to look at the display showing the recommended product recommended by the conversational agent for a predetermined period of time. The analysis unit 233 can analyze whether the user took a predetermined attitude using, for example, known subject recognition technology.

[0065] In the third step, the decision unit 234 determines the reward content when the user takes a predetermined action. For example, the information processing device 2 has defined reward content that is permitted to be granted on the condition that a predetermined action is taken. In this case, when the user takes the predetermined action, the decision unit 234 determines the reward content defined for that predetermined action as the reward content to be granted to the user. In this way, the information processing device 2 can increase the probability that the user will purchase the recommended product.

[0066] The decision unit 234 may determine the reward content based on the length of the conversation between the user and the dialogue agent and a predetermined attitude taken by the user. Specifically, when the decision unit 234 determines the reward content based on the length of the conversation between the user and the dialogue agent, it determines a reward content that is more favorable if the user takes a predetermined attitude.

[0067] The decision unit 234, for example, if the user takes a predetermined action, determines that the highest-grade reward among multiple rewards associated with an authorization period that is less than or equal to the dialogue period in the reward management database will be granted to the user. If the user does not take a predetermined action, the decision unit 234 determines that the lowest-grade reward among multiple rewards associated with an authorization period that is less than or equal to the dialogue period in the reward management database will be granted to the user.

[0068] In this way, the information processing device 2 can increase the likelihood that the user will purchase the recommended product. If the user does not take a predetermined action, the decision unit 234 may determine the reward to be granted to the user to be a reward of a higher product grade from among the multiple rewards associated with an authorization period that is less than or equal to the dialogue period in the reward management database.

[0069] The decision unit 234 may determine a more favorable reward if the user takes a predetermined action after the conversational agent has presented the price of the recommended product. In this case, the decision unit 234 does not determine a more favorable reward if the user takes a predetermined action before the conversational agent presents the price of the recommended product, but determines a more favorable reward if the user takes a predetermined action after the conversational agent has presented the price of the recommended product. By doing so, the information processing device 2 can increase the likelihood that the user will purchase the recommended product.

[0070] The decision unit 234 may determine the reward content based on the duration of the conversation between the user and the conversational agent, the content of the conversation between the user and the conversational agent, and the user's attitude. Specifically, the decision unit 234 determines the reward content based on index values ​​obtained by converting the duration of the conversation between the user and the conversational agent, the content of the conversation between the user and the conversational agent, and the user's attitude into numerical values.

[0071] For example, the information processing device 2 has a defined numerical value for each unit period of the dialogue (e.g., 1 second, 30 seconds, 1 minute, etc.). The information processing device 2 also has defined numerical values ​​that are added when a specific statement is made and when a specific attitude is taken. Furthermore, the reward management database stores numerical values ​​for each type of reward that permit the granting of that particular reward.

[0072] In this case, first, the decision unit 234 calculates an index value by accumulating numerical values ​​according to the elapsed time, whether or not the user makes a predetermined statement, and whether or not the user exhibits a certain attitude during the period from the start to the end of the conversation between the user and the dialogue agent. Then, the decision unit 234 determines the benefit content to be granted to the user as a benefit content that is less than or equal to the index value calculated in the benefit management database and is associated with the numerical value closest to the index value.

[0073] The decision unit 234 may determine the benefits of a specific product based on the content of the conversation between the user and the conversational agent. The decision unit 234 determines the benefits of a specific product based on the content of the conversation between the user and the conversational agent by performing, for example, the following two steps.

[0074] As the first step, the decision unit 234 selects a specific product from among multiple promotional products based on the content of the conversation between the user and the conversational agent. Specifically, the decision unit 234 selects a product from among multiple promotional products that is related to a product included in the user's purchase history associated with the user ID acquired by the user information acquisition unit 231, and that was recommended by the conversational agent during the conversation between the user and the conversational agent. Products related to a product included in the user's purchase history include, for example, promotional products of the same genre as the product included in the user's purchase history, or the same promotional product as the product included in the user's purchase history.

[0075] For example, if the conversational agent recommends a product and the user utters a predetermined keyword (for example, a positive keyword for the recommended product) in relation to that product, the decision unit 234 selects the product recommended by the conversational agent immediately before the user uttered the predetermined keyword as the specific product.

[0076] In the second step, the decision unit 234 determines the benefits offered for purchasing the selected recommended product. In this way, the information processing device 2 can increase the likelihood that the user will purchase the recommended product.

[0077] The granting unit 235 grants the user a benefit that indicates the benefit content determined by the decision unit 234. The granting unit 235 grants the user a benefit, for example, by transmitting benefit information indicating the benefit content to the user's terminal.

[0078] The granting unit 235 may output the reward information to the information terminal 1. The information terminal 1 may, for example, display a code image (e.g., a QR code (registered trademark), etc.) on its display to grant the reward to the user, and the user may grant the reward by reading the code image using a user terminal. The information terminal 1 may also print the reward.

