JP7122286B2 - Decision device, decision method and decision program - Google Patents

Description

The present invention relates to a determination device, a determination method, and a determination program.

2. Description of the Related Art In recent years, electronic commerce technology has been known, in which goods and services are traded via the Internet or the like. In such electronic commerce, a technique is known for automatically changing the price of a transaction object according to the number of purchases of the transaction object.

Retable 2007/136011

However, it may not be possible to say that an appropriate price is set with the conventional technology described above.

For example, in the conventional technology described above, the price of the transaction target is simply changed automatically according to the number of purchases, etc., so a price that motivates the user to make an appropriate purchase behavior is set. I can't say I do.

This application was made in view of the above, and aims at setting a more appropriate price.

A determination device according to the present application includes an acquisition unit that acquires a user's emotion that is related to content provided to the user, and the user's emotion acquired by the acquisition unit. and a determination unit that determines the amount of cost for providing the content based on the content.

According to one aspect of the embodiment, there is an effect that a more appropriate price can be set.

FIG. 1 is a diagram illustrating an example of determination processing according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of a determination device according to the embodiment; 3 is a diagram illustrating an example of a price information storage unit according to the embodiment; FIG. FIG. 4 is a flow chart showing a decision processing procedure by the decision device according to the embodiment. FIG. 5 is a diagram illustrating an example of a hardware configuration;

Embodiments (hereinafter referred to as "embodiments") for implementing the determination device, determination method, and determination program according to the present application will be described in detail below with reference to the drawings. Note that the determination device, determination method, and determination program according to the present application are not limited to this embodiment. Further, each embodiment can be appropriately combined within a range that does not contradict the processing contents. Further, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

[1. Decision processing]
First, an example of determination processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of determination processing according to the embodiment. In the example of FIG. 1, the determination process is performed by the determination system 1 according to the embodiment.

As shown in FIG. 1 , the decision system 1 includes a user device 10 and a decision device 100 . Although not shown in FIG. 1 , the decision system 1 may include multiple user devices 10 and multiple decision devices 100 .

The user device 10 is an information processing device used by a user. The user device 10 may be any type of information processing device, including smart phones, desktop PCs (Personal Computers), notebook PCs, and tablet PCs.

In the example of FIG. 1, user device 10 is a client device that requests content such as a blog, web page, application page, social media, or the like.

The determination device 100 is an information processing device that determines the price of a transaction object such as a product or service. The decision making device 100 may be any type of information processing device, including a server. Although not shown in FIG. 1, the determination device 100 communicates with the user device 10 by wire or wirelessly via a network (for example, the Internet).

In the example of FIG. 1, the determination device 100 is a server device that determines prices displayed within sales content. Sales content is, for example, a product purchase page of a website or an application. In the example of FIG. 1, product links to sales content are included in content such as blogs, web pages, application pages, social media, and the like. The determination device 100 provides sales content to the user device 10 when the product link is selected.

By the way, conventionally, various pricing algorithms are used to determine the price of goods and services. For example, price determination algorithms such as dynamic pricing are used to determine prices of products on EC (Electronic Commerce) sites and EC applications. In dynamic pricing, product prices are generally determined dynamically according to "customer demand". In other words, in general dynamic pricing, the price of a product is determined based on "how much a customer will purchase the product."

However, customers do not always make rational purchases based on the prices of goods and services. For example, a user (that is, a customer) of an EC site or an EC application may be emotionally induced and may not perform appropriate purchasing behavior.

For example, the user's emotion may be a negative emotion such as nervousness or upset. In this case, the user may rush to purchase the product even though the user is hesitating whether to purchase the product. When a user rushes to buy a product, the seller of the product temporarily makes a profit. However, the user may think that the user should have thought twice about purchasing the product. Furthermore, the user may regret buying the product in a hurry. In such cases, the user may not purchase goods from this seller again due to the unpleasant purchasing experience. Thus, if the user's emotions are not taken into account when selling products, the product seller may not be able to maintain a continuous relationship with the user.

Accordingly, in the exemplary embodiment of FIG. 1, the decision device 100 performs the decision process described below in order to achieve ongoing relationship maintenance with the user.

In one example of the decision processing described below, the decision device 100 uses a machine learning model that predicts the user's emotion from the user's behavior to estimate the user's emotion when the product link is selected. As described below, a machine learning model that predicts a user's emotions can be generated, for example, based on learning data collected from crowdsourced workers. The decision device 100 then dynamically decides the price displayed in the sales content according to the estimated user's emotion. In this way, the determination device 100 can set a price that prompts the user to take appropriate purchasing behavior for the product of the sales content.

First, the determining device 100 distributes content to the user device 10 (step S11).

For example, the decision device 100 provides the user device 10 with content such as blogs, web pages, application pages, social media, and the like. As noted above, the content includes product links to sales content. In the example of FIG. 1, the content includes control information that causes the user device 10 to transmit user behavior information. Such control information is written in a script language such as JavaScript (registered trademark), for example.

Next, the determining device 100 acquires user behavior information from the user device 10 (step S12).

In the example of FIG. 1, as described above, the content includes control information that causes the user device 10 to transmit user behavior information. Therefore, when the content is distributed to the user device 10, the user device 10 transmits the user's action information to the decision device 100 according to the control information included in the content. As a result, the decision device 100 can receive the user's behavior information via the content distributed to the user device 10 .

The acquired action information indicates, for example, various logs such as click history, browsed content history, scroll history, line-of-sight history, and the like. Note that the line-of-sight history can be collected by, for example, a line-of-sight sensor mounted on the user device 10 . For example, the user's line of sight can be obtained through AR (Augmented Reality) content.

