JP2022027779A - Device, method, and program for processing information - Google Patents

Abstract

PROBLEM TO BE SOLVED: To appropriately generate information indicative of elements related to an action of a user.

SOLUTION: An information processing device of the present invention comprises an acquisition unit and a generation unit. The acquisition unit acquires relevance information indicative of a degree of relevance between each element of a context related to a time point different from a time point of delivery of content and a predetermined action of a first user on the content. Upon acquisition of action information regarding the predetermined action of a second user who received the content, the generation unit generates relevant element information indicative of elements related to the predetermined action of the second user on the basis of the action information and the relevance information.

SELECTED DRAWING: Figure 3

COPYRIGHT: (C)2022,JPO&INPIT

Description

The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Conventionally, a technique for generating information indicating whether or not a user performs a predetermined action has been provided. For example, there is provided a technique for visually displaying a part of a content that is easily clicked by a user.

Japanese Unexamined Patent Publication No. 2014-174805

However, in the above-mentioned conventional technique, it is not always possible to appropriately generate information indicating an element related to the user's behavior. For example, it is difficult to appropriately generate information indicating an element related to a user's behavior only by visually displaying a portion that is easily clicked by the user.

The present application has been made in view of the above, and an object of the present application is to provide an information processing device, an information processing method, and an information processing program that appropriately generate information indicating elements related to user behavior.

The information processing apparatus according to the present application includes an acquisition unit that acquires relationship degree information indicating the degree of relationship between each element of the context related to a time point different from the content delivery time point and a predetermined action of the first user with respect to the content. , When the behavior information related to the predetermined behavior of the second user to which the content is delivered is acquired, the behavior information is related to the predetermined behavior of the second user based on the behavior information and the relationship degree information. It is characterized by having a generation unit for generating relational element information indicating an element to be processed.

According to one aspect of the embodiment, there is an effect that information indicating an element related to the user's behavior can be appropriately generated.

FIG. 1 is a diagram showing an example of information processing according to an embodiment. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. FIG. 3 is a diagram showing a configuration example of the information processing apparatus according to the embodiment. FIG. 4 is a diagram showing an example of a user information storage unit according to an embodiment. FIG. 5 is a diagram showing an example of the behavior information storage unit according to the embodiment. FIG. 6 is a diagram showing an example of a distribution information storage unit according to an embodiment. FIG. 7 is a diagram showing an example of a model information storage unit according to an embodiment. FIG. 8 is a diagram showing an example of the prediction information storage unit according to the embodiment. FIG. 9 is a diagram showing an example of a relationship degree information storage unit according to an embodiment. FIG. 10 is a flowchart showing an example of information processing according to the embodiment. FIG. 11 is a diagram showing an example of information processing according to the embodiment. FIG. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device.

Hereinafter, the information processing apparatus, the information processing method, and the embodiment for implementing the information processing program (hereinafter referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. It should be noted that this embodiment does not limit the information processing apparatus, information processing method, and information processing program according to the present application. Further, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

(Embodiment)
[1. Information processing]
An example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of information processing according to an embodiment. In the example of FIG. 1, another area AR12 (X area) is used by using a model generated by the information processing apparatus 100 (see FIG. 3) based on the behavior information of the first user located in the predetermined area AR11 (A area). ) Shows the case of generating information about the second user located in. In the example of FIG. 1, push notification is shown as an example as a form of content distribution, but content distribution may be in various modes. For example, the content distribution in the information processing system 1 is not limited to the push notification, and may be a so-called pull-type content distribution in which the content is requested from the terminal device 10. For example, the push notification may be information output by the terminal device 10 regardless of the operation of the terminal device 10 by the user. For example, the push notification may be to actively notify the user of predetermined information. Further, in the following, the operation of displaying the information related to the push notification on the terminal device 10 may be the opening operation by selecting or designating the push notification. Further, the size and shape of the area referred to here may be appropriately set according to the purpose of processing and the like. For example, as the area, areas of various sizes such as "prefecture", "city", "ward", and "town" may be appropriately set.

[Information processing system configuration]
Prior to the description of FIG. 1, the configuration of the information processing system 1 will be described with reference to FIG. FIG. 2 is a diagram showing a configuration example of an information processing system according to an embodiment. As shown in FIG. 2, the information processing system 1 includes a terminal device 10, an information providing device 50, and an information processing device 100. The terminal device 10, the information providing device 50, and the information processing device 100 are connected to each other via a predetermined network N so as to be communicable by wire or wirelessly. The information processing system 1 shown in FIG. 2 may include a plurality of terminal devices 10, a plurality of information providing devices 50, and a plurality of information processing devices 100.

The terminal device 10 is an information processing device used by the user. The terminal device 10 accepts various operations by the user. In the following, the terminal device 10 may be referred to as a user. That is, in the following, the user can be read as the terminal device 10. The terminal device 10 described above is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. FIG. 1 shows a case where the terminal device 10 is a smartphone.

Further, it is assumed that the terminal device 10 has a function such as a GPS (Global Positioning System) sensor and can detect and acquire a position. For example, the terminal device 10 transmits action information such as position information to the information processing device 100. The terminal device 10 is not limited to the above, and may have various sensors. For example, the terminal device 10 acquires biological information such as a voice sensor (mic), an acceleration sensor, a gyro sensor, a temperature sensor, a humidity sensor, an illuminance sensor, a pressure sensor, a proximity sensor, and odor, sweat, heartbeat, pulse, and brain wave. It may have various sensors such as a sensor for the purpose. Then, the terminal device 10 may transmit various sensor information detected by various sensors to the information processing device 100. For example, the terminal device 10 may detect the user's utterance information (sensor information) by a voice sensor and transmit the detected utterance information (sensor information) to the information processing device 100.

For example, the terminal device 10 may have various functions such as a temperature sensor and a barometric pressure sensor, and may be able to detect and acquire peripheral information such as temperature and barometric pressure in which the user is placed. Further, the terminal device 10 may have various functions such as a heart rate sensor and may be able to detect and acquire the biometric information of the user. For example, a user who uses the terminal device 10 may be able to acquire the user's own biometric information by the terminal device 10 by wearing a wearable device capable of communicating with the terminal device 10. For example, a user who uses the terminal device 10 wears a wristband-type wearable device capable of communicating with the terminal device 10, and the terminal device 10 acquires information on the user's own heartbeat (pulse) by the terminal device 10. It may be possible.

The context information regarding the distribution of the content (hereinafter, also simply referred to as “context information”) referred to here includes information indicating various contexts regarding the distribution of the content. For example, the context information includes information indicating the context of the user to whom the content is delivered and information indicating the context of the place where the user is located. For example, contextual information may include information about user attributes. For example, the context information may include information indicating what kind of user the user is. For example, contextual information may include information about various users such as age, profile, interests, and the like. For example, contextual information may include information about the context of time or place. For example, the context information may include information indicating the situation at the time and place when the push notification is made. For example, the context information may include information about a time zone. For example, the context information may include information indicating which of the 24 time zones the time zone corresponds to in the 0 to 23 o'clock range. For example, the context information includes four time zones: morning (4-10 o'clock, etc.), noon (10-16 o'clock, etc.), night (16-22 o'clock, etc.), and midnight (22-4 o'clock, etc.). Information indicating which of these is supported may be included. For example, the context information may include information about a POI (Point of Interest) indicating a facility name such as a store or a stadium corresponding to the user's position. For example, the context information relates to various times and places such as the stay (residence) time at which the user is located at the place, the attribute of the place (commercial area, residential area, etc.) and the time attribute (morning, night, etc.). Information may be included.

For example, contextual information may include information about the context of the environment. For example, the context information may include information indicating what kind of environment the user is in when the push notification is performed. For example, the context information may include various information (peripheral information) such as weather, user's emotion (mood), temperature, and atmospheric pressure. For example, contextual information may include information indicating whether the weather corresponds to sunny, cloudy, rainy, or snowy. For example, the context information may include information indicating whether the user's mood is a positive emotion or a negative emotion. For example, the context information may include information indicating whether the user's mood is a positive emotion such as joy or fun, or a negative emotion such as anger or sadness.

For example, the information processing apparatus 100 estimates a user's emotion (mood) based on various information about the user. For example, the information processing apparatus 100 estimates the user's emotions based on the user's behavior information. The information processing apparatus 100 estimates the user's emotions by appropriately using various conventional techniques. For example, the information processing apparatus 100 estimates the user's emotions using various input information input by the user, such as the content browsed by the user (viewed content) and the query used by the user for the search. For example, the information processing apparatus 100 may estimate the user's emotions by appropriately analyzing the character information and the input information in the browsed content by using various conventional techniques such as parsing. For example, the information processing apparatus 100 stores a list of keywords (emotion keyword list) for each emotion in the storage unit 120 (see FIG. 3), and the keywords included in the character information and the input information in the browsed content are most applicable. The emotions to be processed may be estimated as the emotions of the user. For example, the information processing apparatus 100 uses a list of emotional keywords of keywords corresponding to each of positive emotions and negative emotions, and is included in the text information and input information in the browsed content among the positive emotions and the negative emotions. The emotion of the user who has more keywords may be estimated as the emotion of the user. Further, the information processing apparatus 100 may estimate the user's emotion by using the character information obtained by converting the user's utterance and the above-mentioned emotion keyword list.

For example, the information processing device 100 estimates the user's emotions based on the sensor information detected by the terminal device used by the user. For example, the information processing apparatus 100 may estimate the user's emotions based on the sensor information regarding the user's stride length, amplitude, and the like. Further, for example, the information processing apparatus 100 may estimate the user's emotion by using biological information such as the user's heartbeat and blood pressure, image information obtained by capturing the user's face, and the like. The above is an example, and the information processing apparatus 100 may estimate the user's emotions by any method as long as it can be estimated. For example, the information processing apparatus 100 may estimate the user's emotions based on the tone of the user's utterance (sound tone) or the like. For example, the information processing apparatus 100 may presume that the user's emotion is a positive emotion of joy or enjoyment when the tone (sound tone) of the user's utterance is high. For example, when the tone (sound tone) of the user's utterance is weak, the information processing apparatus 100 may presume that the user's emotion is a negative emotion of anger or sadness. For example, the information processing apparatus 100 may presume that the user's emotion is a positive emotion of joy or enjoyment when the number or amount of products purchased by the user is equal to or more than a predetermined threshold value. For example, the information processing apparatus 100 may presume that the user's emotions are negative emotions of anger or sadness when the number or amount of products purchased by the user is less than a predetermined threshold value.

For example, the context information may include information indicating whether the temperature corresponds to high temperature, medium temperature, or low temperature. For example, the context information includes information indicating whether the temperature corresponds to the average temperature of high (+ 5 ° C or higher), medium (less than ± 5 ° C), or low (-5 ° C or lower, etc.). May be included. For example, the context information may include information indicating whether the atmospheric pressure corresponds to high, medium, or low. For example, in the context information, the atmospheric pressure is high (+1 hectopascal or more, etc.), medium (less than ± 1 hectopascal), low (-1 hectopascal or less, etc.) with respect to the atmospheric pressure immediately before (for example, 10 minutes ago, 1 hour ago, etc.). ) May be included. For example, the context information may include information about the operation content. For example, the context information may include various information such as information indicating what kind of operation (push notification) is performed, information indicating a category of notification content, and information indicating whether or not it is an app teaser. The above is an example, and the context information may include various information, not limited to the above.

For example, the context information may include information about the situation of the user and the terminal device 10, the situation of the user estimated based on the environment (background) of the user and the terminal device 10, and the like. In addition, the context information includes the content of the content provided to the user, the content of the content that the user has reacted to, the attributes of the user, the current position of the user, the current time, the physical environment in which the user is placed, and the society in which the user is placed. Various information such as the environment, the user's motor state, and the estimated user's emotions may be included. Further, the context information may include various information such as the situation of the user and the terminal device 10 and the psychological state of the user estimated based on the environment (background) of the user and the terminal device 10.

The information providing device 50 is an information processing device having various open data. For example, the information providing device 50 provides open data. The information providing device 50 is an information processing device that provides the information processing device 100 with open data, which is so-called widely open data. For example, the information providing device 50 may be an information processing device managed by each local government and providing the data held by the local government to the outside as open data. Further, for example, the information providing device 50 may be various information processing devices such as a server managed by the Japan Meteorological Agency. The information providing device 50 is not limited to the above as long as the data (information) is permitted to be used, and the information providing device 50 is not limited to the above, but is open data related to traffic such as road information, open data related to weather such as weather and temperature, geospatial information, disaster prevention, and disaster prevention. Various open data such as disaster mitigation information, procurement information, statistical information, etc. may be provided.

For example, the information providing device 50 provides open data such as the A area and the B area to the information processing device 100. For example, the information providing device 50 provides the information processing device 100 with environmental information regarding the A area, the B area, and the like. For example, the information providing device 50 provides various environmental information such as traffic information in the area A to the information processing device 100. For example, the information providing device 50 provides various environmental information such as traffic information in the B area and information on the population composition to the information processing device 100. As described above, the environmental information may include various information such as road information and weather information around the user.

The information processing apparatus 100 determines the second user based on the relationship degree information indicating the degree of relationship between each element of the context related to another time point different from the content delivery time point and the predetermined action of the first user with respect to the content. It is an information processing device that generates relational element information indicating elements related to the behavior of. The information processing apparatus 100 is related to a predetermined action of the second user based on the action information and the relationship degree information when the action information regarding the predetermined action of the second user to which the content is delivered is acquired. It is a generator that generates relational element information indicating an element. In the example of FIG. 1, the information processing apparatus 100 shows an element related to a predetermined behavior of a second user by using a model including a feature amount for each element of the context regarding another time point different from the delivery time point of the content. Generate relational element information. The information processing apparatus 100 uses a model for predicting profitability in content distribution to generate relational element information indicating elements related to a predetermined behavior of a second user. The profitability in the distribution of the content referred to here may be various as long as there is a possibility that the distribution of the content will bring profit (profit) to a predetermined entity. The profitability in the distribution of the content may be the profitability in any entity as long as it is an entity related to the distribution of the content. For example, the profitability in the distribution of the content may indicate the profit obtained by the provider of the product by the user purchasing the product related to the distributed content. For example, it is presumed that the longer the user browses the content, the more likely it is that an action that brings profit (profit) to a predetermined entity such as the purchase of the user related to the content will occur, so that the profitability in the distribution of the content is high. May indicate how long the user browses the delivered content. That is, the information processing apparatus 100 uses a model that predicts the user's behavior with respect to the content to generate relational element information indicating an element related to a predetermined behavior of the second user. Further, the information processing apparatus 100 generates a model for predicting the opening probability of the content, as in the model M11 shown in FIG. 11, and uses the model to indicate an element related to a predetermined behavior of the second user. Information may be generated.