[0079] The information processing device 2 may present the details of the benefits the user can receive during the interaction between the user and the dialogue agent. Specifically, the output control unit 236 causes the information terminal 1 to output the details of the benefits stored in the benefits management database, associated with the permission period, each time the interaction period between the user and the dialogue agent becomes longer than the permission period stored in the benefits management database.

[0080] For example, first, the output control unit 236 transmits benefit information indicating the benefit content stored in the benefit management database in association with the permission period to the information terminal 1 when the interaction period between the user and the dialogue agent has elapsed. The information terminal 1 then displays the benefit content indicated by the benefit information obtained from the information processing device 2 on its display. In this way, the information processing device 2 can make the user aware of what benefits they can receive.

[0081] The output control unit 236 may present information regarding benefits that the user has not yet earned. Specifically, the output control unit 236 outputs to the information terminal 1, as information regarding benefits that the user has not yet earned, the benefit details stored in the benefit management database in association with the period of non-earning, and the difference between the period of interaction between the user and the dialogue agent and the period of non-earning. The period of non-earning is a permit period that is longer than the period of interaction between the user and the dialogue agent.

[0082] Figure 4 is a schematic representation of the display screen D shown on the display of information terminal 1. In the example shown in Figure 4, information is displayed in three regions R on display screen D. Region R1 is the region where the avatar corresponding to the conversational agent is displayed. Region R2 is the region where information about the recommended product recommended by the conversational agent is displayed (e.g., an image of the recommended product, a description of the recommended product, etc.). Region R3 is the region where the benefits corresponding to the recommended product are displayed.

[0083] In the example shown in Figure 4, area R3 indicates that the dialogue period is between 5 and 10 minutes, and it can be confirmed that a 5% off coupon can be obtained after 5 minutes have elapsed, but coupons for 10% off or more have not yet been obtained. In this way, the information processing device 2 can make the user aware of what benefits can be obtained by continuing to interact with the dialogue agent.

[0084] The output control unit 236 may present information about the most advantageous of several advantages that the user has not yet acquired. Specifically, the output control unit 236 causes the information terminal 1 to output at least the most advantageous advantage from among several advantages stored in the advantage management database, which have an advantage period longer than the interaction period between the user and the conversation agent and are associated with the most recent advantage period (the advantage period closest to the interaction period).

[0085] In this case, the output control unit 236 may output to the information terminal 1 the conditions for the user to obtain the most advantageous benefit (for example, reasons for not purchasing the recommended product). By doing so, the information processing device 2 can more easily obtain information from the user that is useful for product marketing.

[0086] [Processing by Information Processing Device 2] Next, we will explain the processing flow executed by the information processing system S. Figure 5 is a sequence diagram showing the processing flow executed by the information processing system S. In the example shown in Figure 5, we will explain the processing flow when a dialogue agent is provided on the information terminal 1. This process starts when the user information acquisition unit 231 acquires a user ID from the information terminal 1 (S1).

[0087] The dialogue acquisition unit 232 transmits the user's purchase history associated with the user ID acquired by the user information acquisition unit 231 to the information terminal 1 (S2). The information terminal 1 allows the dialogue agent to refer to the user's purchase history acquired from the information processing device 2, and has the dialogue agent interact with the user (S3).

[0088] The dialogue acquisition unit 232 acquires dialogue information indicating the content of the conversation between the user and a dialogue agent that converses about topics based on the user's purchase history (S4). The decision unit 234 determines the content of the reward based on at least one of the length of the conversation between the user and the dialogue agent and the content of the conversation between the user and the dialogue agent (S5).

[0089] The awarding unit 235 transmits the reward content determined by the determination unit 234 to the information terminal 1 (S6). The information terminal 1 then outputs the reward content that it has obtained from the information processing device 2 (S7).

[0090] [Effects of this embodiment] As explained above, the information processing device 2 determines the content of the reward based on at least one of the following: the length of the conversation between the user and the conversational agent, which converses with the user about topics related to products included in the user's purchase history, and the content of the conversation between the user and the conversational agent. The information processing device 2 then grants the user a reward corresponding to the determined reward content. In this way, the information processing device 2 can provide the user with an incentive to converse with the conversational agent.

[0091] Furthermore, this invention will make it possible to contribute to Goal 9 of the United Nations-led Sustainable Development Goals (SDGs), "Build resilient infrastructure, promote inclusive and sustainable industrialization and foster innovation."

[0092] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of its gist. For example, all or part of the apparatus can be configured by functionally or physically distributing and integrating in any unit. Furthermore, new embodiments resulting from any combination of multiple embodiments are also included in the embodiments of the present invention. The effects of the new embodiments resulting from the combinations are combined with the effects of the original embodiments. [Explanation of symbols]

[0093] 1. Information terminal 2. Information Processing Device 21 Communications Department 22 Memory section 23 Control Unit 231 User Information Acquisition Unit 232 Dialogue Acquisition Unit 233 Analysis Department 234 Decision Section 235 Assignment section 236 Output Control Unit S Information Processing System

Claims

1. A storage unit that stores a user ID (identification) for identifying a user and the purchase history of the user in association with the purchase of the product, A user information acquisition unit that obtains the user ID from the terminal, A dialogue acquisition unit acquires the content of a conversation between the user and a dialogue agent that converses about topics related to the products included in the purchase history associated with the user ID acquired by the user information acquisition unit, A determination unit that determines the content of the reward based on at least one of the length of the conversation between the user and the conversational agent and the content of the conversation, A granting unit grants the user the benefit that the granting unit has determined, the benefit content of which is determined by the granting unit. An information processing device having

2. The decision unit determines the type of benefit that is more advantageous the longer the conversation between the user and the dialogue agent. The information processing apparatus according to claim 1.