Next, the determination device 100 receives selection of a product link (step S13).

For example, the decision device 100 accepts selection of product links displayed in content such as blogs, web pages, application pages, social media, and the like. For illustrative purposes, in the example of FIG. 1, assume that the user has selected a product link to sales content for the product "mineral water BW1". In this example, the determining device 100 receives from the user device 10 a transmission request for sales content related to the product “mineral water BW1”.

Next, the determining device 100 estimates the user's emotion using the acquired user behavior information (step S14).

For example, the decision device 100 estimates the user's emotion using a machine learning model that predicts the user's emotion from the user's behavior. More specifically, the determining device 100 inputs the obtained user behavior information into a machine learning model that predicts the user's emotions during the period in which the user takes one or more behaviors, thereby determining the product link. Estimates the user's emotion when is selected.

Regarding the machine learning model that predicts the user's emotion described above, for example, the decision device 100 uses a sensing device such as a wearable device to estimate the physiological reactions of crowdsourcing workers (for example, changes in heart rate and body temperature). identify. The decision device 100 then estimates the worker's emotion during the period in which the worker performed one or more actions based on the identified physiological response. The one or more behaviors are, for example, behaviors such as clicking, viewing content, scrolling, eye movements, and the like. In this way, the determining device 100 can generate learning data for learning the correspondence between one or more such actions and user's emotions. As a result, the decision making device 100 can generate from the generated learning data a machine learning model that predicts the user's emotions during the period in which the user takes one or more actions. A technique for generating a machine learning model that predicts a user's emotions is described below in connection with FIG.

The decision device 100 then decides the price to be displayed in the sales content based on the estimated user's emotion (step S15).

If the user's estimated emotion is a positive emotion such as pleasure, the user may have high expectations for the product. Such users are likely to be potential customers. In this regard, potential customers are often interested in the price of goods. Therefore, the decision device 100 lowers the price of the product in order to meet the user's expectations for the price of the product.

For example, the determining device 100 determines the price displayed in the sales content such that the price when the user's estimated emotion is positive emotion such as pleasure is lower than a predetermined price. For example, the decision device 100 displays in the sales content such that the price when the estimated user's emotion is a positive emotion is lower than the price when the estimated user's emotion is a neutral emotion. determine the price to be paid. Note that the neutral emotion is, for example, an emotion such as calmness.

The predetermined price mentioned above may be determined using a price determination algorithm such as dynamic pricing. For example, the predetermined price may be determined dynamically according to user demand. Also, for example, the predetermined price may be dynamically determined according to the user's purchase intention.

On the other hand, if the user's estimated emotion is a negative emotion such as nervousness or upset, the user may hesitate to purchase the product as described above, and may purchase the product in a hurry. Also, if the user's estimated emotion is a negative emotion such as stress, the user may make an impulse purchase. In this regard, if the price of the product is high, the user may hesitate whether to purchase the product and, as a result, may not purchase the product. Therefore, the decision device 100 raises the price of the product in order to encourage the user to take appropriate purchasing behavior.

For example, the determining device 100 determines the price displayed in the sales content so that the price when the user's estimated emotion is a negative emotion such as nervousness, upset, or stress is higher than a predetermined price. do. For example, the decision device 100 displays in the sales content such that the price when the estimated user's emotion is negative emotion is higher than the price when the estimated user's emotion is neutral emotion. determine the price to be paid.

In the example of FIG. 1, when the user's estimated emotion is a favorable emotion, the determination device 100 selects a price of "21000 yen" lower than the current price of "2500 yen" of the product "mineral water BW1". , is determined as the price of the product "mineral water BW1". On the other hand, if the user's estimated emotion is a negative emotion, the determination device 100 sets the price "2800 yen" higher than the current price "2500 yen" of the product "mineral water BW1" to the product "mineral water BW1". It is determined as the price of "water BW1".

Regarding the degree of price change, the decision making device 100 may decide the price displayed in the sales content based on arousal. In other words, the decision making device 100 may decide the price displayed in the sales content based on "how strong the emotion was activated."

For example, the determining device 100 determines that the price when the estimated user's emotion is a very positive emotion (e.g., emotion "happiness") is the price when the estimated user's emotion is a positive emotion (e.g., emotion "relax"). ), the price displayed in the sale content may be determined to be higher than the price if . On the other hand, for example, the determining device 100 determines that the price when the estimated user's emotion is a very negative emotion (eg, emotion "upset") is reduced to the price when the estimated user's emotion is a negative emotion (eg, emotion "depression"). ”), the price displayed in the sale content may be determined to be higher than the price if .

Regarding the display mode of sales content, the determination device 100 may determine a component corresponding to a content item for receiving a product purchase request based on the estimated user's emotion.

In the example of FIG. 1, when the user's estimated emotion is a favorable emotion, the determination device 100 sets the text "purchase" as the purchase button text for purchasing the product "mineral water BW1". decide. On the other hand, if the user's estimated emotion is a negative emotion, the decision device 100 sets the text "next week sale (buy now)" as the purchase button text for purchasing the product "mineral water BW1". decide. In this way, when the user's estimated emotion is a negative emotion, the determination device 100 may make it difficult for the user to purchase the product.

It should be noted that in the exemplary embodiment of FIG. 1, the decision device 100 decides the price displayed in the sales content based on the estimated user's emotion, but is not limited to this. . In other embodiments, the determination device 100 may determine the price displayed within the product link based on the user's emotions when the product link is displayed.