The information processing device 100 is different from the predetermined area based on the operation information indicating whether or not the user has performed the predetermined operation on the content pushed and notified by the terminal device 10 used by the user located in the predetermined area. This is an information processing device that generates predictive information that predicts the presence or absence of a predetermined operation of the user for the content when the content is push-notified to the terminal device 10 used by the user located in the area of. For example, the information processing device 100 acquires various information such as behavior information including position information from the terminal device 10. Further, for example, the information processing apparatus 100 acquires various information such as open data from the information providing apparatus 50.

From here, an example of information processing by the information processing apparatus 100 (see FIG. 3) will be described with reference to FIG. First, the map information MP1 shown in FIG. 1 will be briefly described. The map information MP1 shown in FIG. 1 is a diagram schematically showing an area or the like included in a predetermined range. For example, the map information MP1 is a diagram for schematically showing the status of push notification to the terminal device 10 to the A area and the X area.

In the example of FIG. 1, the information processing apparatus 100 pushes notification of a predetermined content to the terminal apparatus 10 used by a certain user, and acquires information indicating that the content has been opened by the user (step S1-1). For example, the information processing device 100 indicates that a predetermined content (for example, content CT11 or the like) is push-notified to the terminal device 10 used by the user U1 (see FIG. 4) located in the A area, and the user U1 opens the package. Get information. As described above, when "user U * (* is an arbitrary numerical value)" is described, it means that the user is a user identified by the user ID "U *". For example, when "user U1" is described, the user is a user identified by the user ID "U1".

For example, the information processing apparatus 100 push-notifies the terminal device 10 used by the user U1 located in the partial area LC1-1 of the A area, and acquires information indicating that the predetermined content has been opened by the user U1. .. The partial area LC1-1 may be an area within a predetermined range in the area A. The partial area LC1-1 may be one position information representing the range of the partial area LC1-1. For example, the partial area LC1-1 may be the position information of the center within the range of the partial area LC1-1. Further, the partial area LC1-1 may be a combination of the position information of the center within the range of the partial area LC1-1 and the information indicating the range from the center (for example, within 100 m). Further, the partial area LC1-1 may be a list of positions within the range of the partial area LC1-1. Further, in the example of FIG. 1, the information processing apparatus 100 acquires information indicating that the content (content CT11) notified in step S1-1 has been viewed by the user during the time RTM1 after opening (step S2). ). For example, the information processing apparatus 100 may acquire information indicating that the content notified in step S1-1 has been displayed on the user's terminal apparatus 10 during the time RTM 1 after opening.

Further, the information processing device 100 acquires information such as sensor information from the terminal device 10 used by the user U1 and estimates the emotion of the user U1 at each time point. For example, the information processing apparatus 100 estimates the emotion of the user U1 at a time different from the date and time dt11 based on the sensor information at a time different from the date and time (date and time dt11) when the predetermined content is delivered to the user U1. For example, the information processing apparatus 100 estimates the emotion of the user U1 5 minutes before the date and time dt11 based on the sensor information acquired from the terminal device 10 used by the user U1 at the time point 5 minutes before the date and time dt11. .. For example, the information processing apparatus 100 estimates the emotion of the user U1 one minute before the date and time dt11 based on the sensor information acquired from the terminal device 10 used by the user U1 at the time point one minute before the date and time dt11. .. Further, the information processing apparatus 100 stores the estimated emotions of the user U1 at each time point in the storage unit 120 (see FIG. 3) in association with the user U1. The information processing device 100 may acquire information indicating the emotion of the user U1 at each time point from an external information processing device.

The information processing device 100 is not limited to the content delivered to the user, and may use information indicating the viewing time of the user of the entire content group having a predetermined relationship with the content after the content is delivered. For example, the information processing apparatus 100 is not limited to the content CT11 delivered to the user U1, but uses information indicating the viewing time of the user U1 of the entire content group having a predetermined relationship with the content CT11 after the content CT11 is delivered. You may. For example, the information processing apparatus 100 may use information indicating the browsing time of the user U1 of the entire content group of the site (site STX) to which the content CT11 belongs after the content CT11 is delivered to the user U1. That is, the information processing apparatus 100 may set the time (profitability) when the user browses the content group related to the site STX after the distribution of the content related to the site STX to the user as the target for generating the prediction information. In this case, for example, the information processing apparatus 100 generates forecast information for the profit (profitability) obtained by the business operator who operates the site STX by the user's behavior after the content related to the site STX is delivered to the user. May be.

For example, the information processing device 100 stores the information acquired from the terminal device 10 in the action information storage unit 123 (see FIG. 5). The information processing device 100 may provide the content to the terminal device 10, or another device may provide the content as long as the information processing device 100 can acquire the information used for generating the prediction information. .. For example, the content may be provided to the terminal device 10 by any device as long as the information processing device 100 can acquire the information used for generating the prediction information.

Further, in the example of FIG. 1, the information processing apparatus 100 is push-notified to the terminal apparatus 10 used by a certain user, and acquires information indicating that the predetermined content has not been opened by the user (step S1-2). .. For example, the information processing device 100 push-notifies the terminal device 10 used by the user U2 (see FIG. 4) located in the area A, and acquires information indicating that the predetermined content has not been opened by the user U2. For example, the information processing apparatus 100 obtains information indicating that the predetermined content is push-notified to the terminal apparatus 10 used by the user U2 located in the partial area LC1-2 of the A area and is not opened by the user U2. do.

Further, the information processing device 100 acquires information such as sensor information from the terminal device 10 used by the user U2, and estimates the emotion of the user U2 at each time point. For example, the information processing apparatus 100 estimates the emotion of the user U2 at a time different from the date and time dt21 based on the sensor information at a time different from the date and time (date and time dt21) when the predetermined content is delivered to the user U2. For example, the information processing apparatus 100 estimates the emotion of the user U2 5 minutes before the date and time dt21 based on the sensor information acquired from the terminal device 10 used by the user U2 at the time point 5 minutes before the date and time dt21. .. For example, the information processing apparatus 100 estimates the emotion of the user U2 one minute before the date and time dt21 based on the sensor information acquired from the terminal device 10 used by the user U2 at the time point one minute before the date and time dt21. .. Further, the information processing apparatus 100 stores the estimated emotions of the user U2 at each time point in the storage unit 120 (see FIG. 3) in association with the user U2. The information processing device 100 may acquire information indicating the emotion of the user U2 at each time point from an external information processing device.

In the example of FIG. 1, for the sake of simplicity, the user's operation related to the two push notifications in steps S1-1 and S1-2 is illustrated, but many users are located in the A area. It is assumed that the push notification (for example, 10 million times, etc.) is given, and the information processing apparatus 100 acquires action information such as operation information indicating whether or not the user has opened the notification in response to the push notification. Further, steps S1-1 and S1-2 are for explaining the process, and any of steps S1-1 and S1-2 may be performed first, and steps S1-1 and S1-2 are performed first. May be performed multiple times. Hereinafter, when steps S1-1 and S1-2 are described without distinction, they are collectively referred to as step S1.

Further, the information processing apparatus 100 generates a model used for generating prediction information based on the user's behavior information regarding the push notification acquired in step S1 (step S3). For example, the information processing apparatus 100 generates a model that predicts the user's behavior with respect to the distributed content based on the behavior information of the first user in the A area. For example, the information processing apparatus 100 generates a model that predicts the behavior of the user to whom the content is delivered based on the behavior information of the first user in the area A. For example, the information processing apparatus 100 generates a model that predicts the user's behavior with respect to the delivered content based on the context information of the first user in the A area. For example, the information processing apparatus 100 generates a model that predicts how much the delivered content will be opened and viewed based on the context information. For example, the information processing apparatus 100 generates a model for predicting profitability in push notification based on various information stored in the open data storage unit 121, the user information storage unit 122, the action information storage unit 123, and the like. For example, the information processing apparatus 100 has a model that predicts the user's behavior with respect to the push-notified content based on various information stored in the open data storage unit 121, the user information storage unit 122, the action information storage unit 123, and the like. Generate.

For example, the information processing apparatus 100 generates a model based on the environmental information of the area A stored in the open data storage unit 121. For example, the information processing apparatus 100 generates a model based on the user information of the user located in the A area stored in the user information storage unit 122. For example, the information processing apparatus 100 generates a model based on the behavior information of the user located in the A area stored in the behavior information storage unit 123. Further, for example, the information processing apparatus 100 may generate a model by adding information about the content pushed to the user. For example, the information processing apparatus 100 may generate a model including a feature amount whose element is the category of the content pushed to the user.

Here, the information processing apparatus 100 generates a model including each feature amount corresponding to each element. That is, the information processing apparatus 100 determines the feature amount of the model and learns the weight of each feature amount to generate the model. For example, the information processing apparatus 100 may generate a model using a feature quantity that combines elements of context information by various conventional techniques such as a Kronecker product. For example, the information processing apparatus 100 generates a model including a feature quantity in which two or more elements are combined. For example, the information processing apparatus 100 determines a feature amount that combines elements of context information. For example, the information processing apparatus 100 determines a feature amount that combines elements between each category of context information.

For example, the information processing apparatus 100 has an element group EL1 corresponding to an element of the context (also referred to as a "first element") at a time point different from the content delivery time point in the context information, and an element different from the first element (also referred to as "first element"). The feature amount of the model is determined based on each combination with the element group EL2 corresponding to the "second element"). For example, the information processing apparatus 100 determines each combination of the first element of the element group EL1 and the second element of the element group EL2 as the feature amount of the model. For example, the information processing apparatus 100 has the first element of the element group EL2, such as "plus emotion 5 minutes ago", "minus emotion 1 minute ago", "rain 3 minutes ago", and the like. Each combination with the two elements "30's", "male", "soccer field", etc. is determined as the feature amount of the model.

In the example of FIG. 1, the information processing apparatus 100 corresponds to the feature quantity # 1 corresponding to the combination of positive emotions, 30s and men 5 minutes ago, and the combination of positive emotions, 30s and women 5 minutes ago. The feature amount # 2, the feature amount # 3 corresponding to the combination of positive emotions, 20s and men 5 minutes ago, etc. are determined as the feature amount of the model M1. Although not shown in the example of FIG. 1, the information processing apparatus 100 has a feature amount # 4 corresponding to a combination of positive emotions and men in their thirties and men one minute before, and positive emotions and thirties 30 minutes before. And feature amount # 5 corresponding to the combination of women, feature amount # 11 corresponding to the combination of sunny and soccer field 3 minutes ago, feature amount # 12 corresponding to the combination of rain and soccer field 1 hour ago, etc. The various features of the model M1 are determined as the features of the model M1. For example, the information processing apparatus 100 has elements related to context such as "plus emotion 5 minutes ago", "plus emotion 10 minutes ago", and "rain 1 hour ago" stored in the storage unit 120 (see FIG. 3). The combination may be determined by using the context element list information of the above and the attribute element list information of the elements related to the user's attributes such as "30's", "20's", "male", and "female". For example, the information processing apparatus 100 may generate information indicating each combination by combining the first element selected from the context element list information and the second element selected from the attribute element list information. For example, the information processing apparatus 100 may determine tens of millions or hundreds of millions of features as features to be included in the model M1.

Further, the feature amount included in the model is not limited to the combination of elements, and the information processing apparatus 100 may generate a model including the feature amount corresponding to only one element of the context information. Further, the information processing apparatus 100 may generate a model including a feature amount corresponding to the feature amount in which four or more various elements are combined. For example, the information processing apparatus 100 may generate a model including a feature amount corresponding only to the element "plus emotion 5 minutes ago" and a feature amount corresponding only to the element "rain 3 minutes ago". The combination of the above elements is an example, and may be various combinations such as a combination between elements in the element group EL1.

For example, the information processing apparatus 100 may generate a model that predicts the user's behavior with respect to the push-notified content, using the information when the push-notified content is opened as correct answer information (correct example). For example, the information processing apparatus 100 pushes various context information such as user user information, user position information, user behavior information, and user environment information when the push-notified content is opened as correct answer information. You may generate a model that predicts the user's behavior with respect to the notified content. For example, when the user U1 opens the push-notified content in the partial area LC1-1, the information processing apparatus 100 includes user information of the user U1, position information of the user U1, behavior information of the user U1, and environmental information of the user U1. Various context information such as, etc. may be used as correct answer information to generate a model for predicting the user's behavior with respect to the push-notified content. For example, the information processing apparatus 100 generates the model M1 by using the context information regarding the distribution of the content to the user U1. For example, the information processing apparatus 100 generates the model M1 by using context information regarding a time point different from the time point in which the content is delivered to the user U1. For example, the information processing apparatus 100 generates a model M1 using various context information including the weather at the position of the user U1 and the emotion of the user U1 at a time other than the time when the content is delivered to the user U1. .. For example, the information processing apparatus 100 uses various context information including the weather at the position of the user U1 in the past, the emotion of the user U1, and the like before the time when the content is delivered to the user U1, and the model M1 is used. Generate. Not limited to the past, the information processing apparatus 100 uses various context information including the time after the content is delivered to the user U1, that is, the weather at the position of the user U1 in the future, the emotion of the user U1, and the like. The model M1 may be generated. It should be noted that the information processing apparatus 100 may generate the model M1 by using the context information at the time of distribution of the content to the user U1 as well as the context information in the past or future from the time of distribution of the content to the user U1. good.

In the example of FIG. 1, when the content is opened, the information processing apparatus 100 is set to any of a plurality of levels indicating the degree of the user's behavior regarding profitability based on the viewing time of the user's content after opening the content. Determine the level of user behavior in each delivery as appropriate.

For example, when the browsing time of the user's content is less than 5 seconds, the information processing apparatus 100 predicts by learning to output a score "1" with the level of the user's behavior in the distribution as level LV1. Generate a model to do. For example, in the information processing apparatus 100, when the time RTM1 which is the viewing time of the user U1 shown in FIG. 1 is a predetermined time of less than 5 seconds (for example, 3 seconds), the context information for distribution to the user U1 is input. In this case, a predictive model is generated by learning to output a score “1”.

Further, for example, when the browsing time of the user's content is 5 seconds or more and less than 1 minute, the information processing apparatus 100 learns to output a score "2" with the level of the user's behavior in the distribution as level LV2. By doing so, a model to predict is generated. For example, in the information processing apparatus 100, when the time RTM1 which is the browsing time of the user U1 shown in FIG. 1 is a predetermined time (for example, 30 seconds) of 5 seconds or more and less than 1 minute, the context information in the delivery to the user U1 is When input, a predictive model is generated by learning to output a score "2".

Further, for example, when the user's content viewing time is 1 minute or more and less than 5 minutes, the information processing apparatus 100 learns to output a score "3" with the level of the user's behavior in the distribution as level LV3. By doing so, a model to predict is generated. For example, in the information processing apparatus 100, when the time RTM1 which is the viewing time of the user U1 shown in FIG. 1 is a predetermined time (for example, 2 minutes) of 1 minute or more and less than 5 minutes, the context information in the delivery to the user U1 is When input, a predictive model may be generated by learning to output a score of "3". The above is an example, and the information processing apparatus 100 may use various levels, and the information processing apparatus 100 may generate a model for predicting various profitability, not limited to the viewing time.