3. The decision unit selects a recommended product from among a plurality of predetermined products that is related to the product included in the purchase history associated with the user ID acquired by the user information acquisition unit and that was recommended by the dialogue agent in the dialogue between the user and the dialogue agent, and determines the content of the benefit that will be preferential for purchasing the selected recommended product. The information processing apparatus according to claim 1.

4. The decision unit determines the most favorable reward when the user utters a predetermined keyword during a conversation between the user and the dialogue agent that indicates the user may wish to purchase the recommended product. The information processing apparatus according to claim 3.

5. The dialogue acquisition unit acquires captured images of the user during the dialogue between the user and the dialogue agent. The information processing device further includes an analysis unit that analyzes, based on the captured image, whether the user took a predetermined attitude indicating that they may want to purchase the recommended product after the dialogue agent recommended the recommended product. The decision unit determines the type of benefit that is more favorable to the user if the user takes the predetermined attitude. The information processing apparatus according to claim 3.

6. The decision unit determines the most favorable type of benefit if the conversational agent takes the predetermined attitude after presenting the price of the recommended product. The information processing apparatus according to claim 5.

7. The decision unit determines the most favorable reward when the user makes a statement regarding their evaluation of the product included in the purchase history associated with the user ID acquired by the user information acquisition unit during a conversation between the user and the dialogue agent, or of a recommended product suggested by the dialogue agent. The information processing apparatus according to claim 1.

8. The memory unit further stores, for each specified product, the reason why a consumer does not purchase that specified product. The decision unit, when the user states a reason for not purchasing a recommended product suggested by the dialogue agent during a conversation between the user and the dialogue agent, determines a more favorable reward based on the amount of information stored in the memory unit regarding the user's stated reason for not purchasing the recommended product. The information processing apparatus according to claim 1.

9. The memory unit further stores, for each predetermined product, the reason why the consumer purchased that predetermined product. The determination unit, when the user states the reason for purchasing the product included in the purchase history associated with the user ID acquired by the user information acquisition unit during a conversation between the user and the dialogue agent, determines the most favorable reward content in accordance with the amount of information stored in the storage unit regarding the reason for purchasing the product stated by the user. The information processing apparatus according to claim 1.

10. The memory unit further stores, for each predetermined benefit, a predetermined period and a predetermined benefit that is permitted to be granted after the predetermined period has elapsed, with the degree of preferential treatment increasing the longer the predetermined period. The information processing device further includes an output control unit that, each time the duration of the interaction between the user and the dialogue agent exceeds the predetermined period stored in the storage unit, outputs the predetermined benefit content stored in the storage unit in association with that predetermined period to the terminal. The information processing apparatus according to claim 1.

11. The output control unit further causes the terminal to output the predetermined benefit content stored in the storage unit in association with the unfulfilled period, which is a predetermined period longer than the duration of the dialogue between the user and the dialogue agent, and the difference between the duration of the dialogue between the user and the dialogue agent and the unfulfilled period. The information processing apparatus according to claim 10.

12. The memory unit further stores, at predetermined intervals, a predetermined period and a plurality of predetermined benefits, each of which has a different degree of preferential treatment, that are permitted to be granted when the predetermined period has elapsed. The information processing device further includes an output control unit that causes the terminal to output to the terminal the predetermined benefit content that has the highest degree of preferential treatment among a plurality of predetermined benefit content stored in the storage unit in association with the most recent predetermined period, which is longer than the period of dialogue between the user and the dialogue agent. The information processing apparatus according to claim 1.

13. A computer having a storage unit that stores a user ID for identifying a user and the purchase history of the product purchased by the said user in association with each other performs the following: The steps include obtaining the user ID from the terminal, The steps include obtaining the content of a conversation between the user and a conversational agent that engages in a conversation about a topic based on the product included in the purchase history associated with the acquired user ID, A step of determining the reward content based on at least one of the length of the conversation between the user and the conversational agent and the content of the conversation, A step of granting the user a benefit that indicates the determined benefit content, An information processing method having

14. A computer having a storage unit that stores a user ID for identifying a user and the purchase history of the product purchased by the said user in association with each other, A user information acquisition unit that obtains the user ID from the terminal. A dialogue unit that acquires the content of a conversation between the user and a dialogue agent that converses about topics related to the products included in the purchase history associated with the user ID acquired by the user information acquisition unit. A determination unit that determines the content of the reward based on at least one of the length of the conversation between the user and the conversational agent and the content of the conversation, A granting unit grants the user the benefit that the granting unit has determined, which represents the content of the benefit. A program designed to function as such.

Images