For example, the decision device 100 inputs the user's behavior information received via the content into the above-described machine learning model that predicts the user's emotion, thereby predicting the user's emotion when the user browses the content. can be estimated. When the determining device 100 receives from the user device 10 a transmission request for other content including a product link, the determining device 100 displays the product link based on the estimated user emotion. You can decide the price. For example, the determination device 100 may determine the price displayed in the product link so that the price when the estimated user's emotion is a positive emotion such as pleasure is lower than a predetermined price. . Also, for example, the determining device 100 may set the price displayed in the product link so that the price when the user's estimated emotion is a negative emotion such as nervousness, upset, or stress is higher than a predetermined price. may be determined.

After that, the determining device 100 provides sales content to the user device 10 as a response corresponding to the selection of the product link (step S16).

In the example of FIG. 1, the provided sales content (not shown) shows prices determined based on the user's emotions as described above. Additionally, the provided sales content shows purchase buttons determined based on the user's emotions as described above.

As described above, the determination device 100 according to the embodiment uses user behavior information and a machine learning model that predicts the user's emotions based on the user's behavior, and when a product link to sales content is selected, Estimate the user's emotion. The decision device 100 then dynamically decides the price displayed in the sales content according to the estimated user's emotion. As a result, the determination device 100 can achieve overall optimization of product sales.

For example, in general dynamic pricing, product prices are dynamically determined according to "user demand" as described above. In other words, in demand-based dynamic pricing, the price of a product is determined based on "how much a customer will buy the product" as described above. This means that demand-driven dynamic pricing optimizes the seller's profit at the point of sale.

On the other hand, in the exemplary embodiment of FIG. 1, the prices displayed within the sales content are dynamically determined according to "user sentiment" as described above. In other words, in emotional dynamic pricing, the price of a product is determined based on whether the customer is happy with the purchase of the product. This means that emotional dynamic pricing optimizes the customer experience. As described above, the decision device 100 can dynamically determine prices displayed within sales content based on user sentiment as well as user demand. This allows the decision making device 100 to optimize the seller's profits and increase sales opportunities. Therefore, the determining device 100 can achieve overall optimization of product sales on EC sites and EC applications. The determination device 100 that implements such determination processing will be described in detail below.

[2. Configuration of Decision Device]
Next, a configuration example of the determination device 100 according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of the determination device 100 according to the embodiment. As shown in FIG. 2 , the determination device 100 has a communication section 110 , a storage section 120 and a control section 130 . The deciding device 100 has an input unit (for example, keyboard, mouse, etc.) for receiving various operations from an administrator or the like who uses the deciding device 100, and a display unit (liquid crystal display, etc.) for displaying various information. may

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information to and from the user device 10 via the network.

(storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2 , storage unit 120 has content information storage unit 121 .

(Content information storage unit 121)
FIG. 3 is a diagram showing an example of the content information storage unit 121 according to the embodiment. The content information storage unit 121 stores content information of content. For example, the content information storage unit 121 stores content information of content related to a predetermined transaction target.

The content information storage unit 121 stores content information received by the receiving unit 131, for example. In the example of FIG. 3, the content information storage unit 121 stores "content information" for each "content ID". As an example, the 'content information' includes the item 'merchandise', the item 'emotion' and the item 'component'.

"Content ID" indicates an identifier for identifying content. "Product" indicates the product associated with the content. "Emotion" indicates the emotion associated with the content. "Component" indicates a component included in the content. "Component" includes the item "Text". "Text" indicates the text in the component.

For example, FIG. 3 shows that the content identified by the content ID “C11” is associated with the product “mineral water BW1”.

Also, for example, FIG. 3 shows that the content identified by the content ID “C11” is associated with the feeling “favorable feeling”.

Also, for example, FIG. 3 shows that the text in the component included in the content identified by the content ID “C11” is the text “Purchase”.

(control unit 130)
The control unit 130 is a controller, for example, by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), various programs (decision program) stored in the storage device inside the decision device 100 (equivalent to one example) is implemented by executing the RAM or the like as a work area. Also, the control unit 130 is a controller, and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 130 includes a receiving unit 131, an acquiring unit 132, a determining unit 133, a first providing unit 134, and a second providing unit 135, and performs information processing described below. realize or perform the function or action of Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 2, and may be another configuration as long as it performs the information processing described later.

(Receiver 131)
The receiving unit 131 receives content information of content. For example, the receiving unit 131 receives content information from a predetermined information processing device. For example, the receiving unit 131 receives content information from devices of entities (eg, users, companies) related to the determining device 100 . The receiving section 131 may store the received content information in the content information storage section 121 .

The receiving unit 131 may receive content information from the user of the determining device 100 via the user interface. The receiving section 131 may store the received content information in the content information storage section 121 .

The receiving unit 131 receives a content request from the user device 10 . For example, the receiving unit 131 receives from the user device 10 a request for acquiring content related to a predetermined transaction target. Also, for example, the receiving unit 131 receives from the user device 10 a request for acquiring sales content that is displayed triggered by selection of content related to a predetermined transaction target.

In one example, the receiving unit 131 receives from the user device 10 a request to acquire content such as blogs, web pages, application pages, social media, or product links included in such content.

In one example, the reception unit 131 receives selection of a product link.

For example, the receiving unit 131 receives selection of product links displayed in content such as blogs, web pages, application pages, and social media. When the user selects a product link to sales content related to products, the receiving unit 131 receives a transmission request for sales content related to products from the user device 10 .