Further, for example, the information processing apparatus 100 generates a model for predicting the user's behavior with respect to the push-notified content by using the information when the push-notified content is not opened as incorrect answer information (negative example). May be good. For example, the information processing apparatus 100 predicts by learning to output a score "0" with the level of the user's behavior in the distribution as level LV0 when the user does not open the content. To generate. For example, the information processing apparatus 100 may generate a model for predicting by learning to output a score "0" when context information is input when the push-notified content is not opened. good.

For example, the information processing apparatus 100 uses various context information such as user user information, user position information, user behavior information, and user environment information when the push-notified content is not opened as incorrect answer information. , May generate a model that predicts the user's behavior with respect to the push-notified content. For example, when the user U2 does not open the push-notified content in the partial area LC1-2, the information processing apparatus 100 may use the user information of the user U2, the position information of the user U2, the action information of the user U2, or the user U2. Various context information such as environment information may be used as incorrect answer information to generate a model for predicting the user's behavior with respect to the push-notified content. For example, the information processing apparatus 100 generates the model M1 by using the context information regarding the distribution of the content to the user U2. For example, the information processing apparatus 100 generates the model M1 by using context information regarding a time point different from the time point in which the content is delivered to the user U2. For example, the information processing apparatus 100 generates a model M1 using various context information including the weather at the position of the user U2 and the emotions of the user U2 at a time other than the time when the content is delivered to the user U2. .. For example, the information processing apparatus 100 uses various context information including the weather at the position of the user U2 in the past, the emotion of the user U2, and the like before the time when the content is delivered to the user U2, and uses the model M1. Generate. Not limited to the past, the information processing apparatus 100 uses various context information including the weather at the position of the user U2 in the future, the emotion of the user U1, and the like after the time when the content is delivered to the user U2. The model M1 may be generated.

In the example of FIG. 1, the information processing apparatus 100 generates model information of the model M1 as shown in the model information MD. For example, the information processing apparatus 100 generates the model M1 as shown in the model information storage unit 125 (see FIG. 7).

The model M1 shown in the model information storage unit 125 in FIG. 7 includes "feature amount # 1 (plus emotions 5 minutes ago x 30s x male)" to "feature amount # 3 (plus emotions 5 minutes ago x 20)". Each weight (value) is stored in association with each feature amount (element) such as "dai x male". For example, in the example shown in FIG. 7, the model information regarding the model M1 has a positive emotion 5 minutes ago, and the weight of the feature quantity # 1 corresponding to the combination of the 30s and the male is "0.5", and the weight is positive 5 minutes ago. The weight of feature # 2 corresponding to the combination of emotions, 30s and women is "-0.1", and the weight of feature # 3 corresponding to the combination of emotions, plus emotions, 20s and men 5 minutes ago is "0". .2 ”etc. It should be noted that the generation of each model may be performed by appropriately using various conventional techniques related to machine learning. For example, the model may be generated by using a technique related to machine learning of supervised learning such as SVM (Support Vector Machine). It should be noted that the description regarding the generation of the above model is an example, and the generation of the model may be performed by a learning method appropriately selected according to the information that can be acquired and the like. In this way, the information processing apparatus 100 generates the model M1 by learning the weights of each feature amount such as the feature amount # 1 to the feature amount # 3 of the model M1.

For example, the information processing apparatus 100 receives context information related to content distribution as input, and generates a model M1 that outputs a score based on the input. For example, the information processing apparatus 100 takes context information as an input, and generates a model M1 that outputs a score indicating the possibility of an action on the delivered content by the user corresponding to the input context information. For example, the information processing apparatus 100 takes context information as an input and generates a model M1 that outputs a score indicating the level of the user's behavior (profitability) in the distribution of the content corresponding to the input context information. As shown in the model M11 of FIG. 11, the information processing apparatus 100 may generate a model as the model M1 that outputs a score indicating the probability that the user to whom the content is delivered performs the opening operation action.

Then, the information processing apparatus 100 generates relationship degree information indicating the degree of relationship with the predetermined behavior of the user with respect to the content based on the generated model M1 (step S4). In the example of FIG. 1, the information processing apparatus 100 generates relationship degree information indicating the degree of relationship with the user's opening behavior with respect to the content based on the generated model M1. The information processing apparatus 100 generates relationship degree information indicating the degree of relationship with the user's browsing behavior with respect to the content based on the generated model M1.

For example, the information processing apparatus 100 generates relationship degree information indicating the degree of relationship with a predetermined behavior of the user with respect to the content based on the weight of each feature amount of the model M1. For example, the information processing apparatus 100 generates relationship degree information in which the relationship information corresponding to each feature amount is ranked so that the feature amount having the larger absolute value of the weight has a higher rank among the feature amounts of the model M1. do. Then, the information processing apparatus 100 stores the generated relationship degree information in the relationship degree information storage unit 127.

The “target behavior” in the relationship degree information storage unit 127 of FIG. 1 indicates a predetermined behavior of the target user. Further, the "rank" in the relationship degree information storage unit 127 in FIG. 1 indicates the rank (ranking) of the degree of relationship of each relational information with the target behavior. The "relationship information ID" in the relationship degree information storage unit 127 of FIG. 1 indicates information for identifying the relationship information. The "weight" in the relationship information storage unit 127 of FIG. 1 indicates the weight of the feature amount corresponding to the relationship information. “Element # 1” to “element # 3” in the relationship degree information storage unit 127 in FIG. 1 indicate elements of the feature amount corresponding to the relationship information.

The relationship information storage unit 127 of FIG. 1 shows that the target action is an action for the user's content. For example, it indicates that the target action is an action such as opening the content of the user. Further, the relational information (relationship information ST1) identified by the relational information ID "ST1" corresponds to the feature amount having a weight of "0.5", and the element # 1 is "plus emotion 5 minutes ago". Indicates that element # 2 is "30's" and element # 3 is "male". That is, the relationship information ST1 corresponds to the feature amount # 1 of the model M1.

As described above, in the example of FIG. 1, in the information processing apparatus 100, among the feature quantities of the model M1, the feature quantity # 1 has the largest absolute value of the weight, so that the order of the relational information ST1 corresponding to the feature quantity # 1. Is decided to be the first place. In the information processing apparatus 100, among the feature quantities of the model M1, the combination of the element "plus emotion", "30s" and "male" of the feature quantity # 1 is related to the user's behavior such as opening the content. Generates relationship information indicating that there is. In the information processing device 100, since the weight of the relationship information ST1 of the combination of the elements "plus emotion 5 minutes ago", "30s" and "male" is a positive value, a male user in his 30s acts on the content. In this case, it can be estimated that the user's emotion 5 minutes before the action is likely to be a positive emotion.

Further, in the information processing apparatus 100, among the feature quantities of the model M1, the feature quantity corresponding to the combination of the elements "minus emotion one minute before", "20s", and "female" is the feature quantity whose weight is the absolute value #. Since it is the second largest after 1, the ranking of the relational information ST2 corresponding to the feature amount is determined to be the second place. In the information processing device 100, since the weight of the relationship information ST2 of the combination of the elements "minus emotion one minute ago", "20s" and "female" is a negative value, a female user in her 20s acts on the content. In that case, it can be estimated that it is unlikely that the user's emotion one minute before the action was a negative emotion.

The information processing apparatus 100 may determine the ranking in order from the one with the largest weight of the feature amount. In this case, the information processing apparatus 100 generates relationship degree information indicating that the element of the feature amount having a large weight affects the user's behavior such as opening the content.

Then, the information processing apparatus 100 generates the relational element information based on the generated relational degree information. First, the information processing apparatus 100 determines a target user (target user) for generating related element information (step S5). In the example of FIG. 1, the information processing apparatus 100 determines the user U3 located in the X area as the target user. The information processing apparatus 100 determines the user U3, which is a second user, located in the X area, which is an area other than the A area, as the target user.

Then, in the example of FIG. 1, the content is pushed to the user U3 located in the X area, and the user U3 opens the content. As a result, the information processing device 100 push-notifies the terminal device 10 used by the user U3 of the predetermined content, and acquires information indicating that the content has been opened by the user U3 (step S6). For example, the information processing apparatus 100 acquires behavioral information indicating that the user U3 located in the X area has opened the predetermined content (for example, the content CT11 or the like) that has been push-notified.

Then, the information processing apparatus 100 determines whether or not the behavior of the user U3 satisfies a predetermined criterion. For example, the information processing apparatus 100 determines whether or not the predetermined criteria are satisfied by comparing the behavior information of the user U3 with a predetermined condition on the condition that the content is opened. For example, the information processing apparatus 100 determines that when the behavior information of the user to whom the content is delivered includes the behavior information of opening the content, the information processing apparatus 100 satisfies a predetermined criterion. The predetermined criteria are not limited to the conditions for opening the content, and various conditions and the like may be appropriately set.

Since the information processing apparatus 100 determines that the behavior of the user U3 satisfies a predetermined criterion, the information processing apparatus 100 generates the related element information (step S7). In the example of FIG. 1, the information processing apparatus 100 generates the relational element information by using the information stored in the relational degree information storage unit 127. The information processing apparatus 100 uses the information stored in the relationship information storage unit 127 to generate related element information regarding the opening of the content by the user U3. For example, the information processing apparatus 100 generates related element information regarding the opening of the content by the user U3 based on the attribute information of the user U3 stored in the user information storage unit (see FIG. 4). For example, the information processing apparatus 100 generates related element information regarding the opening of the content by the user U3 based on the age "30s" and the gender "male" which are the attribute information of the user U3.

The information processing apparatus 100 selects the relational information in which the elements include "30's" and "male" from the relational information stored in the relational degree information storage unit 127. For example, the information processing apparatus 100 selects a predetermined number (for example, 5 or 10) of relational information from the one having the highest rank among the relational information including "30s" and "male" as elements. In the example of FIG. 1, the information processing apparatus 100 selects the relational information ST1 or the like in which the elements include "30s" and "male" in order from the highest rank.

Here, since the information processing apparatus 100 has a positive value for the weight of the selected relational information ST1, it is highly likely that the emotion of the target user U3 5 minutes before is "plus".

Further, although not shown, in the example of FIG. 1, the information processing apparatus 100 selects the relational information (relationship information STX) corresponding to the combination of the elements “plus emotion 6 minutes ago” and “30s”. It is assumed that the weight of the relational information STX is a negative value. Therefore, the information processing apparatus 100 estimates that there is a high possibility that the emotion of the target user U3 6 minutes before is not "plus", that is, "minus".

As a result, the information processing apparatus 100 generates the relational element information FINF1 of the user U3 who is the target user located in the X area. In the example of FIG. 1, in the information processing apparatus 100, based on the opening operation of the content of the user U3, the emotion 5 minutes before the user U3 located in the X area is a positive emotion, and the emotion 6 minutes before is a negative emotion. The relational element information FINF1 indicating that it is presumed to be the emotion of is generated. As described above, the information processing apparatus 100 generates the relational element information FINF1 indicating that the emotion of the user U3 was a negative emotion 6 minutes ago and changed to a positive emotion 5 minutes ago. Based on the related element information FINF1, the information processing apparatus 100 estimates that the user U3 who opened the push notification changed from a negative emotion to a positive emotion between 6 minutes and 5 minutes before the opening. As a result, the information processing apparatus 100 is likely to perform the content opening operation for the male user in his thirties to which the user U3 belongs, after the emotion changes from negative to positive, based on the related element information FINF1. Can be estimated. For example, the information processing apparatus 100, based on the relational element information FINF1, for a male user in his thirties to which the user U3 belongs, when the emotion changes from negative to positive between 6 minutes and 5 minutes ago, the content It can be estimated that there is a high possibility that the opening operation will be performed.

As described above, the information processing apparatus 100 can appropriately generate information indicating elements related to the user's behavior by using the generated model M1. In the example of FIG. 1, the information processing apparatus 100 uses the model M1 generated from the information of the first user in the A area and the behavior information of the second user in the X area different from the A area, and the behavior of the second user. Information indicating the elements related to can be appropriately generated. Specifically, the information processing apparatus 100 appropriately obtains information for estimating the context of the X area by using the model M1 generated from the information of the first user in the A area and the behavior information of the second user in the X area. Can be generated.

As a result, the information processing apparatus 100 can appropriately estimate the context. That is, the information processing apparatus 100 reversely estimates the context corresponding to the dependent variable (feature amount) of the model M1 from the information indicating the opening operation of the user's content corresponding to the objective variable (output value (score)) of the model M1. can do. That is, the information processing apparatus 100 reversely estimates the context corresponding to the dependent variable (feature amount) of the model M1 from the objective variable (output value (score)) of the model M1, so that the other information processing device 100 is different from the content distribution time point. The context at the time can be estimated appropriately. In this way, the information processing apparatus 100 can appropriately estimate changes in the context before and after the content distribution time.

In the example of FIG. 1, a male user U3 in his thirties is acting to open the delivered content. Then, the information processing apparatus 100 estimates that the male user U3 in his thirties changed his emotion from negative to positive a few minutes before the content was delivered. Therefore, it can be estimated that the information processing apparatus 100 is more likely to be opened by a group of male users in their thirties if the content is delivered at the timing after the emotion changes from negative to positive. In this way, the information processing apparatus 100 can estimate what kind of emotional change the user is likely to take.

[1-1. Information generation example]
Note that FIG. 1 is an example, and the information processing apparatus 100 may generate various information, not limited to the above. This point will be described below with reference to FIG. FIG. 11 is a diagram showing an example of information processing according to the embodiment. In FIG. 11, the same points as in FIG. 1 may be omitted as appropriate. In the example of FIG. 11, the information processing apparatus 100 (see FIG. 3) pushes to another area AR21 (area B) based on the action information such as the user's operation information regarding the push notification in the predetermined area AR11 (area A). The case of generating the prediction information about the notification is shown. In the example of FIG. 11, push notification is shown as an example as a form of content distribution, but content distribution may be in various modes. For example, the content distribution in the information processing system 1 is not limited to the push notification, and may be a so-called pull-type content distribution in which the content is requested from the terminal device 10.

For example, in the example of FIG. 11, the distribution information of the open rate of the push notification in the B area is accurately generated due to the lack of action information such as the actual user operation information regarding the push notification in the B area. Shows when it is difficult. For example, the push notification may be information output by the terminal device 10 regardless of the operation of the terminal device 10 by the user. For example, push notification may be to actively notify the user of predetermined information. Further, the opening rate referred to here indicates, for example, the rate at which the user has opened the push notification displayed on the terminal device 10. Further, the opening operation may be a predetermined operation of the user such as selection and designation for the push notification. For example, the opening operation may be a predetermined operation of the user for displaying the information related to the push notification on the terminal device 10. For example, in the example of FIG. 11, as shown in step S10, the number of notifications in the B area is assumed to be small. It should be noted that step S10 is for illustrating that the number of notifications in the B area is small, and may not be included in the processing procedure.

First, the map information MP1-1 to MP1-3 shown in FIG. 11 will be briefly described. The map information MP1-1 to MP1-3 shown in FIG. 11 is a diagram schematically showing an area or the like included in a predetermined range. For example, the map information MP1-1 is a diagram schematically showing the status of push notification to the terminal device 10 to the A area and the B area. Further, for example, the map information MP1-2 is a diagram for schematically showing distribution information of the opening rate of the push notification to the terminal device 10 in the A area. Further, for example, the map information MP1-3 is a diagram for schematically showing the prediction information of the opening rate of the push notification to the terminal device 10 in the B area. Further, the range (area) shown in the map information MP1-1 to MP1-3 is the same area. Further, in the following, when the map information MP1-1 to MP1-3 will be described without particular distinction, the map information MP1 will be described.

In the example of FIG. 11, the information processing device 100 push-notifies the terminal device 10 used by a user of the predetermined content, and acquires information indicating that the content has been opened by the user (step S11-1). For example, the information processing apparatus 100 indicates that a predetermined content (for example, content CT11 or the like) is push-notified to the terminal device 10 used by the user U1 (see FIG. 4) located in the A area, and the user U1 opens the package. Get information. For example, the information processing apparatus 100 push-notifies the terminal device 10 used by the user U1 located in the partial area LC1-1 of the A area, and acquires information indicating that the predetermined content has been opened by the user U1. .. The partial area LC1-1 may be an area within a predetermined range in the area A. Further, in the example of FIG. 11, the information processing apparatus 100 may acquire information indicating that the content (content CT11) notified in step S11-1 has been viewed by the user during the time RTM1 after opening. .. For example, the information processing apparatus 100 may acquire information indicating that the content notified in step S11-1 has been displayed on the user's terminal apparatus 10 during the time RTM 1 after opening.

For example, the information processing device 100 stores the information acquired from the terminal device 10 in the action information storage unit 123 (see FIG. 5). The information processing device 100 may provide the content to the terminal device 10, or another device may provide the content as long as the information processing device 100 can acquire the information used for generating the prediction information. .. For example, the content may be provided to the terminal device 10 by any device as long as the information processing device 100 can acquire the information used for generating the prediction information.

Further, in the example of FIG. 11, the information processing apparatus 100 is push-notified to the terminal apparatus 10 used by a certain user, and acquires information indicating that the predetermined content has not been opened by the user (step S11-2). .. For example, the information processing device 100 push-notifies the terminal device 10 used by the user U2 (see FIG. 4) located in the area A, and acquires information indicating that the predetermined content has not been opened by the user U2. For example, the information processing apparatus 100 obtains information indicating that the predetermined content is push-notified to the terminal apparatus 10 used by the user U2 located in the partial area LC1-2 of the A area and is not opened by the user U2. do.

In the example of FIG. 11, for the sake of simplicity, the user's operation related to the two push notifications in steps S11-1 and S11-2 is illustrated, but many users are located in the A area. It is assumed that a push notification (for example, 10 million times, etc.) is given, and the information processing apparatus 100 acquires action information such as operation information indicating whether or not the user has opened the notification in response to the notification. Further, steps S11-1 and S11-2 are for explaining the process, and any of steps S11-1 and S11-2 may be performed first, and steps S11-1 and S11-2 are performed first. May be performed multiple times. Hereinafter, when steps S11-1 and S11-2 are described without distinction, they are collectively referred to as step S11.

Then, the information processing apparatus 100 generates distribution information based on action information such as operation information related to push notification (step S12). For example, the information processing apparatus 100 generates distribution information by calculating the open rate of the content based on the operation information related to the push notification. For example, the information processing apparatus 100 stores the distribution information generated based on the operation information acquired in step S11 in the distribution information storage unit 124 (see FIG. 6). For example, the information processing apparatus 100 stores the distribution information with the area A as the aggregation target area in the distribution information storage unit 124.

The “aggregation target area” shown in the distribution information storage unit 124 in FIG. 6 indicates an area for which distribution information is collected. Further, the "distribution information" shown in the distribution information storage unit 124 in FIG. 6 indicates the distribution information collected for the aggregation target area. The "partial area" shown in the distribution information storage unit 124 in FIG. 6 indicates a partial area in the aggregation target area. The “number of pushes” shown in the distribution information storage unit 124 in FIG. 6 indicates the number of times a push notification is given to a user located in the corresponding partial area. Further, the "opening count" shown in the distribution information storage unit 124 in FIG. 6 indicates the number of times a user located in the corresponding partial area has opened the push notification. Further, the "opening rate (%)" indicates the rate (= number of opening / number of pushes x 100) that the user located in the corresponding partial area opened the push notification. For example, the "opening rate (%)" is a value of 0 to 100 (%). For example, the information processing apparatus 100 calculates the opening rate.

For example, in the example shown in the distribution information storage unit 124 in FIG. 6, the distribution information for the aggregation target area "A area" is "10000 (times)" for the user located in the partial area LC1-1 in the A area. Indicates that a push notification has been made. Further, for example, it indicates that the user located in the partial area LC1-1 has opened the push notification "2000 (times)". Further, for example, the opening rate of the user located in the partial area LC1-1 is "20 (%)" because it has been opened 2,000 times out of 10,000 notifications. For example, the information processing apparatus 100 calculates the opening rate of the user located in the partial area LC1-1 as "20% (= 2000/10000 * 100)".

The information processing apparatus 100 is not limited to the above, and the opening rate may be calculated based on various information. For example, the information processing apparatus 100 may calculate the open rate of the user located in the partial area LC1-1 by using the score itself output by the model M11. For example, the information processing apparatus 100 calculates the average value of the scores output by the model M11 in which the context information of the content distribution in the partial area LC1-1 is input as the open rate of the user located in the partial area LC1-1. May be good. For example, the information processing apparatus 100 calculates the open rate of the user located in the partial area LC1-1 by dividing the total value of the scores output by the model M11 for the content distribution in the partial area LC1-1 by the number of outputs. You may. For example, in the information processing apparatus 100, the total value of the scores output by the model M11 for the content distribution in the partial area LC1-1 is "45 (= 0.2 + 0.5 + ...)", And the number of outputs is "100". In some cases, the open rate of the user located in the partial area LC1-1 may be calculated as "45% (= 45/100 * 100)".

In the example of FIG. 11, the information processing apparatus 100 generates the distribution information DM 11 having the area A as the aggregation target area. The distribution information DM11 shown in the A area of the map information MP1-2 in FIG. 11 shows the high and low of the opening rate in each partial area in a display mode like a heat map. In the example of FIG. 11, it is shown that the area where the hatching is darker, the higher the opening rate is. In the example of FIG. 11, the distribution information DM11 shows that the opening rate is high in the partial area LC1-1 or the like in the A area. Further, in the example of FIG. 11, the distribution information DM11 shows that the opening rate is low in the partial area LC1-2 or the like in the A area. That is, in the A area, the opening rate is high in the vicinity of the central portion thereof, and the opening rate decreases as the distance from the center increases.

Further, the information processing apparatus 100 generates a model used for generating prediction information based on action information such as operation information related to push notification acquired in step S11 (step S13). For example, the information processing apparatus 100 generates a model that predicts whether or not to open the push notification based on the action information such as the operation information in the area A. For example, the information processing apparatus 100 generates a model that predicts a user's behavior (profitability) in distribution of content based on context information. For example, the information processing apparatus 100 generates a model that predicts whether or not the delivered content will be opened based on the context information. For example, the information processing apparatus 100 generates a model that predicts whether or not to open the push notification based on various information stored in the open data storage unit 121, the user information storage unit 122, the action information storage unit 123, and the like. .. For example, the information processing apparatus 100 generates a model based on the environmental information of the area A stored in the open data storage unit 121. For example, the information processing apparatus 100 generates a model based on the user information of the user located in the area A stored in the user information storage unit 122. For example, the information processing apparatus 100 generates a model based on the behavior information of the user located in the A area stored in the behavior information storage unit 123. Further, for example, the information processing apparatus 100 may generate a model by adding information about the content pushed to the user.

For example, the information processing apparatus 100 may generate a model for predicting whether or not to open the push notification, using the information when the push-notified content is opened as correct answer information (correct example). For example, the information processing apparatus 100 may generate the model M11 by learning to output the score "1" when the context information when the push-notified content is opened is input. For example, the information processing apparatus 100 pushes various context information such as user user information, user position information, user behavior information, and user environment information when the push-notified content is opened as correct answer information. You may generate a model that predicts whether to open the notification. For example, when the user U1 opens the push-notified content in the partial area LC1-1, the information processing apparatus 100 includes user information of the user U1, position information of the user U1, behavior information of the user U1, and environmental information of the user U1. Various context information such as, etc. may be used as correct answer information to generate a model for predicting whether to open a push notification.

Further, for example, the information processing apparatus 100 may generate a model for predicting whether or not to open the push notification, using the information when the push-notified content is not opened as incorrect answer information (negative example). .. For example, the information processing apparatus 100 may generate the model M11 by learning to output the score "0" when the context information when the push-notified content is not opened is input. .. For example, the information processing apparatus 100 uses various context information such as user user information, user position information, user behavior information, and user environment information when the push-notified content is not opened as incorrect answer information. , May generate a model that predicts whether to open a push notification. For example, when the user U2 does not open the push-notified content in the partial area LC1-2, the information processing apparatus 100 may use the user information of the user U2, the position information of the user U2, the action information of the user U2, or the user U2. Various context information such as environment information may be used as incorrect answer information, and a model for predicting whether to open the push notification may be generated.

In the example of FIG. 11, the information processing apparatus 100 generates model information of the model M11 as shown in the model information MD. For example, the information processing apparatus 100 generates the model M11 as shown in the model information storage unit 125 (see FIG. 7). For example, the information processing apparatus 100 receives context information related to content distribution as input, and generates a model M11 that outputs a score based on the input. For example, the information processing apparatus 100 takes context information as an input, and generates a model M11 that outputs a score indicating the probability that the user performs a predetermined action in the distribution of the content corresponding to the input context information. In this case, the information processing apparatus 100 may use the score output by the model M11 as a value indicating the probability that the user performs a predetermined action. For example, the information processing apparatus 100 may use the score output by the model M11 as a value indicating the opening probability of opening the content by the user. For example, the information processing apparatus 100 takes context information as an input, and generates a model M11 that outputs a score indicating the degree of possibility that the user performs a predetermined action in the distribution of the content corresponding to the input context information. For example, the information processing apparatus 100 takes context information as an input, and generates a model M11 that outputs a score indicating the degree (level) at which the user performs a predetermined action in the distribution of the content corresponding to the input context information.

For example, in the information processing apparatus 100, when the score output by the model M11 in which context information such as user information and environment information around the user is input is "0.7", the user opens the push notification. It may be determined that the probability of the information processing is "70% (= 0.7 * 100)". For example, the information processing apparatus 100 may associate a score in the range of 0 to 1 output by the model M11 with 0% to 100%. For example, in the information processing apparatus 100, when the score output by the model M11 to which the context information is input is "0", the probability that the user opens the push notification is "0% (= 0 * 100)". May be determined. For example, in the information processing apparatus 100, when the score output by the model M11 to which the context information is input is "1", the probability that the user opens the push notification is "100% (= 1 * 100)". May be determined.

Further, for example, when the model M11 outputs a value less than 0, that is, a negative score, the information processing apparatus 100 may associate the negative score with 0%. For example, if the information processing apparatus 100 determines that the score output by the model M11 into which the context information is input is "-1", the probability that the user opens the push notification is "0%". good. In this case, for example, the information processing apparatus 100 generates the model M11 by learning to output a score of 0 or less when the context information when the push-notified content is not opened is input. You may.

Further, for example, when the model M11 outputs a score having a value larger than 1, the information processing apparatus 100 may associate a score having a value larger than 1 with 100%. For example, the information processing apparatus 100 may determine that the probability that the user opens the push notification is "100%" when the score output by the model M11 into which the context information is input is "3". .. In this way, the information processing apparatus 100 inputs the context information and generates a model M11 that outputs a score indicating the probability (degree) that the user performs a predetermined action in the distribution of the content corresponding to the input context information. May be good. In this case, for example, the information processing apparatus 100 generates the model M11 by learning to output a score of 1 or more when the context information when the push-notified content is opened is input. May be good. For example, the information processing apparatus 100 may generate the model M11 by learning to output a score of 1 or more when context information is input according to the profit from the opened contents.

For example, the information processing apparatus 100 receives context information such as user information and surrounding environment information in which the user is located, and generates a model M11 that outputs a score based on the input. For example, the information processing apparatus 100 takes context information as an input and generates a model M11 that outputs a score based on the input. For example, the information processing apparatus 100 inputs context information such as user information and surrounding environment information in which the user is located, and the score output by the model M11 based on the input is a predetermined threshold value (for example, "0.5"). "Etc.) If it is the above, it may be determined that the user opens the content to be push-notified. For example, the information processing apparatus 100 may store the generated model M11 in the model information storage unit 125 (see FIG. 7). The model M11 shown in FIG. 11 may be the same model as the model M1 shown in FIG. It should be noted that the generation of each model may be performed by appropriately using various conventional techniques related to machine learning. For example, the model may be generated by using a technique related to machine learning of supervised learning such as SVM (Support Vector Machine).

Then, the information processing apparatus 100 generates prediction information based on the generated model M11 (step S14). For example, the information processing apparatus 100 generates prediction information by calculating the opening rate of the content based on the generated model M11. For example, the information processing apparatus 100 generates prediction information about the B area based on the model M11 and various information about the B area which is a prediction target area.

The information processing apparatus 100 acquires open data of the prediction target area. In the example of FIG. 11, the information processing apparatus 100 acquires the environmental information ED of the B area. For example, the information processing apparatus 100 may acquire various information such as environmental information of the B area from the open data storage unit 121 (see FIG. 3).

Further, for example, the information processing apparatus 100 acquires user information located in the prediction target area. In the example of FIG. 11, the information processing apparatus 100 acquires the user information UD of the B area. For example, the information processing apparatus 100 acquires user information as shown in the user information storage unit 122 (see FIG. 4) and user behavior information as shown in the behavior information storage unit 123 (see FIG. 5).

For example, the information processing apparatus 100 may generate prediction information for the B area for a user whose position information stored in the user information storage unit 122 (see FIG. 4) corresponds to the B area. For example, the information processing apparatus 100 generates prediction information of the B area for the user U3 whose position information is the partial area LC2-1 in the B area, the user U4 whose position information is the partial area LC2-2 in the B area, and the like. You may.