The content related to the above-mentioned predetermined trading object is, for example, content such as blogs, web pages, application pages, social media, or product links included in such content, but is not limited thereto. The content related to the above-mentioned predetermined transaction target may be content related to electronic markets such as EC sites and EC applications. Contents related to electronic markets are, for example, contents of online shopping, auctions, and the like.

The predetermined transaction object described above may be a product or a service (for example, a hotel reservation). Certain trading objects may be sold in electronic marketplaces (eg, online shopping). Also, a given trading object may be put up for sale in an electronic marketplace (eg, an auction).

The receiving unit 131 receives behavior information of a user (for example, user). For example, the receiving unit 131 receives user behavior information via content distributed by the first providing unit 134 . The receiving unit 131 may store the received behavior information in a behavior information storage unit (not shown), which is a predetermined storage area within the storage unit 120 .

The content delivered by the first providing unit 134 is, for example, the content related to the above-mentioned predetermined trading object. The contents delivered by the first providing unit 134 include search, portal, shopping, auction, news, finance, travel, restaurant introduction, sports, television, video, game, map, route information, cooking, real estate, automobile, blog. , marriage, comics, fortune-telling, local information, and the like.

In one example, the content distributed by the first providing unit 134 is content such as blogs, web pages, application pages, social media, and the like. In this example, the content includes product links to sales content. Sales content is, for example, a product purchase page of a website or an application.

In one example, the content distributed by the first providing unit 134 includes control information that causes the user device 10 to transmit user behavior information. Therefore, when this content is distributed to the user device 10, the user device 10 transmits user behavior information to the decision device 100 according to the control information included in this content. As a result, the receiving unit 131 can receive the user's behavior information via the content distributed to the user device 10 .

(Acquisition unit 132)
The acquisition unit 132 acquires an emotion of a user (for example, a user) when content related to a predetermined transaction target is provided.

For example, the acquisition unit 132 acquires the user's emotion when the content is displayed.

Also, for example, the acquisition unit 132 acquires the user's emotion when selecting the content.

Also, for example, the acquisition unit 132 estimates the user's emotion based on the user's behavior that is related to the content. For example, the acquisition unit 132 estimates an emotion having a causal relationship with a series of behaviors related to the content among the behaviors of the user.

Also, for example, the acquisition unit 132 estimates the user's emotion based on the behavior of the user until the content is provided to the user. For example, the acquisition unit 132 estimates an emotion having a causal relationship with a series of behaviors related to the content among the behaviors of the user.

The acquisition unit 132 may acquire behavior information of a user (for example, a user). For example, the acquisition unit 132 may acquire behavior information received by the reception unit 131 . The acquisition unit 132 may acquire behavior information received via content distributed by the first provision unit 134 .

In one example, the acquisition unit 132 acquires user behavior information from the user device 10 . In this example, the acquired behavior information indicates various logs such as click history, browsed content history, scroll history, line-of-sight history, and the like. Note that the line-of-sight history can be collected by, for example, a line-of-sight sensor mounted on the user device 10 . For example, the user's line of sight may be obtained via AR content.

It should be noted that the acquisition unit 132 uses a model (for example, MIL (Multiple Instance Learning)) that has learned the relationship between the emotion of the user (for example, the user) and a series of actions of the user that have a causal relationship with this emotion. A model learned using the technology of ) may be used to estimate the user's emotion when viewing content based on the acquired behavior information. For example, the acquisition unit 132 collects the chronological order of the user, such as a series of operations (clicks and scrolls) performed by the user when browsing content, the order of content browsed by the user, and what kind of link was selected. A model that has learned the relationship between an action and the emotion that the user is presumed to have before, during, or after the action may be used. Such a model is realized by learning, for example, the relationship between the emotions estimated from the user's biological information and the user's series of actions using MIL technology. When a series of actions of a person is input, an emotion presumed to have some kind of causal relationship with the series of actions before, during, or after the action is output. That is, such a model uses emotions and a series of actions as learning data, and by performing learning using MIL technology, has a causal relationship with all or part of the input series of actions (some Learning will be performed so as to output information indicative of emotion (with relevance). In addition, when the acquisition unit 132 acquires the user's behavioral information and biometric information, the acquisition unit 132 uses a model that has learned the relationship between the behavioral information, the biometric information, etc., and emotions to User sentiment may be inferred.

In one example, the acquisition unit 132 estimates the user's emotion using the acquired user behavior information.

For example, the acquisition unit 132 estimates the user's emotion using a machine learning model that predicts the user's emotion from the user's behavior. More specifically, the acquiring unit 132 inputs the acquired user behavior information to a machine learning model that predicts the user's emotions during a period in which the user takes one or more behaviors, thereby obtaining product links. Estimates the user's emotion when is selected.

Note that the acquisition unit 132 inputs the user behavior information received via the content distributed by the first provision unit 134 to the above-described machine learning model that predicts the user's emotion, thereby allowing the user to understand the content. may be estimated.

Regarding the machine learning model that predicts the user's emotion described above, for example, the acquisition unit 132 uses a sensing device such as a wearable device to calculate the physiological reaction of the crowdsourcing worker (for example, changes in heart rate and body temperature). identify. Then, the acquisition unit 132 estimates the worker's emotions during the period in which the worker took one or more actions based on the identified physiological reactions. The one or more behaviors are, for example, behaviors such as clicking, viewing content, scrolling, eye movements, and the like. In this way, the acquisition unit 132 can generate learning data for learning the correspondence between one or more actions and user's emotions. As a result, the acquisition unit 132 can generate, from the generated learning data, a machine learning model that predicts the user's emotions during the period in which the user has taken one or more actions.