For example, the information processing apparatus 100 may predict whether the user U3 will open the push notification by inputting context information such as the user information of the user U3 and the environment information of the user U3 into the model M11. For example, the information processing apparatus 100 inputs various information including the position information and action information of the user U3 into the model M11, and when the model M11 outputs a score less than a predetermined threshold value, the user U3 opens the push notification. It may be determined not to. In this case, the information processing apparatus 100 stores information indicating that the user U3 does not open the push notification in the storage unit 120 (see FIG. 3), or the push notification is performed once in the partial area LC2-1. The indicated information may be stored in the prediction information storage unit 126 (see FIG. 8).

Further, for example, the information processing apparatus 100 may predict whether the user U4 will open the push notification by inputting context information such as the user information of the user U4 and the environment information of the user U4 into the model M11. For example, the information processing apparatus 100 inputs various information including the position information and behavior information of the user U4 into the model M11, and when the model M11 outputs a score equal to or higher than a predetermined threshold value, the user U4 opens the push notification. Then, it may be determined. In this case, the information processing apparatus 100 stores information indicating that the user U4 opens the push notification in the storage unit 120, or indicates that the push notification is performed once in the partial area LC2-2 and is opened. Information may be stored in the prediction information storage unit 126 (see FIG. 8).

For example, the information processing apparatus 100 may generate prediction information for a user located in the B area at a predetermined time zone. For example, the information processing apparatus 100 may generate prediction information corresponding to the B area in the morning for a user located in the B area in the morning time zone (6 o'clock to 10 o'clock). For example, the information processing apparatus 100 may generate prediction information corresponding to the B area at night for a user located in the B area during the night time zone (19:00 to 23:00).

As described above, the information processing apparatus 100 generates prediction information regarding the B area based on the model M11 and various information. For example, the information processing apparatus 100 stores the prediction information with the B area as the prediction target area in the prediction information storage unit 126.

The “prediction target area” shown in the prediction information storage unit 126 in FIG. 8 indicates an area that is a target for generating prediction information. Further, the "prediction information" shown in the prediction information storage unit 126 in FIG. 8 indicates the prediction information generated for the prediction target area. The “partial area” shown in the prediction information storage unit 126 in FIG. 8 indicates a partial area within the prediction target area. The “number of pushes” shown in the prediction information storage unit 126 in FIG. 8 indicates the number of times that the push notification is predicted to be performed to the user located in the corresponding partial area in the generation of the prediction information. Further, the "opening count" shown in the prediction information storage unit 126 in FIG. 8 indicates the number of times that the push notification is predicted to be opened by the user located in the corresponding partial area in the generation of the prediction information. Further, the "opening rate (%)" shown in the prediction information storage unit 126 in FIG. 8 is the ratio (= number of times of opening) that the user located in the corresponding partial area is predicted to open the push notification in the generation of the prediction information. / Number of pushes x 100) is shown. For example, the "opening rate (%)" is a value of 0 to 100 (%). For example, the information processing apparatus 100 calculates the open rate of the user.

For example, in the example shown in the prediction information storage unit 126 in FIG. 8, the prediction information about the prediction target area “B area” is “2000 (times)” for the user located in the partial area LC2-1 in the B area. Indicates that push notifications are expected to occur. Further, for example, it is shown that the user located in the partial area LC2-1 in the B area is expected to open the push notification "40 (times)". Further, for example, the opening rate of the user located in the partial area LC2-1 in the B area is predicted to be opened 40 times out of the 2,000 notifications, so that the opening rate is "2 (%)". Is shown. For example, the information processing apparatus 100 calculates the opening rate of the user located in the partial area LC2-1 as "2% (= 40/2000 * 100)".

In the example of FIG. 11, the information processing apparatus 100 generates the prediction information PM11 having the B area as the prediction target area. The prediction information PM11 shown in the B area of the map information MP1-3 in FIG. 11 shows the high and low of the opening rate in each partial area in a display mode like a heat map. In the example of FIG. 11, it is shown that the region where the hatching is darker, the higher the expected opening rate is. In the example of FIG. 11, the prediction information PM11 shows that the opening rate is high in the lower right partial area or the like in the B area. In the example of FIG. 11, the prediction information PM11 shows that the opening rate is slightly high in the partial area LC2-2 or the like in the B area. Further, in the example of FIG. 11, the prediction information PM11 shows that the opening rate is low in the partial area LC2-1 or the like in the B area. That is, in the B area, the opening rate is high in the vicinity of the lower right portion, and the opening rate decreases as the distance from the lower right portion increases.

As described above, the information processing apparatus 100 generates predictive information for predicting the open rate of the push notification for the B area where the actual result of the push notification is insufficient. As a result, the information processing apparatus 100 can accurately perform various services related to push notification even in the B area where the track record of push notification is insufficient. For example, the information processing apparatus 100 can generate distribution information using the information of an area where information can be easily collected, such as an area with a large population. On the other hand, it is difficult for the information processing apparatus 100 to generate distribution information using the information in an area where the amount of information that can be acquired is not sufficient due to a small population or the like. Therefore, the information processing apparatus 100 can generate the prediction information of the area where the information is insufficient by using the information of the area where the information is sufficient, so that the desired prediction can be made even for the area where the information is insufficient. As described above, the information processing apparatus 100 makes it possible to predict the presence or absence of a predetermined operation of the user in another area where the actual results can be sufficiently acquired, based on the information in the predetermined area where the actual results can be sufficiently acquired. be able to. Further, for example, the information processing apparatus 100 can generate predictive information indicating that the opening rate tends to be high in the vicinity where a specific POI is located. For example, the information processing apparatus 100 can generate prediction information or the like indicating that the open rate tends to be high in an area where there are many users with specific attributes. Further, for example, the information processing apparatus 100 generates prediction information according to a time zone even at the same position, so that prediction information indicating that the opening rate increases at the timing when a predetermined event is performed or the like can be obtained. Can be generated.

As described above, various predictions are possible based on the prediction information generated by the information processing apparatus 100. For example, when the information processing apparatus 100 generates prediction information based on a position (area or the like) and a time (time zone or the like), the generated prediction information makes it possible to predict the timing at which the opening rate increases in a certain area. .. For example, when the information processing apparatus 100 generates prediction information based on position (area, etc.) and time (time zone, etc.), the generated prediction information is in an area near a bus stop and at the timing when students gather. Therefore, it is possible to predict that the opening rate near the bus stop will increase. Further, the information processing apparatus 100 generates prediction information based on the position (area, etc.) and time (time zone, etc.), and the generated prediction information is used in the area near the bus stop and at the timing when students gather. Moreover, it is possible to predict that the opening rate near the bus stop will increase just before the bus arrives.

Further, for example, the information processing apparatus 100 generates prediction information based on the position (area, etc.) and time (time zone, etc.), and the generated prediction information is used to generate an area near the racecourse where an important race is held. Moreover, it is possible to predict that the opening rate in the vicinity of the racecourse will increase at the timing when an important race starts. Further, for example, the information processing apparatus 100 generates prediction information based on the position (area, etc.) and time (time zone, etc.), and the generated prediction information is used to generate an area near the racetrack where an important race is held. Moreover, it is possible to predict that the opening rate in the vicinity of the racetrack will increase at a predetermined timing (for example, 20 minutes before the start of the race) for an important race. Further, the information processing apparatus 100 may use such prediction information to charge a higher fee for advertisement distribution in the area during the time zone when the opening rate is high than in other time zones. Further, for example, the information processing apparatus 100 uses such prediction information to display a unit price on the advertisement space in the content to be delivered to the terminal apparatus 10 located in the area during the time period when the opening rate is high in the area. May be higher than at other times. The above is an example, and the information processing apparatus 100 may use the prediction information for various services.

For example, the information processing apparatus 100 may perform push notification based on the generated prediction information. For example, the information processing apparatus 100 may give a push notification to a user located in a portion of the prediction information PM11 where the hatching is dark (lower right in the B area). Further, for example, the information processing apparatus 100 may provide the generated prediction information to an external information processing apparatus. For example, the information processing device 100 may provide prediction information to an external device that provides a content providing service.

[1-1-1. Generation of prediction information by simulation]
As described above, the information processing apparatus 100 shows a case where the information processing apparatus 100 generates prediction information based on context information such as behavior information of a user located in area B, which is a prediction target area, and surrounding environment information, and model M11. However, prediction information may be generated by a predetermined simulation. In this case, the storage unit 120 of the information processing apparatus 100 may include a simulator information storage unit (not shown) in which various information related to a predetermined simulator such as information about a virtual space is stored. For example, the information processing apparatus 100 may generate prediction information based on the B area on the virtual space that reflects the context information of the flow of people in the B area and the features of the B area.

Further, the model information storage unit 125 of the information processing apparatus 100 may store a model (hereinafter, also referred to as “agent model”) applied to the agent in the simulation. For example, the information processing apparatus 100 may generate a model to be applied to an agent in a simulation. For example, the information processing apparatus 100 generates a model based on the user's behavior information. For example, the information processing apparatus 100 may generate an agent model based on the behavior information of the user in the area A. For example, the information processing apparatus 100 generates an agent model according to each attribute based on the user's behavior information. For example, the information processing apparatus 100 may generate various agent models such as an agent model for a man in his twenties and an agent model for a woman in his twenties based on user behavior information. For example, the information processing apparatus 100 may generate an agent model by adding various environmental information such as open data. For example, the information processing apparatus 100 may store the generated agent model in the model information storage unit 125.

For example, even if the information processing apparatus 100 uses various information related to a predetermined simulator such as information about a virtual space stored in the simulator information storage unit to generate simulation information (simulation log) regarding the behavior of an agent in the predetermined simulator. good. For example, the information processing apparatus 100 may generate simulation information (simulation log) by assigning an agent model stored in the model information storage unit 125 to an agent and performing a simulation regarding push notification and opening thereof. Further, the information processing apparatus 100 may generate prediction information based on the generated simulation information.

For example, the information processing apparatus 100 may generate a simulation log by simulating the behavior of a user (human) in the area B, which is the prediction target area. For example, prediction information may be generated based on a simulation in order to predict the open rate of push notifications in the B area because the number of push notifications to the actual user in the B area is insufficient. ..

For example, the information processing apparatus 100 determines an agent model applied to each agent. For example, the information processing apparatus 100 may determine an agent model to be applied to each agent based on the information regarding the population composition of the B area included in the environmental information ED of the B area. For example, the information processing apparatus 100 may determine an agent model to be applied to each agent based on the population composition of the B area regarding age and gender as attribute information. The attribute information used for the population composition is not limited to age and gender, and various attribute information may be used.

In the following example, it is assumed that the population composition of area B is mostly males in their twenties. For example, the information processing apparatus 100 generates agents for the number of humans (population, etc.) in the B area. In the example of FIG. 11, the information processing apparatus 100 has a population of 50,000 in the B area and generates 50,000 agents. For example, the information processing apparatus 100 assigns attributes to 50,000 agents so as to reflect the population composition in the area A. For example, when the ratio of males in their twenties in the B area is 50%, the information processing apparatus 100 assigns the attributes of males in their twenties to 25,000 agents. Further, for example, when the ratio of females in their twenties in the B area is 20%, the information processing apparatus 100 assigns the attributes of females in their twenties to 10,000 agents.

For example, the information processing apparatus 100 applies an agent model corresponding to a male in his twenties to an agent having an attribute of a male in his twenties. For example, the information processing apparatus 100 applies an agent model corresponding to a male in his twenties to 25,000 agents to which the attribute of a male in his twenties is assigned. Further, for example, the information processing apparatus 100 applies an agent model corresponding to a woman in her twenties to 10,000 agents to which the attribute of a woman in her twenties is assigned.

For example, the information processing apparatus 100 performs a simulation by an agent to which an agent model is applied. For example, each agent applied to the virtual space corresponding to the B area acts according to the agent model assigned to each agent. For example, if an agent to which an agent model corresponding to a man in his twenties is applied receives a push notification at a predetermined timing, does the push notification open according to the context such as the position or situation in the B area at that time? Decide whether or not. Further, for example, when an agent to which an agent model corresponding to a woman in her twenties is applied receives a push notification at a predetermined timing, the push notification is opened according to the context such as the position or situation in the B area at that time. Decide if you want to.

In this way, the information processing apparatus 100 generates a simulation log by causing each agent to perform an action in the virtual space corresponding to the B area. For example, the information processing apparatus 100 may store the generated simulation log in the storage unit 120. For example, the information processing apparatus 100 generates prediction information based on the generated simulation log. For example, the information processing apparatus 100 generates prediction information (prediction information PM11 or the like in FIG. 11) with the B area as the prediction target area based on the simulation log corresponding to the B area.

[1-2. About model generation]
The information processing apparatus 100 may generate a model by various methods, not limited to the above. For example, the information processing apparatus 100 may generate (update) a model by using the information of the generated model. The information processing apparatus 100 may generate (update) the model by feeding back the information of the generated model. For example, the information processing apparatus 100 may generate (update) a model by using the information of the generated model as a constraint condition. For example, the information processing apparatus 100 may generate (update) a model with a feature amount satisfying a predetermined condition as a constraint condition among the information of the generated model.

For example, the information processing apparatus 100 generates a model including the feature amount excluding the feature amount in which the absolute value of the weight is equal to or less than a predetermined threshold value (for example, 0.01, 0.001 or the like) among the generated model information. You may (update). For example, in the information processing apparatus 100, among the generated model M1, the model M1 except for the feature amount (feature amount # X) in which the absolute value of the weight is 0.00001 and is equal to or less than a predetermined threshold value (0.001). May be generated (updated). For example, when the feature amount #X corresponds to the combination of the elements "soccer field" and the "cucumber", the information processing apparatus 100 uses the model M1 by excluding the feature amount corresponding to the combination of the elements having a low relationship. It can be generated (updated) more appropriately.

[2. Information processing device configuration]
Next, the configuration of the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the information processing apparatus according to the embodiment. As shown in FIG. 3, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 includes an input unit (for example, a keyboard, a mouse, etc.) that receives various operations from the administrator of the information processing device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 110 is connected to a network (for example, the network N in FIG. 2) by wire or wirelessly, and transmits / receives information to / from the terminal device 10.

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 120 according to the embodiment includes an open data storage unit 121, a user information storage unit 122, an action information storage unit 123, a distribution information storage unit 124, and a model information storage unit 125. It has a prediction information storage unit 126 and a relationship degree information storage unit 127.

Although not shown, various open data are stored in the open data storage unit 121. For example, the open data storage unit 121 stores open data including traffic information such as road information such as construction work and traffic jams, weather information such as weather and temperature, and economic information such as household budget and consumption. You may.

Although not shown, the storage unit 120 includes a content information storage unit that stores content information such as the content CT11. The content information storage unit stores tag information (for example, soccer, cucumber, etc.) shown in the content of each content in association with information for identifying the content (content ID, etc.). The content information storage unit stores information related to various contents such as the content itself such as the content CT11 and the information indicating the category (for example, sports, entertainment, etc.) of the content such as the content CT11. Although not shown, the storage unit 120 includes a POI information storage unit that stores the facility name of each POI such as a store or a stadium, the location of the facility, the area, and the like. The POI information storage unit stores various information such as a category of each POI in association with information that identifies each POI (such as a POI ID).

(User information storage unit 122)
The user information storage unit 122 according to the embodiment stores various information about the user. For example, the user information storage unit 122 stores various information related to user attributes and various information related to user behavior. FIG. 4 is a diagram showing an example of a user information storage unit according to an embodiment. The user information storage unit 122 shown in FIG. 4 includes items such as "user ID", "age", "gender", "home", "work location", "interest", and "location information".

The "user ID" indicates identification information for identifying a user. Further, "age" indicates the age of the user identified by the user ID. The "age" may be a specific age of the user identified by the user ID, for example, 35 years old. Further, "gender" indicates the gender of the user identified by the user ID.

Further, "home" indicates the location information of the user's home identified by the user ID. In the example shown in FIG. 4, "home" is illustrated with an abstract code such as "LC11", but may be information indicating latitude or longitude. Further, for example, "home" may be a region name or an address.

Further, the "work location" indicates the location information of the user's work location identified by the user ID. In the example shown in FIG. 4, the “work location” is illustrated with an abstract code such as “LC12”, but may be information indicating latitude or longitude. Further, for example, the "work location" may be a region name or an address.

Further, "interest" indicates the interest of the user identified by the user ID. That is, "interest" indicates an object that the user identified by the user ID is highly interested in. In the example shown in FIG. 4, one "interest" is shown for each user, but there may be a plurality of "interests".

Further, the "position information" indicates the user's position information at a predetermined date and time (for example, when the prediction information is generated). For example, the "location information" indicates the latest user location information acquired before a predetermined date and time (for example, when the prediction information is generated). In the example of FIG. 4, the "position information" is illustrated by the abstract reference numeral "LC1-1" or the like, but the "position information" may store specific latitude / longitude information or the like.

For example, in the example shown in FIG. 4, the age of the user identified by the user ID "U1" is "20's", and the gender is "male". Further, for example, the user identified by the user ID "U1" indicates that his / her home is "LC11". Further, for example, the user identified by the user ID "U1" indicates that the work location is "LC12". Further, for example, the user identified by the user ID "U1" indicates that he / she is interested in "economy". For example, for the user U1, it is shown that the position information indicating that the user U1 is located in the partial area LC1-1 of the A area is the position information last acquired before the predetermined date and time, that is, the latest position information.

The user information storage unit 122 is not limited to the above, and may store various information depending on the purpose. For example, the user information storage unit 122 may store other demographic attribute information and psychographic attribute information in addition to age and gender as user attribute information. For example, the user information storage unit 122 may store information such as a name, family structure, and income.

(Behavior information storage unit 123)
The behavior information storage unit 123 according to the embodiment stores various information related to the user's behavior. FIG. 5 is a diagram showing an example of the behavior information storage unit according to the embodiment. For example, the behavior information storage unit 123 stores the user's behavior information for the content provided to the terminal device 10 of each user. The action information storage unit 123 shown in FIG. 5 includes items such as "user ID", "action ID", "type", "content", "date and time", and "position". It should be noted that the user's action is not limited to the action actively performed by the user, and may include various actions such as an action performed on the user, that is, a passive action by the user.

The "user ID" indicates identification information for identifying a user. For example, the user identified by the user ID "U1" corresponds to the user U1 shown in the example of FIG. Further, the "behavior ID" indicates information that identifies the user's behavior. Further, "type" indicates information regarding the type of action of the corresponding user. Further, "content" indicates the content targeted in the corresponding user's behavior. The "date and time" indicates the date and time when the corresponding user's action was performed. Although the "date and time" is abstractly illustrated as "dt11" or the like, a specific date and time such as "September 13, 2018 22:31:52" may be stored.

Further, the "position" indicates the position information of the user corresponding to the action of the user. For example, "position" indicates the user's position information when the user's action information is acquired. In the example of FIG. 5, the "position" is illustrated by an abstract reference numeral "LC1-1" or the like, but specific latitude / longitude information or the like may be stored in the "position information". Further, the "location information" may include a POI (point of interest) name indicating a facility name such as a store or a stadium, an area, or the like.

For example, in the example of FIG. 5, the user (user U1) identified by the user ID “U1” is an action identified by the action ID “AC11” (behavior AC11) or an action identified by the action ID “AC12” (user U1). It indicates that the action AC12) etc. was performed. Specifically, in the example of FIG. 5, it is shown that the notification (behavior AC11) of the content CT11 is performed for the user U1 located in the partial area LC1-1 at the date and time dt11. For example, the action AC 11 indicates that the content CT 11 is provided to the terminal device 10 used by the user U1 by push notification at the date and time dt11. Further, in the example of FIG. 5, it is shown that the user U1 has performed an operation (behavior AC12) to open the content CT11 in the partial area LC1-1 at the date and time dt12 after the content CT11 is push-notified at the date and time dt11. .. Further, in the example of FIG. 5, it is shown that the user U1 browses the content CT11 (behavior AC13) during the time RTM1 (for example, 5 minutes, 10 minutes, etc.). For example, it is shown that the user U1 browses the content CT11 (behavior AC13) in the partial area LC1-1 over the time RTM1 between the date and time dt12 and the date and time dt13.

The behavior information storage unit 123 is not limited to the above, and may store various information depending on the purpose. For example, the action information storage unit 123 may store the user's position information when each action information is acquired in association with each action information. Further, FIG. 5 shows a case where the action information is stored in the action information storage unit 123 for each user ID, but the action information is not limited to each user ID and may be stored, for example, in chronological order.

(Distribution information storage unit 124)
The distribution information storage unit 124 according to the embodiment stores various information regarding the distribution. FIG. 6 is a diagram showing an example of a distribution information storage unit according to an embodiment. For example, the distribution information storage unit 124 stores the distribution information of each aggregation target area. The distribution information storage unit 124 shown in FIG. 6 includes items such as “aggregation target area” and “distribution information”. The "distribution information" includes items such as "partial area", "push count", "open count", and "open rate (%)".

The “aggregation target area” indicates an area for which distribution information is collected. Further, "distribution information" indicates distribution information collected for the aggregation target area. “Partial area” indicates a partial area within the aggregation target area. "Number of pushes" indicates the number of times a push notification is given to a user located in the corresponding partial area. Further, the "opening count" indicates the number of times that the user located in the corresponding partial area has opened the push notification. Further, the "opening rate (%)" indicates the rate at which the user located in the corresponding partial area opens the push notification (= number of opens / number of pushes x 100). For example, the "opening rate (%)" is a value of 0 to 100 (%).

For example, in the example shown in FIG. 6, it is shown that distribution information has been collected for the aggregation target area “A area”. The aggregation target area "A area" corresponds to the area AR11 in FIG. For example, it indicates that the push notification of "10000 (times)" has been performed to the user located in the partial area LC1-1 in the aggregation target area "A area". Further, for example, it indicates that the user located in the partial area LC1-1 in the aggregation target area “A area” has opened the push notification “2000 (times)”. Further, for example, the opening rate of the user located in the partial area LC1-1 in the aggregation target area "A area" is "20 (%)" because the opening rate is 2,000 times out of 10,000 notifications. Indicates that.

The distribution information storage unit 124 is not limited to the above, and may store various information depending on the purpose.

(Model information storage unit 125)
The model information storage unit 125 according to the embodiment stores information about the model. For example, the model information storage unit 125 stores model information used for generating prediction information. FIG. 7 is a diagram showing an example of a model information storage unit according to an embodiment. The model information storage unit 125 shown in FIG. 7 corresponds to the model M1 or the like as model information from "feature amount # 1 (plus emotion x 30s x male 5 minutes ago)" to "feature amount # 3 (5 minutes)". It has items such as "plus emotions x 20s x men)".

For example, in the example shown in FIG. 7, the model information regarding the model M1 has a positive emotion 5 minutes ago, and the weight of the feature quantity # 1 corresponding to the combination of the 30s and the male is "0.5", and the weight is positive 5 minutes ago. The weight of feature # 2 corresponding to the combination of emotions, 30s and women is "-0.1", and the weight of feature # 3 corresponding to the combination of emotions, plus emotions, 20s and men 5 minutes ago is "0". .2 ”etc. For example, when the features (features) of the model are represented by an m-dimensional vector, the number of features (features) is m, and the weights of the features ## 1 to # m are stored. For example, the weight of each feature is a real number and may be a negative value.

The model information storage unit 125 is not limited to the above, and may store various model information depending on the purpose. For example, the model information storage unit 125 may store various model information such as a probability model.

(Prediction information storage unit 126)
The prediction information storage unit 126 according to the embodiment stores various information related to prediction. For example, the prediction information storage unit 126 stores various information related to the prediction and various information generated by the prediction. FIG. 8 is a diagram showing an example of the prediction information storage unit according to the embodiment. The prediction information storage unit 126 shown in FIG. 8 includes items such as “prediction target area” and “prediction information”. The "prediction information" includes items such as "partial area", "push count", "open count", and "open rate (%)".

The “prediction target area” indicates an area for which forecast information is generated. Further, the "prediction information" indicates the prediction information generated for the prediction target area. “Partial area” indicates a partial area within the prediction target area. The “number of pushes” indicates the number of times that the push notification is predicted to be performed to the user located in the corresponding partial area in the generation of the prediction information. Further, the "opening count" indicates the number of times that the push notification is predicted to be opened by the user located in the corresponding partial area in the generation of the prediction information. Further, the “opening rate (%)” indicates the ratio (= number of opening / number of pushes × 100) that the user located in the corresponding partial area is expected to open the push notification in the generation of the prediction information. For example, the "opening rate (%)" is a value of 0 to 100 (%).

For example, in the example shown in FIG. 8, it is shown that the prediction information is generated for the prediction target area “B area”. The prediction target area "B area" corresponds to the area AR21 in FIG. For example, it indicates that it is predicted that the push notification of "2000 (times)" will be performed to the user located in the partial area LC2-1 in the prediction target area "B area". Further, for example, it is shown that the user located in the partial area LC2-1 in the prediction target area “B area” is predicted to open the push notification “40 (times)”. Further, for example, since the opening rate of the user located in the partial area LC2-1 in the prediction target area "B area" is predicted to be opened 40 times out of 2,000 notifications, "2 (%). ) ”.

The prediction information storage unit 126 is not limited to the above, and may store various information depending on the purpose.

(Relationship information storage unit 127)
The relationship degree information storage unit 127 according to the embodiment stores various information related to the elements related to the predetermined behavior of the user. For example, the relationship degree information storage unit 127 stores various information related to the feature amount related to the predetermined behavior of the user among the feature amounts of the model for predicting the predetermined behavior of the user. FIG. 9 is a diagram showing an example of a relationship degree information storage unit according to an embodiment. The relationship degree information storage unit 127 shown in FIG. 9 has items such as "target action", "rank", "relationship information ID", "weight", "element # 1", "element # 2", and "element # 3". Is included. In the relationship degree information storage unit 127, not only "element # 1" to "element # 3" but also "element # 4", "element # 5", and other items corresponding to the number of elements corresponding to the feature amount are included. included.

The "target behavior" indicates a predetermined behavior of the target user. In addition, the "rank" indicates the rank (ranking) of the degree of the relationship between each related information and the target behavior. In the example of FIG. 9, “ranking” indicates a case where the higher the absolute value of the weight of each relational information is, the higher the ranking is assigned. The "relationship information ID" indicates information for identifying the relational information. The "weight" indicates the weight of the feature amount corresponding to the relational information. “Element # 1” to “element # 3” and the like indicate elements of the feature amount corresponding to the relational information.

In the example shown in FIG. 9, it is shown that the target action is an action for the user's content. For example, it indicates that the target action is an action such as opening the content of the user. Further, the relational information (relationship information ST1) identified by the relational information ID "ST1" corresponds to the feature amount having a weight of "0.5", and the element # 1 is "plus emotion 5 minutes ago". Indicates that element # 2 is "30's" and element # 3 is "male". That is, the relationship information ST1 corresponds to the feature amount # 1 of the model M1.

The relationship degree information storage unit 127 is not limited to the above, and may store various information depending on the purpose.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device inside the information processing device 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). Various programs (corresponding to an example of a decision program and an information processing program) are realized by executing the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 130 includes an acquisition unit 131, a determination unit 132, a generation unit 133, and a provision unit 134, and realizes or executes an information processing function or operation described below. .. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it is configured to perform information processing described later.

(Acquisition unit 131)
The acquisition unit 131 acquires various types of information. The acquisition unit 131 acquires various information from an external device such as the terminal device 10. The acquisition unit 131 acquires various information from the storage unit 120. The acquisition unit 131 acquires various information from an external information processing device. The acquisition unit 131 is provided with various information from the open data storage unit 121, the user information storage unit 122, the action information storage unit 123, the distribution information storage unit 124, the model information storage unit 125, the prediction information storage unit 126, and the relationship degree information storage unit 127. To get. The acquisition unit 131 acquires the behavior information of a predetermined user. The acquisition unit 131 acquires information regarding open data. The acquisition unit 131 acquires action information such as position information from the terminal device 10.

The acquisition unit 131 acquires relationship degree information indicating the degree of relationship between each element of the context regarding another time point different from the content delivery time point and the predetermined action of the first user with respect to the content. The acquisition unit 131 has the relationship degree information generated based on other action information related to the predetermined action of the first user located in the predetermined area, and the second user located in another area different from the predetermined area. Get the behavior information of.

The acquisition unit 131 acquires a model that includes each feature amount corresponding to each element and is used for predicting a predetermined behavior of the user with respect to the content based on the context information of the context. The acquisition unit 131 acquires a model that outputs a score related to a predetermined action of the user with respect to the content in response to the input of the context information. The acquisition unit 131 acquires the correct answer information, which is the behavior information regarding the user's predetermined behavior, and the model generated based on the context information for the content delivered to the user. The acquisition unit 131 acquires relationship degree information indicating the degree of relationship between each element including the user's emotion at another time point and a predetermined action of the first user with respect to the content. The acquisition unit 131 acquires relationship degree information indicating the degree of relationship between each element including the user's emotion at another time point before the content delivery time point and the predetermined action of the first user with respect to the content. ..

The acquisition unit 131 acquires behavioral information such as operation information indicating the presence or absence of a predetermined operation of the user with respect to the content delivered to the terminal device 10 used by the user located in the predetermined area. The acquisition unit 131 acquires behavioral information such as operation information indicating the presence or absence of a predetermined operation of the user with respect to the push-notified content in the terminal device used by the user located in the predetermined area. The acquisition unit 131 acquires behavioral information such as operation information indicating whether or not the user has opened the content pushed by the terminal device used by the user located in a predetermined area.