As for the method for generating a machine learning model that predicts the user's emotion, for example, the acquisition unit 132 performs MIL based on the generated learning data to generate a prediction model that predicts the user's emotion. In MIL, one or more worker actions are contained in one emotional bag (eg, positive bag or negative bag). A positive bag for a given emotion includes one or more behaviors corresponding to this given emotion. On the other hand, a negative bag for a given emotion contains only one or more behaviors that do not correspond to this given emotion. For example, the acquisition unit 132 performs MIL based on the generated learning data, and generates an SVM (Support Vector Machine) that classifies the user's emotion as a prediction model that predicts the user's emotion. When input into a generated SVM, the generated SVM classifies the user's emotions during the time the user took one or more user actions. By inputting the acquired user behavior information into the generated prediction model, the acquisition unit 132 can estimate the user's emotion and a series of user behaviors that have a causal relationship with this emotion.

Note that when the user uses a sensing device such as a wearable device, the acquisition unit 132 uses the sensing device to identify the user's physiological reaction (for example, changes in heart rate or body temperature). You may The sensing device may be the user equipment 10 . Then, based on the identified physiological reaction, the acquisition unit 132 acquires the user's behavior during a period in which the user took one or more actions (for example, actions such as clicking, browsing content, scrolling, and movement of the line of sight). You may estimate the emotion of For example, the acquisition unit 132 determines emotions such as “happiness,” “surprise,” and “fear” (for example, six basic emotions) based on the specified physiological reaction, and the user performs one or more actions. You may estimate as a user's emotion in the time taken. Such emotions may be emotions associated with content selection, such as product links. For example, the acquisition unit 132 may estimate emotions such as happiness, calmness, and disgust as user emotions when the user selects such content. Alternatively, such emotion may be an emotion associated with viewing content. For example, the acquisition unit 132 may estimate emotions such as happiness, calmness, and disgust as emotions of the user when the user browses the content.

(Determination unit 133)
The determination unit 133 determines the price of the predetermined transaction target based on the emotion acquired by the acquisition unit 132 .

For example, the determination unit 133 determines the price of a predetermined transaction object to be displayed in the content based on the acquired emotion.

Also, for example, the determination unit 133 determines the price of a predetermined transaction object based on the acquired emotion, which is displayed in the sales content displayed when the content is selected.

Also, for example, if the feeling of the user (for example, the user) is favorable, the determining unit 133 lowers the price of the predetermined transaction object below the predetermined price.

Also, for example, when the user is hesitant about purchasing a predetermined transaction object, the determination unit 133 raises the price of the predetermined transaction object above the predetermined price. For example, the determination unit 133 further performs control to prevent the purchase of a predetermined transaction target by the user.

Also, for example, the determination unit 133 changes the price of a predetermined transaction target by an amount corresponding to the intensity of the user's emotion.

In one example, the determination unit 133 determines the price displayed in the sales content based on the user's emotion estimated by the acquisition unit 132 .

For example, the determination unit 133 determines the price to be displayed in the sale content so that the price when the user's emotion estimated by the acquisition unit 132 is a positive emotion such as pleasure is lower than a predetermined price. do. For example, the determination unit 133 makes the price when the user's emotion estimated by the acquisition unit 132 is a positive emotion lower than the price when the user's emotion estimated by the acquisition unit 132 is a neutral emotion. determine the price displayed within the sales content. Note that the neutral emotion is, for example, an emotion such as calmness.

The predetermined price mentioned above may be determined using a price determination algorithm such as dynamic pricing. For example, the predetermined price may be determined dynamically according to user demand. Also, for example, the predetermined price may be dynamically determined according to the user's purchase intention.

On the other hand, for example, the determination unit 133 sets the price in the sales content so that the price when the user's emotion estimated by the acquisition unit 132 is a negative emotion such as nervousness, upset, or stress is higher than a predetermined price. Determines the displayed price. For example, the determination unit 133 makes the price when the user's emotion estimated by the acquisition unit 132 is a negative emotion higher than the price when the user's emotion estimated by the acquisition unit 132 is a neutral emotion. determine the price displayed within the sales content.

In one example, when the user's emotion estimated by the acquisition unit 132 is a positive emotion, the determination unit 133 determines a price lower than the current price of the item as the price of the item. On the other hand, when the user's emotion estimated by the acquisition unit 132 is a negative emotion, the determination unit 133 determines a price higher than the current price of the item as the price of the item.

Regarding the degree of price change, the determination unit 133 may determine the price displayed in the sales content based on the alertness level. In other words, the determination unit 133 may determine the price displayed in the sales content based on "how strongly the emotion was activated."

For example, the determination unit 133 determines that the price when the user's emotion estimated by the acquisition unit 132 is a very positive emotion (e.g., the emotion "happiness") is the price when the user's emotion estimated by the acquisition unit 132 is positive. The price displayed in the sales content may be determined to be higher than the price if it were an emotion (eg, emotion "relaxed"). On the other hand, for example, the determination unit 133 determines that the price when the user's emotion estimated by the acquisition unit 132 is a very negative emotion (for example, the emotion "upset") is set to the price when the user's emotion estimated by the acquisition unit 132 is negative. The price displayed in the sales content may be determined to be higher than the price for a positive emotion (eg, the emotion "depressed").

Regarding the display mode of sales content, the determination unit 133 may determine a component corresponding to a content item for accepting a product purchase request based on the user's emotion estimated by the acquisition unit 132 .