The acquisition unit 131 acquires action information such as operation information associated with the user's position information when the user performs a predetermined operation on the push-notified content in the predetermined area. The acquisition unit 131 acquires action information such as operation information associated with time information when the user performs a predetermined operation for the push-notified content in the predetermined area. The acquisition unit 131 acquires action information such as operation information associated with context information when a user performs a predetermined operation on the content pushed and notified in a predetermined area. The acquisition unit 131 acquires behavior information such as operation information associated with environmental information related to a predetermined area when the user performs a predetermined operation with respect to the push-notified content in the predetermined area.

In the example of FIG. 1, the acquisition unit 131 is push-notified to the terminal device 10 used by a certain user, and acquires information indicating that the content has been opened by the user. The acquisition unit 131 pushes the terminal device 10 used by the user U1 located in the area A to notify the terminal device 10, and acquires information indicating that the content has been opened by the user U1. The acquisition unit 131 pushes the terminal device 10 used by the user U1 located in the partial area LC1-1 of the A area to notify the terminal device 10, and acquires information indicating that the content has been opened by the user U1.

The acquisition unit 131 acquires information indicating that the notified content (content CT11) has been viewed by the user during the time RTM1 after opening. The acquisition unit 131 may acquire information indicating that the content notified in step S1-1 has been displayed on the user's terminal device 10 during the time RTM 1 after opening.

The acquisition unit 131 acquires information indicating that the predetermined content has been push-notified to the terminal device 10 used by a certain user and has not been opened by the user. The acquisition unit 131 acquires information indicating that the predetermined content has been push-notified to the terminal device 10 used by the user U2 located in the A area and has not been opened by the user U2. The acquisition unit 131 acquires information indicating that the predetermined content has been push-notified to the terminal device 10 used by the user U2 located in the partial area LC1-2 of the A area and has not been opened by the user U2.

The acquisition unit 131 pushes and notifies the terminal device 10 used by the user U3 of the predetermined content, and acquires information indicating that the content has been opened by the user U3. The acquisition unit 131 acquires behavioral information indicating that the user U3 located in the X area has opened the predetermined content (for example, content CT11 or the like) that has been push-notified.

The acquisition unit 131 acquires the open data of the prediction target area. In the example of FIG. 11, the acquisition unit 131 acquires the environmental information ED of the B area. The acquisition unit 131 may acquire various information such as environmental information of the B area from the open data storage unit 121 (see FIG. 3).

In addition, the acquisition unit 131 acquires user information located in the prediction target area. In the example of FIG. 11, the acquisition unit 131 acquires the user information UD of the B area. The acquisition unit 131 acquires user information as shown in the user information storage unit 122 (see FIG. 4) and user behavior information as shown in the behavior information storage unit 123 (see FIG. 5).

(Decision unit 132)
The determination unit 132 determines various information. The determination unit 132 determines various information. The determination unit 132 determines various information based on the various information stored in the storage unit 120. The determination unit 132 determines various information based on the various information stored in the storage unit 120. The determination unit 132 is based on the open data storage unit 121, the user information storage unit 122, the behavior information storage unit 123, the distribution information storage unit 124, the model information storage unit 125, the prediction information storage unit 126, the relationship degree information storage unit 127, and the like. And decide various information. The determination unit 132 is based on the open data storage unit 121, the user information storage unit 122, the behavior information storage unit 123, the distribution information storage unit 124, the model information storage unit 125, the prediction information storage unit 126, the relationship degree information storage unit 127, and the like. To determine various information. The determination unit 132 determines various information based on the various information acquired by the acquisition unit 131. The determination unit 132 determines various information based on the various information acquired by the acquisition unit 131. The determination unit 132 determines various information based on the various information generated by the generation unit 133. The determination unit 132 determines various information based on the various information generated by the generation unit 133. The determination unit 132 determines the model to be used for generating the prediction information. In the example of FIG. 11, the determination unit 132 determines the model used for generating the prediction information in the model M11.

In the example of FIG. 1, the determination unit 132 generates a model including a feature quantity in which two or more elements are combined. For example, the determination unit 132 determines a feature amount that combines elements of context information. For example, the determination unit 132 determines a feature amount that combines elements between each category of context information.

For example, the determination unit 132 includes an element group EL1 corresponding to the first element of the context at a time point different from the content delivery time point, and an element group EL2 corresponding to the second element different from the first element in the context information. Based on each combination of, the features of the model are determined. For example, the determination unit 132 determines each combination of the first element of the element group EL1 and the second element of the element group EL2 as the feature amount of the model. For example, the determination unit 132 includes the first element of the element group EL1, "plus emotion 5 minutes ago", "minus emotion 1 minute ago", "rain 3 minutes ago", and the like, and the second element group EL2. Each combination with the elements "30's", "male", "soccer field", etc. is determined as the feature amount of the model.

The decision unit 132 has a feature amount # 1 corresponding to a combination of positive emotions, 30s and men 5 minutes before, and a feature amount # 2 and 5 corresponding to a combination of positive emotions, 30s and women 5 minutes ago. Minutes before, the feature amount # 3 corresponding to the combination of positive emotions, 20s and men is determined as the feature amount of the model M1. Since the feature amount # 1 has the largest absolute value of the weight among the feature amounts of the model M1, the determination unit 132 determines the rank of the relational information ST1 corresponding to the feature amount # 1 to the first place. In the determination unit 132, among the feature quantities of the model M1, the feature quantity corresponding to the combination of the elements "minus emotion one minute before", "20s" and "female" has the absolute value of the weight next to the feature quantity # 1. Therefore, the ranking of the relational information ST2 corresponding to the feature amount is determined to be the second place.

The determination unit 132 generates the relational element information based on the generated relational degree information. The determination unit 132 determines a target user (target user) for generating the related element information. The determination unit 132 determines the user U3 located in the X area as the target user. The determination unit 132 determines the user U3, which is a second user, located in the X area, which is an area other than the A area, as the target user.

The determination unit 132 determines whether or not the behavior of the user U3 satisfies a predetermined criterion. For example, the determination unit 132 determines whether or not the predetermined criteria are satisfied by comparing the behavior information of the user U3 with a predetermined condition on the condition that the content is opened. For example, when the behavior information of the user to whom the content is delivered includes the behavior information of opening the content, the determination unit 132 determines that the predetermined criterion is satisfied.

The determination unit 132 inputs user information, surrounding environment information in which the user is located, and the like, and the score output by the model M11 based on the input is equal to or higher than a predetermined threshold value (for example, "0.5"). In some cases, it may be determined that the user opens the push-notified content. The determination unit 132 inputs various information including the position information and action information of the user U3 into the model M11, and if the model M11 outputs a score less than a predetermined threshold value, the determination unit 132 determines that the user U3 does not open the push notification. You may. The determination unit 132 inputs various information including the position information and action information of the user U4 into the model M11, and determines that the user U4 opens the push notification when the model M11 outputs a score equal to or higher than a predetermined threshold value. You may.

The determination unit 132 determines an agent model to be applied to each agent. The determination unit 132 may determine an agent model to be applied to each agent based on the information regarding the population composition of the B area included in the environmental information ED of the B area. The determination unit 132 may determine an agent model to be applied to each agent based on the population composition of area B regarding age and gender as attribute information.

(Generation unit 133)
The generation unit 133 generates various information. The generation unit 133 estimates various information. The generation unit 133 selects various information. The generation unit 133 extracts various information. The generation unit 133 calculates various information. The generation unit 133 estimates various information based on the various information stored in the storage unit 120. The generation unit 133 selects various information based on the various information stored in the storage unit 120. The generation unit 133 extracts various information based on the various information stored in the storage unit 120. The generation unit 133 calculates various information based on the various information stored in the storage unit 120. The generation unit 133 is based on the open data storage unit 121, the user information storage unit 122, the behavior information storage unit 123, the distribution information storage unit 124, the model information storage unit 125, the prediction information storage unit 126, the relationship degree information storage unit 127, and the like. And estimate various information. The generation unit 133 is based on the open data storage unit 121, the user information storage unit 122, the behavior information storage unit 123, the distribution information storage unit 124, the model information storage unit 125, the prediction information storage unit 126, the relationship degree information storage unit 127, and the like. And select various information. The generation unit 133 is based on the open data storage unit 121, the user information storage unit 122, the behavior information storage unit 123, the distribution information storage unit 124, the model information storage unit 125, the prediction information storage unit 126, the relationship degree information storage unit 127, and the like. And extract various information. The generation unit 133 estimates various information based on the various information acquired by the acquisition unit 131. The generation unit 133 selects various information based on the various information acquired by the acquisition unit 131. The generation unit 133 extracts various information based on the various information acquired by the acquisition unit 131. The generation unit 133 estimates the user's context using the information acquired by the acquisition unit 131.

The generation unit 133 generates various information stored in the storage unit 120. The generation unit 133 generates distribution information stored in the distribution information storage unit 124. The generation unit 133 generates a model stored in the model information storage unit 125. The generation unit 133 generates the prediction information stored in the prediction information storage unit 126.

The generation unit 133 is an element related to the predetermined behavior of the second user based on the behavior information and the relationship degree information when the behavior information regarding the predetermined behavior of the second user to which the content is delivered is acquired. Generates relational element information indicating. The generation unit 133 generates relationship element information indicating an element related to a predetermined action in another area based on the action information and the relationship degree information.

The generation unit 133 generates the relational element information based on the model. When the behavior information of the second user satisfies a predetermined condition, the generation unit 133 generates the relational element information based on the model. The generation unit 133 generates the relational element information based on the relational degree information indicating the weight of each feature amount in the model. The generation unit 133 generates the relational element information by selecting a feature amount whose corresponding weight satisfies a predetermined condition from each feature amount of the model. The generation unit 133 generates the relational element information by selecting a feature amount whose absolute value of the corresponding weight is equal to or larger than a predetermined threshold value among the feature amounts of the model.

In the example of FIG. 1, the generation unit 133 generates the model information of the model M1 as shown in the model information MD. For example, the generation unit 133 generates the model M1 as shown in the model information storage unit 125 (see FIG. 7). The generation unit 133 generates the model M1 by learning the weights of each feature amount such as the feature amount # 1 to the feature amount # 3 of the model M1.

Based on the generated model M1, the generation unit 133 generates relationship degree information indicating the degree of relationship with the predetermined behavior of the user with respect to the content. The generation unit 133 generates relationship degree information indicating the degree of relationship with the user's opening behavior with respect to the content based on the generated model M1. The generation unit 133 generates relationship degree information indicating the degree of relationship with the user's browsing behavior with respect to the content based on the generated model M1.

For example, the generation unit 133 generates relationship degree information indicating the degree of relationship with the predetermined behavior of the user with respect to the content, based on the weight of each feature amount of the model M1. For example, the generation unit 133 generates relationship degree information in which the relationship information corresponding to each feature amount is ranked so that the feature amount having the larger absolute value of the weight has a higher rank among the feature amounts of the model M1. ..

In the example of FIG. 1, the generation unit 133 generates the model information of the model M1 as shown in the model information MD. For example, the generation unit 133 generates the model M1 as shown in the model information storage unit 125 (see FIG. 7). The generation unit 133 generates the model M1 by learning the weights of each feature amount such as the feature amount # 1 to the feature amount # 3 of the model M1.

For example, the generation unit 133 generates relationship degree information indicating the degree of relationship with the predetermined behavior of the user with respect to the content, based on the weight of each feature amount of the model M1. For example, the generation unit 133 generates relationship degree information in which the relationship information corresponding to each feature amount is ranked so that the feature amount having the larger absolute value of the weight has a higher rank among the feature amounts of the model M1. ..

Since the generation unit 133 determines that the behavior of the user U3 satisfies a predetermined criterion, the generation unit 133 generates the related element information. In the example of FIG. 1, the generation unit 133 generates the relational element information by using the information stored in the relational degree information storage unit 127. The generation unit 133 uses the information stored in the relationship information storage unit 127 to generate related element information regarding the opening of the content by the user U3. For example, the generation unit 133 generates related element information regarding the opening of the content by the user U3 based on the attribute information of the user U3 stored in the user information storage unit (see FIG. 4). For example, the generation unit 133 generates related element information regarding the opening of the content by the user U3 based on the age "30s" and the gender "male" which are the attribute information of the user U3.

The generation unit 133 selects the relationship information in which the elements include "30's" and "male" from the relationship information stored in the relationship degree information storage unit 127. For example, the generation unit 133 selects a predetermined number (for example, 5 or 10) of relational information from the one having the highest rank among the relational information including "30s" and "male" as elements. In the example of FIG. 1, the generation unit 133 selects the relational information ST1 or the like in which the elements include "30s" and "male" in order from the highest rank.

The generation unit 133 generates the relational element information FINF1 of the user U3 who is the target user located in the X area. In the example of FIG. 1, the generation unit 133 has a positive emotion 5 minutes before the user U3 located in the X area and a negative emotion 6 minutes before, based on the opening operation of the content of the user U3. Generates relational element information FINF1 indicating that it is presumed to be an emotion.

When the content is delivered to the terminal device 10 used by the user located in a different area from the predetermined area, the generation unit 133 is based on the action information such as the operation information acquired by the acquisition unit 131. Generates predictive information that predicts the presence or absence of a predetermined operation of the user on the content. The generation unit 133 pushes the content to the terminal device used by the user located in another area different from the predetermined area based on the action information such as the operation information acquired by the acquisition unit 131. Generates predictive information that predicts the presence or absence of a predetermined operation of the user on the content. When the content is push-notified to the terminal device used by the user located in another area based on the action information such as the operation information acquired by the acquisition unit 131, the generation unit 133 of the generation unit 133 for the content. Generates predictive information that predicts the presence or absence of an opening operation.

The generation unit 133 generates prediction information that predicts the position where the user performs a predetermined operation for the content to be push-notified in another area based on the action information such as the operation information. The generation unit 133 generates prediction information that predicts the time for the user to perform a predetermined operation for the content to be push-notified in another area based on the action information such as the operation information.

The generation unit 133 predicts the presence or absence of a predetermined operation of the user for the content to be push-notified in the other area based on the action information such as the operation information and the context information of the user located in the other area. Generate forecast information. The generation unit 133 generates prediction information that predicts the presence or absence of a predetermined operation of the user for the content to be push-notified in the other area, based on the action information such as the operation information and the environment information about the other area. do.

Based on the action information such as the operation information, the generation unit 133 generates distribution information indicating the distribution of the user who performs a predetermined operation for the content to be push-notified in another area as the prediction information. The generation unit 133 generates, as prediction information, a distribution map showing the distribution in other areas of the user who performs a predetermined operation for the content to be push-notified in other areas based on the action information such as the operation information. ..

The generation unit 133 generates distribution information based on action information such as operation information related to push notification. In the example of FIG. 11, the generation unit 133 generates the distribution information DM 11 having the A area as the aggregation target area. The generation unit 133 generates a model used to generate prediction information based on behavior information such as operation information related to push notification. The generation unit 133 generates a model that predicts whether or not to open the push notification based on the action information such as the operation information in the A area.