In one example, when the user's emotion estimated by the acquisition unit 132 is a positive emotion, the determination unit 133 determines the text "purchase" as the purchase button text for purchasing the product. On the other hand, when the user's emotion estimated by the acquisition unit 132 is a negative emotion, the determination unit 133 determines the text "next week sale (buy now)" as the purchase button text for purchasing the product. do. In this way, when the user's emotion estimated by the acquisition unit 132 is a negative emotion, the determination unit 133 may make it difficult for the user to purchase the product.

In another example, when the user's emotion estimated by the acquisition unit 132 is a positive emotion, the determination unit 133 determines the text "proceed to order" as the purchase button text for purchasing the product. may On the other hand, when the user's emotion estimated by the acquisition unit 132 is a negative emotion, the determination unit 133 may determine the text "Add to Cart" as the purchase button text for purchasing the product. . In yet another example, when the user's emotion estimated by the acquisition unit 132 is the emotion "enjoyment", the determination unit 133 sets the text "buy now" to the purchase button for purchasing the product. May be determined as text. On the other hand, when the user's emotion estimated by the acquisition unit 132 is the emotion "nervous", the determination unit 133 determines the text "purchase later" as the purchase button text for purchasing the product. may

If the user's emotion estimated by the acquisition unit 132 is a negative emotion, a purchase button that does not allow the user to purchase a product may be determined as the purchase button to be displayed in the sales content. For example, when the user's emotion estimated by the acquisition unit 132 is negative emotion, the purchase button may be grayed out.

Note that the determination unit 133 may determine the price to be displayed in the product link described above based on the user's emotion when the product link is displayed.

For example, when the receiving unit 131 receives from the user device 10 a transmission request for other content including a product link, the determining unit 133 determines whether the user estimated by the acquiring unit 132 is the content (that is, the first provision The price displayed within this product link may be determined based on the user's sentiment when viewing the content delivered by unit 134 . For example, the determination unit 133 determines the price displayed in the product link so that the price when the user's emotion estimated by the acquisition unit 132 is a positive emotion such as pleasure is lower than a predetermined price. You may In addition, for example, the determination unit 133 sets the price in the product link so that the price when the user's emotion estimated by the acquisition unit 132 is a negative emotion such as nervousness, upset, or stress is higher than a predetermined price. You may determine the displayed price.

(First providing unit 134)
The first providing unit 134 provides content to the user device 10 . The first providing unit 134 provides the user device 10 with the content received by the receiving unit 131, for example. The first providing unit 134 may acquire content from the content information storage unit 121 . The first providing unit 134 may provide the acquired content to the user device 10 .

In one example, the first provider 134 distributes content to the user device 10 . In this example, when the receiving unit 131 receives a request for acquiring content related to a predetermined transaction target, the first providing unit 134 provides content related to the predetermined transaction target to the user device 10. .

(Second providing unit 135)
The second providing unit 135 provides the user device 10 with other content that is displayed when the content provided by the first providing unit 134 is selected. The second providing unit 135 provides the user device 10 with other content received by the receiving unit 131, for example. The second providing unit 135 may acquire other content from the content information storage unit 121 . The second providing unit 135 may provide the other acquired content to the user device 10 .

In one example, the second providing unit 135 provides sales content to the user device 10 in response to selection of the product link. In this example, the second providing unit 135 provides the sales content to the user device 10 when the receiving unit 131 receives a transmission request for the sales content related to the product.

In one example, the sales content provided by the second provider 135 indicates a price determined based on the user's emotions. Further, the sales content provided by the second providing unit 135 indicates purchase buttons determined based on the user's emotions.

[3. Decision processing flow]
Next, a procedure of determination processing by the determination device 100 according to the embodiment will be described. FIG. 4 is a flowchart showing a decision processing procedure by the decision device 100 according to the embodiment.

As shown in FIG. 4, first, the determination device 100 acquires the emotion of the user, which is the emotion at the time of providing the content related to the predetermined transaction object (step S101).

For example, the decision device 100 acquires the user's emotion when the content is displayed.

Also, for example, the determining device 100 acquires the user's emotion when selecting content.

Also, for example, the determination device 100 estimates the user's emotion based on the user's behavior that is related to the content. For example, the determination device 100 estimates an emotion having a causal relationship with a series of behaviors related to the content among the behaviors of the user.

Also, for example, the determining device 100 estimates the user's emotion based on the behavior of the user until the content is provided to the user. For example, the determination device 100 estimates an emotion having a causal relationship with a series of behaviors related to the content among the behaviors of the user.

Next, the decision device 100 decides the price of the predetermined trading object based on the acquired emotion (step S102).

For example, the decision device 100 decides the price of a given transaction object to be displayed in the content based on the obtained emotion.

Also, for example, the determination device 100 determines a price of a predetermined transaction object based on the acquired emotion, which is to be displayed in sales content triggered by the selection of the content.

Also, for example, the determination device 100 lowers the price of the predetermined transaction object below the predetermined price when the user's emotion is favorable.

Further, for example, if the user is hesitant about purchasing a predetermined transaction object, the determination device 100 raises the price of the predetermined transaction object above the predetermined price. For example, the decision device 100 further performs control to prevent purchase of a predetermined transaction target by the user.

Also, for example, the determination device 100 changes the price of a predetermined transaction object by an amount corresponding to the intensity of the user's emotion.

[4. Modification]
The determination device 100 according to the above embodiments may be implemented in various different forms other than the above embodiments. Therefore, other embodiments of the determination device 100 will be described below.

[4-1. Determining the Price of a Transaction Object Based on the Emotions of Multiple Users]
The acquisition unit 132 may acquire the emotions of multiple users (for example, multiple users) who have provided content related to a predetermined transaction target. Moreover, the determination unit 133 may determine the price of a predetermined transaction target based on the emotions of a plurality of users. For example, the determination unit 133 may change the price of a predetermined transaction target when the ratio of users who have favorable feelings among a plurality of users satisfies a predetermined condition.

For example, when a plurality of users view the content distributed by the first providing unit 134 at the same timing, the determining unit 133 determines a predetermined may determine the price of the traded object. Also, for example, when a plurality of users access other content provided by the second providing unit 135 at the same timing, the determining unit 133 determines the emotions of the plurality of users acquired by the acquiring unit 132. may determine the price of a given traded object based on .

For example, when the emotion of the majority of the users is positive emotion such as pleasure, the determination unit 133 determines a price lower than the current price of the predetermined transaction object as the price of this predetermined transaction. good too. On the other hand, for example, when the emotions of the majority of a plurality of users are negative emotions such as nervousness and upset, the determination unit 133 determines a price higher than the current price of a predetermined transaction object as the price of this predetermined transaction. may be determined as

[4-2. Determination of transaction target price based on user attributes]
The determination unit 133 may determine the price of a predetermined transaction object based on the user's (for example, user's) emotion and the user's attribute. For example, the determination unit 133 may determine the price of a predetermined transaction target based on attributes possessed by the user and relating to the relationship between price and purchase.

For example, the determination unit 133 may determine the price of a predetermined transaction object based on the value perceived by the user. For example, when the user prefers luxury goods or luxury goods, the determination unit 133 may determine a price higher than the current price of a predetermined transaction target as the price of this predetermined transaction. On the other hand, for example, when the user prefers a reasonably priced transaction target, the determination unit 133 may determine a price lower than the current price of a predetermined transaction target as the predetermined transaction price.

[4-3. The price of the transaction target that changes in real time]
The first providing unit 134 may change the price displayed in the content provided by the first providing unit 134 in real time according to the user's emotion obtained by the obtaining unit 132 . In this case, the content provided by the first providing unit 134 is, for example, auction content.

For example, when the user's emotion is a positive emotion such as pleasure, the first providing unit 134 may reduce the price of a predetermined transaction target in real time. On the other hand, for example, when the user's emotion is a negative emotion such as nervousness or upset, the first providing unit 134 may raise the price of a predetermined transaction target in real time.

[4-4. others〕
Also, among the processes described in the above embodiments, some of the processes described as being automatically performed can also be performed manually. Alternatively, all or part of the processes described as being performed manually may be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

For example, part or all of the storage unit 120 shown in FIG. 2 may be held in a storage server or the like instead of being held by the determination device 100 . In this case, the determining device 100 acquires various information such as price information by accessing the storage server.

[4-5. Hardware configuration]
Also, the determination device 100 according to the above-described embodiments is implemented by a computer 1000 configured as shown in FIG. 5, for example. FIG. 5 is a diagram illustrating an example of a hardware configuration; A computer 1000 is connected to an output device 1010 and an input device 1020, and an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected via a bus 1090. have

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used for various calculations by the arithmetic device 1030 and various databases are registered, and is implemented by a ROM (Read Only Memory), HDD, flash memory, or the like.

The output IF 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various types of information such as a monitor and a printer. It is realized by a connector conforming to a standard such as HDMI (registered trademark) (High Definition Multimedia Interface). Also, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, keyboard, scanner, etc., and is realized by, for example, USB.

Note that the input device 1020 includes, for example, optical recording media such as CDs (Compact Discs), DVDs (Digital Versatile Discs), PDs (Phase change rewritable discs), magneto-optical recording media such as MOs (Magneto-Optical discs), and tapes. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Also, the input device 1020 may be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends the data to arithmetic device 1030, and also transmits data generated by arithmetic device 1030 via network N to other devices.

The arithmetic device 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070 . For example, arithmetic device 1030 loads a program from input device 1020 or secondary storage device 1050 onto primary storage device 1040 and executes the loaded program.

For example, when the computer 1000 functions as the determination device 100 , the arithmetic device 1030 of the computer 1000 implements the functions of the control unit 130 by executing programs loaded on the primary storage device 1040 .

[5. effect〕
As described above, the determination device 100 according to the embodiment has the acquisition unit 132 and the determination unit 133 . The acquisition unit 132 acquires the emotion of the user, which is the emotion when the content related to the predetermined transaction object is provided. The determination unit 133 determines the price of the predetermined transaction target based on the emotion acquired by the acquisition unit 132 .

Also, in the determination device 100 according to the embodiment, the acquisition unit 132 acquires the user's emotion when the content is displayed. Also, in the determination device 100 according to the embodiment, the determination unit 133 determines the price of the predetermined transaction object, which is displayed in the content, based on the emotion acquired by the acquisition unit 132 .

Also, in the determination device 100 according to the embodiment, the acquisition unit 132 acquires the emotion of the user when selecting the content. In addition, in the determination device 100 according to the embodiment, the determination unit 133 determines the price of the predetermined transaction object based on the emotion acquired by the acquisition unit 132, and the sales price displayed when the content is selected. Determining prices displayed within content.

Further, in the determination device 100 according to the embodiment, the determination unit 133 lowers the price of the predetermined transaction object below the predetermined price when the user's emotion is favorable.