The generation unit 133 generates a model for predicting whether to open the push notification based on various information stored in the open data storage unit 121, the user information storage unit 122, the action information storage unit 123, and the like. The generation unit 133 generates a model based on the environmental information of the area A stored in the open data storage unit 121. The generation unit 133 generates a model based on the user information of the user located in the A area stored in the action information storage unit 123. The generation unit 133 generates a model based on the behavior information of the user located in the A area stored in the user information storage unit 122. The generation unit 133 may generate a model by adding information about the content to be push-notified to the user.

The generation unit 133 may generate a model for predicting whether or not to open the push notification, using the information when the push notification content is opened as correct answer information (correct example). The generation unit 133 opens the push notification by using various context information such as the user information of the user, the position information of the user, the behavior information of the user, and the environment information of the user when the content to be pushed notification is opened as correct answer information. You may generate a model that predicts whether or not to do so. When the user U1 opens the content to be push-notified in the partial area LC1-1, the generation unit 133 includes various information such as user information of the user U1, position information of the user U1, behavior information of the user U1, and environmental information of the user U1. You may generate a model that predicts whether to open the push notification by using the context information of.

Further, the generation unit 133 may generate a model for predicting whether or not to open the push notification, using the information when the push notification content is not opened as incorrect answer information (negative example). The generation unit 133 uses various context information such as user information of the user, location information of the user, behavior information of the user, and environment information of the user when the content to be pushed notification is not opened as incorrect answer information, and push notification. You may generate a model that predicts whether to open the package. When the content pushed by the user U2 in the partial area LC1-2 is not opened, the generation unit 133 may use the user information of the user U2, the position information of the user U2, the behavior information of the user U2, the environment information of the user U2, and the like. You may generate a model that predicts whether to open the push notification by using various context information of the above as incorrect information.

In the example of FIG. 11, the generation unit 133 generates the model information of the model M11 as shown in the model information MD. The generation unit 133 generates the model M11 as shown in the model information storage unit 125 (see FIG. 7). The generation unit 133 receives context information including user information and surrounding environment information in which the user is located, and generates a model M11 that outputs a score based on the input. The generation unit 133 uses the context information as an input and generates a model M11 that outputs a score based on the input. The generation unit 133 generates prediction information based on the generated model M11. The generation unit 133 generates prediction information about the B area based on the model M11 and various information about the B area which is the prediction target area.

The generation unit 133 may generate prediction information for a user located in the B area at a predetermined time zone. The generation unit 133 may generate prediction information corresponding to the B area in the morning for a user located in the B area in the morning time zone (6 o'clock to 10 o'clock). The generation unit 133 may generate prediction information corresponding to the B area at night for users located in the B area during the night time zone (19:00 to 23:00).

In the example of FIG. 11, the generation unit 133 generates the prediction information PM11 having the B area as the prediction target area. The generation unit 133 generates predictive information for predicting the open rate of push notifications for the B area where the actual results of push notifications are insufficient.

(Providing section 134)
The providing unit 134 provides various information. The providing unit 134 provides various information to an external information processing device. The providing unit 134 provides various information to the terminal device 10. The providing unit 134 provides various information to an external information processing device such as the terminal device 10. The providing unit 134 transmits various information to the terminal device 10. The providing unit 134 distributes various information to the terminal device 10. The providing unit 134 provides various information based on various information acquired by the acquiring unit 131. The providing unit 134 provides various information based on various information determined by the determining unit 132. The providing unit 134 provides various information based on various information generated by the generating unit 133. The providing unit 134 may provide various services based on the prediction information generated by the generating unit 133.

The providing unit 134 may perform a push notification based on the generated prediction information. In the example of FIG. 11, the providing unit 134 may give a push notification to a user located in a portion where hatching is dark (lower right in the B area) in the prediction information PM11. The providing unit 134 may provide the generated prediction information to an external information processing device. The providing unit 134 may provide prediction information to an external device that provides a content providing service.

[3. Information processing flow]
Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 10 is a flowchart showing an example of information processing according to the embodiment.

As shown in FIG. 10, the information processing apparatus 100 acquires relationship degree information indicating the degree of relationship between each element of the context regarding a time point different from the content delivery time point and a predetermined action of the first user with respect to the content. (Step S101). Then, the information processing apparatus 100 acquires the action information regarding the predetermined action of the second user to which the content is delivered (step S102). Then, the information processing apparatus 100 generates relational element information indicating an element related to a predetermined behavior of the second user based on the behavior information and the relational degree information (step S103).

[4. effect〕
As described above, the information processing apparatus 100 according to the embodiment has an acquisition unit 131 and a generation unit 133. The acquisition unit 131 acquires relationship degree information indicating the degree of relationship between each element of the context regarding another time point different from the content delivery time point and the predetermined action of the first user with respect to the content. The generation unit 133 is an element related to the predetermined behavior of the second user based on the behavior information and the relationship degree information when the behavior information regarding the predetermined behavior of the second user to which the content is delivered is acquired. Generates relational element information indicating.

As described above, when the information processing apparatus 100 according to the embodiment acquires the behavior information related to the predetermined behavior of the second user to which the content is delivered, the behavior information and another time point different from the delivery time of the content are obtained. Based on the relationship degree information indicating the degree of relationship between each element of the context regarding the content and the predetermined action of the first user with respect to the content, the relationship element information indicating the element related to the predetermined action of the second user is generated. Therefore, it is possible to appropriately generate information indicating elements related to the user's behavior.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 has the relationship degree information generated based on other behavior information regarding the predetermined behavior of the first user located in the predetermined area, and other than the predetermined area. Acquires the behavior information of the second user located in another area different from the above. The generation unit 133 generates relationship element information indicating an element related to a predetermined action in another area based on the action information and the relationship degree information.

As described above, the information processing apparatus 100 according to the embodiment is different from the relationship degree information generated based on other behavior information regarding the predetermined behavior of the first user located in the predetermined area, other than the predetermined area. Based on the behavior information of the second user located in the other area, the information indicating the element related to the user's behavior is appropriately generated by generating the relational element information indicating the element related to the predetermined behavior in the other area. Can be generated in. For example, the information processing apparatus 100 uses the information of the first area where the information is sufficient to generate the prediction information of the user located in the second area where the information is insufficient, so that the area where the information is insufficient can also be generated. The desired prediction is possible.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 is a model including each feature amount corresponding to each element, and predicts a predetermined behavior of the user with respect to the content based on the context information of the context. Get the model to use. The generation unit 133 generates the relational element information based on the model.

As described above, the information processing apparatus 100 according to the embodiment is a model including each feature amount corresponding to each element, and is a model used for predicting a predetermined behavior of the user with respect to the content based on the context information of the context. Based on this, by generating the relational element information, it is possible to appropriately generate the information indicating the element related to the user's behavior.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires a model that outputs a score related to a predetermined action of the user with respect to the content in response to the input of the context information.

As described above, the information processing apparatus 100 according to the embodiment generates the relational element information based on the model that outputs the score regarding the user's predetermined behavior with respect to the content in response to the input of the context information. It is possible to appropriately generate information indicating elements related to behavior.

Further, in the information processing apparatus 100 according to the embodiment, the generation unit 133 generates the related element information based on the model when the behavior information of the second user satisfies a predetermined condition.

As described above, when the behavior information of the second user satisfies a predetermined condition, the information processing apparatus 100 according to the embodiment generates the relational element information based on the model to obtain the elements related to the behavior of the user. The information shown can be generated appropriately.

Further, in the information processing apparatus 100 according to the embodiment, the generation unit 133 generates the relational element information based on the relational degree information indicating the weight of each feature amount in the model.

As described above, the information processing apparatus 100 according to the embodiment generates information indicating the elements related to the user's behavior by generating the relation element information based on the relationship degree information indicating the weight of each feature amount in the model. Can be generated appropriately.

Further, in the information processing apparatus 100 according to the embodiment, the generation unit 133 generates related element information by selecting a feature amount whose corresponding weight satisfies a predetermined condition from each feature amount of the model.

As described above, the information processing apparatus 100 according to the embodiment generates the relational element information by selecting the feature amount whose corresponding weight satisfies a predetermined condition from each feature amount of the model, thereby causing the user. It is possible to appropriately generate information indicating elements related to behavior.

Further, in the information processing apparatus 100 according to the embodiment, the generation unit 133 selects the feature amount whose absolute value of the corresponding weight is equal to or higher than a predetermined threshold value among the feature amounts of the model, thereby displaying the related element information. Generate.

As described above, the information processing apparatus 100 according to the embodiment generates the relational element information by selecting the feature amount whose absolute value of the corresponding weight is equal to or more than a predetermined threshold value among the feature amounts of the model. Therefore, it is possible to appropriately generate information indicating elements related to the user's behavior.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires correct answer information which is behavior information related to a predetermined behavior of the user for the content delivered to the user and a model generated based on the context information. do.

As described above, the information processing apparatus 100 according to the embodiment is related to the content delivered to the user based on the correct answer information which is the behavior information regarding the user's predetermined behavior and the model generated based on the context information. By generating element information, it is possible to appropriately generate information indicating elements related to the user's behavior.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires relationship degree information indicating the degree of relationship between each element including the user's emotion at another time point and a predetermined action of the first user with respect to the content. do.

As described above, the information processing apparatus 100 according to the embodiment has a relationship based on the relationship degree information indicating the degree of relationship between each element including the user's emotion at another time point and the predetermined behavior of the first user with respect to the content. By generating element information, it is possible to appropriately generate information indicating an element related to the user's behavior.

Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 includes each element including the user's emotion at another time point before the content delivery time point, and the predetermined action of the first user with respect to the content. Acquires the relationship degree information indicating the degree of relationship with.

As described above, in the information processing apparatus 100 according to the embodiment, the relationship between each element including the user's emotion at another time point before the content delivery time point and the predetermined action of the first user with respect to the content. By generating the relational element information based on the relational degree information indicating the degree, it is possible to appropriately generate the information indicating the element related to the user's behavior.

[5. Hardware configuration]
The information processing apparatus 100 according to the above-described embodiment is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) Has 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 receives data from another device via the network N and sends it to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the network N.

The CPU 1100 controls an output device such as a display or a printer, and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. Further, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

The media interface 1700 reads a program or data stored in the recording medium 1800 and provides the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable Disk), a magneto-optical recording medium such as MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. And so on.

For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from another device via the network N.

Although some of the embodiments of the present application have been described in detail with reference to the drawings, these are examples, and various modifications are made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure line of the invention. It is possible to carry out the present invention in other modified forms.

[6. others〕
Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. 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 figure is not limited to the information shown in the figure.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in any unit according to various loads and usage conditions. Can be integrated and configured.

In addition, the processes described in the above-described embodiments can be appropriately combined as long as the processing contents do not contradict each other.

Further, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

1 Information processing system 100 Information processing device 121 Open data storage unit 122 User information storage unit 123 Behavior information storage unit 124 Distribution information storage unit 125 Model information storage unit 126 Predictive information storage unit 127 Relationship degree information storage unit 130 Control unit 131 Acquisition unit 132 Decision unit 133 Generation unit 134 Providing unit 10 Terminal device 50 Information providing device N network

The information processing apparatus according to the present application includes an acquisition unit that acquires relationship degree information indicating the degree of relationship between each element of the context related to a time point different from the content delivery time point and a predetermined action of the first user with respect to the content. , Generates relational element information indicating an element related to the predetermined behavior of the second user based on the behavior information regarding the predetermined behavior of the second user to which the content is delivered and the relationship degree information. It is characterized by having a generation unit for processing.

Claims (13)

An acquisition unit that acquires relationship degree information indicating the degree of relationship between each element of the context related to another time point different from the content delivery time point and the predetermined action of the first user with respect to the content.
When the behavior information related to the predetermined behavior of the second user to which the content is delivered is acquired, the behavior information is related to the predetermined behavior of the second user based on the behavior information and the relationship degree information. A generator that generates relational element information that indicates an element,
An information processing device characterized by being equipped with. The acquisition unit
The relationship degree information generated based on the other action information of the first user located in the predetermined area and the second user located in another area different from the predetermined area. Acquire the above-mentioned behavior information of
The generator is
The information processing apparatus according to claim 1, wherein the information processing apparatus according to claim 1 generates the related element information indicating an element related to the predetermined action in the other area based on the action information and the relationship degree information. .. The acquisition unit
A model including each feature amount corresponding to each element and used for predicting the predetermined behavior of the user with respect to the content is acquired based on the context information of the context.
The generator is
The information processing apparatus according to claim 1 or 2, wherein the related element information is generated based on the model. The acquisition unit
The information processing apparatus according to claim 3, further comprising acquiring the model that outputs a score regarding the predetermined behavior of the user with respect to the content in response to the input of the context information. The generator is
The information processing apparatus according to claim 3 or 4, wherein when the behavior information of the second user satisfies a predetermined condition, the relational element information is generated based on the model. The generator is
The information processing apparatus according to any one of claims 3 to 5, wherein the relational element information is generated based on the relational degree information indicating the weight of each feature amount in the model. The generator is
Any one of claims 3 to 6, wherein the related element information is generated by selecting the feature amount whose corresponding weight satisfies a predetermined condition from the feature amounts of the model. The information processing device described in. The generator is
The related element information is generated by selecting the feature amount whose absolute value of the corresponding weight is equal to or more than a predetermined threshold value among the feature amounts of the model. The information processing apparatus according to any one of the following items. The acquisition unit
Claims 3 to 8 are characterized in that the correct answer information, which is behavior information related to a predetermined behavior of the user, and the model generated based on the context information are acquired for the content delivered to the user. The information processing apparatus according to any one of the following items. The generator is
Claims 1 to 9 are characterized in that the relationship degree information indicating the degree of relationship between the elements including the user's emotions at other time points and the predetermined behavior of the first user with respect to the content is acquired. The information processing apparatus according to any one of the above items. The generator is
The relationship degree information indicating the degree of relationship between each element including the user's emotion at the other time point, which is a time point before the delivery time of the content, and the predetermined action of the first user with respect to the content. The information processing apparatus according to claim 10, wherein the information processing apparatus is obtained. It is an information processing method executed by a computer.
An acquisition process for acquiring relationship degree information indicating the degree of relationship between each element of the context related to another time point different from the content delivery time point and the predetermined action of the first user with respect to the content.
When the behavior information related to the predetermined behavior of the second user to which the content is delivered is acquired, the behavior information is related to the predetermined behavior of the second user based on the behavior information and the relationship degree information. A generation process that generates relational element information indicating elements, and
An information processing method characterized by including. An acquisition procedure for acquiring relationship degree information indicating the degree of relationship between each element of the context related to another time point different from the content delivery time point and the predetermined action of the first user with respect to the content, and an acquisition procedure.
When the behavior information related to the predetermined behavior of the second user to which the content is delivered is acquired, the behavior information is related to the predetermined behavior of the second user based on the behavior information and the relationship degree information. The generation procedure to generate the relational element information indicating the element, and
An information processing program characterized by having a computer execute.

Images