Further, in the determination device 100 according to the embodiment, the determination unit 133 raises the price of the predetermined transaction object higher than the predetermined price when the user hesitates to purchase the predetermined transaction object.

In addition, in the determination device 100 according to the embodiment, the determination unit 133 further performs control to prevent the user from purchasing a predetermined transaction target.

Also, in the determination device 100 according to the embodiment, the determination unit 133 changes the price of the predetermined transaction object by an amount corresponding to the intensity of the user's emotion.

In addition, in the determination device 100 according to the embodiment, the acquisition unit 132 acquires the emotions of multiple users who have provided content related to a predetermined transaction target. Also, in the determination device 100 according to the embodiment, the determination unit 133 determines the price of a predetermined transaction target based on the emotions of a plurality of users.

In addition, in the determination device 100 according to the embodiment, the determination unit 133 changes the price of a predetermined transaction target when the ratio of users who have favorable feelings among a plurality of users satisfies a predetermined condition. do.

Also, in the determination device 100 according to the embodiment, the determination unit 133 determines the price of a predetermined transaction object based on the user's emotion and the user's attributes.

In addition, in the determination device 100 according to the embodiment, the determination unit 133 determines the price of a predetermined transaction object based on the attribute of the user, which is related to the relationship between price and purchase.

Also, in the determination device 100 according to the embodiment, the acquisition unit 132 estimates the user's emotion based on the user's behavior that is related to the content.

In addition, in the determination device 100 according to the embodiment, the acquisition unit 132 estimates the user's emotion based on the behavior of the user until the content is provided to the user.

In addition, in the determination device 100 according to the embodiment, the acquisition unit 132 estimates an emotion having a causal relationship with a series of behaviors related to the content among the behaviors of the user.

Through the processes described above, the determination device 100 can set a more appropriate price.

As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

Further, the above-described determination device 100 may be implemented by a plurality of server computers, and depending on the function, may be implemented by calling an external platform or the like using an API (Application Programming Interface), network computing, or the like. Flexible to change.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the receiving section can be read as receiving means or a receiving circuit.

1 determination system 10 user device 100 determination device 110 communication unit 120 storage unit 121 content information storage unit 130 control unit 131 reception unit 132 acquisition unit 133 determination unit 134 first provision unit 135 second provision unit

Claims (14)

Inputting the user's behavior into a machine learning model that predicts the user's emotion when providing content related to a predetermined transaction target from the specific user's behavior. an acquisition unit that acquires by
When the emotion acquired by the acquisition unit is a negative emotion, the price of the predetermined trading object is set higher than the price when the emotion acquired by the acquisition unit is a neutral emotion. and a decision unit for deciding such that: 2. The determination device according to claim 1 , wherein the determination unit further performs control to prevent the purchase of the predetermined transaction target by the user. The acquisition unit acquires the emotion of the user when the content is displayed,
The determination device according to claim 1, wherein the determination unit determines a price displayed in the content, which is the price of the predetermined transaction object. The acquisition unit acquires the user's emotion when the content is selected,
2. The determining unit determines the price of the predetermined transaction object, which is displayed in sales content displayed when the content is selected. decision device. The determination unit determines the price of the predetermined transaction object when the user's emotion is a favorable emotion, and the price when the emotion acquired by the acquisition unit is a neutral emotion. decide to be lower than the price
The decision device according to any one of claims 1 to 4 , characterized in that: The determination device according to any one of claims 1 to 5, wherein the determination unit changes the price of the predetermined trading object by an amount corresponding to the intensity of emotion of the user. . The acquisition unit acquires the emotions of a plurality of users who have provided content related to a predetermined transaction target by inputting the behaviors of the plurality of users into the machine learning model ,
The determination unit sets the price of the predetermined transaction object to the current price of the predetermined transaction object when a ratio of users having favorable feelings among the plurality of users satisfies a predetermined condition . change to a lower price than
The decision device according to any one of claims 1 to 6 , characterized in that: 8. The method according to any one of claims 1 to 7 , wherein said decision unit decides the price of said predetermined trading object based on said user's emotion and said user's attribute. decision device. 9. The determination according to claim 8 , wherein the determination unit determines the price of the predetermined transaction object based on an attribute of the user, which is an attribute related to a relationship between price and purchase. Device. 2. The acquiring unit estimates the emotion of the user by inputting, into the machine learning model, an action of the user that is related to the content. 10. A decision device according to any one of 10-10. The acquisition unit estimates the emotion of the user by inputting the user 's behavior, which is the behavior until the content is provided to the user, into the machine learning model. The decision device according to any one of claims 1 to 10, wherein: The determination device according to claim 10 or 11 , wherein the acquisition unit estimates an emotion having a causal relationship with a series of actions related to the content among actions of the user. A decision method executed by a decision device,
Inputting the user's behavior into a machine learning model that predicts the user's emotion when providing content related to a predetermined transaction target from the specific user's behavior. an obtaining step of obtaining by
If the emotion acquired by the acquisition step is a negative emotion, the price of the predetermined trading object is set higher than the price when the emotion acquired by the acquisition step is a neutral emotion. and a determining step of determining so that Inputting the user's behavior into a machine learning model that predicts the user's emotion when providing content related to a predetermined transaction target from the specific user's behavior. an acquisition procedure to be acquired by
When the emotion obtained by the obtaining procedure is a negative emotion, the price of the predetermined trading object is made higher than the price when the emotion obtained by the obtaining procedure is a neutral emotion. A determination program for causing a computer to execute a determination procedure for determining and

Images