JP6753833B2 - Grant device, grant method, grant program, and program - Google Patents

Description

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

Conventionally, a technique for generating a model using various information and the like has been provided. For example, there is provided a technique of acquiring an action log when a user accesses a service providing site using a user terminal and performing machine learning using the acquired action log.

Japanese Unexamined Patent Publication No. 2016-62411 Japanese Unexamined Patent Publication No. 2013-254372

However, in the above-mentioned conventional technique, for example, it is not always possible to enable the use of log information in consideration of the meaning of the action log (log information). For example, simply using the acquired log information makes it possible to use the log information in consideration of the meaning of the log information, such as using the log information uniformly regardless of the validity of each information. Can be difficult.

The present application has been made in view of the above, and an object of the present application is to provide a granting device, a granting method, a granting program, and a model that enable the use of log information in consideration of the meaning of the log information.

The granting device according to the present application is a condition for adding a flag to the acquisition unit that acquires the behavior information related to the user's behavior and the behavior information acquired by the acquisition unit and stored as a log. Based on this, it is characterized in that it includes a granting unit that grants the flag.

According to one aspect of the embodiment, there is an effect that the log information can be used in consideration of the meaning of the log information.

FIG. 1 is a diagram showing an example of a granting process according to the first embodiment. FIG. 2 is a diagram showing a configuration example of the grant system according to the first embodiment. FIG. 3 is a diagram showing a configuration example of the terminal device according to the first embodiment. FIG. 4 is a diagram showing an example of a grant condition information storage unit according to the first embodiment. FIG. 5 is a diagram showing an example of the behavior information storage unit according to the first embodiment. FIG. 6 is a flowchart showing an example of the granting process according to the first embodiment. FIG. 7 is a diagram showing a configuration example of a terminal device according to a modified example. FIG. 8 is a diagram showing an example of a model information storage unit according to a modified example. FIG. 9 is a diagram showing a configuration example of the grant system according to the second embodiment. FIG. 10 is a diagram showing a configuration example of the server device according to the second embodiment. FIG. 11 is a diagram showing an example of the grant condition information storage unit according to the second embodiment. FIG. 12 is a diagram showing an example of the behavior information storage unit according to the second embodiment. FIG. 13 is a diagram showing a configuration example of the terminal device according to the second embodiment. FIG. 14 is a hardware configuration diagram showing an example of a computer that realizes the functions of the terminal device and the server device.

Hereinafter, a granting device, a granting method, a granting program, and a mode for carrying out the model (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 granting device, granting method, granting program, and model 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.

(First Embodiment)
[1. Grant process]
First, an example of the granting process according to the first embodiment will be described with reference to FIG. FIG. 1 is a diagram showing an example of a granting process according to the first embodiment. FIG. 1 describes a case where the terminal device 10 used by the user performs the granting process. That is, FIG. 1 shows a case where the granting process is performed on the client side in the estimation system 1 (see FIG. 2) as the client-server system.

In FIG. 1, the terminal device 10 as the granting device acquires the behavioral information related to the user's behavior, and the behavioral information stored as a log, which is the acquired behavioral information, is flagged based on the conditions for flagging. Is given. The flag referred to here may be information associated with the user's behavior (behavior information) in order to indicate the value (meaning) of the behavior information. For example, the flag may be information indicating the characteristics of what kind of target the behavioral information is useful information for. FIG. 1 shows, for example, a case where the terminal device 10 functions as a device (logger) for collecting behavioral information by adding information indicating the meaning of the behavioral information.

In FIG. 1, the granting process in the terminal device 10 used by the user identified by the user ID “U1” (hereinafter, may be referred to as “user U1”) will be described as an example.

First, the terminal device 10 acquires the action information of the user U1 (step S11). In the example of FIG. 1, the terminal device 10 acquires the action information indicating that the user U1 has browsed the content CT1 at the date and time dt10. The terminal device 10 acquires behavioral information indicating that the user U1 has browsed the content CT1 on the Internet. For example, the terminal device 10 acquires the action information AC10 indicating that the user U1 has browsed the content CT1 at the date and time dt10. In the example of FIG. 1, although it is illustrated by "dt10" or the like, a specific date and time such as "September 10, 2017 23:18:56" may be stored in the "date and time".

When "behavior information AC * (* is an arbitrary numerical value)" is described, it indicates that the behavior information is information (behavior information) related to the behavior identified by the behavior ID "AC *". For example, when "behavior information AC21" is described, the behavior information is the behavior information of the behavior identified by the behavior ID "AC21".

As described above, in the example of FIG. 1, the terminal device 10 acquires the action information indicating that the user U1 has browsed the content CT1 at the date and time dt10, as shown in the action information storage unit 142-1.

In FIG. 1, the behavior information storage unit 142 will be described as the behavior information storage units 142-1 and 142-2 according to the addition of information corresponding to each action. That is, in FIG. 1, it is shown that the behavior information storage unit 142-1 is updated to the behavior information storage unit 142-2. Further, the behavior information storage units 142-1 and 142-2 are the same behavior information storage units 142. Further, in the following, when the behavior information storage units 142-1 and 142-2 will be described without particular distinction, they will be described as the behavior information storage unit 142.

The “action ID” shown in the action information storage unit 142 in FIG. 1 indicates information that identifies the user's action. The “date and time” shown in the action information storage unit 142 in FIG. 1 indicates the date and time when the corresponding user's action was performed. The “type” shown in the action information storage unit 142 in FIG. 1 indicates information regarding the action type of the corresponding user. The “content” shown in the action information storage unit 142 in FIG. 1 indicates a specific content of the corresponding user action. The “flag” shown in the action information storage unit 142 in FIG. 1 indicates a flag given to the action (behavior information) of the corresponding user.

Then, the terminal device 10 that has acquired the action information determines whether to add a flag to the acquired action information (step S12). In the example of FIG. 1, the terminal device 10 determines whether to add a flag to the action information by using the information stored in the addition condition information storage unit 141.

For example, the grant condition information storage unit 141 in FIG. 1 stores information regarding the grant condition of each flag used in the grant process (hereinafter, also referred to as “grant condition information”). FIG. 1 shows an example of grant condition information stored in the grant condition information storage unit 141. As shown in FIG. 1, the grant condition information storage unit 141 has items such as "condition ID", "target", "action type", "condition 1", and "condition 2" as grant condition information. Although only "condition 1" and "condition 2" are shown in FIG. 4, even if conditions corresponding to the number of conditions corresponding to each condition ID such as "condition 3" and "condition 4" are stored. Good.

The “condition ID” shown in the grant condition information storage unit 141 in FIG. 1 indicates information for identifying the condition (grant condition) used for flag assignment. The “target” shown in the grant condition information storage unit 141 in FIG. 1 indicates the target of the flag when the corresponding condition is satisfied. Further, the "action type" shown in the grant condition information storage unit 141 in FIG. 1 indicates the type of action of the user used for determining the corresponding condition. Further, "condition 1" and "condition 2" shown in the grant condition information storage unit 141 in FIG. 1 indicate specific conditions.

For example, in the example shown in FIG. 1, the condition (condition CD11) identified by the condition ID "CD11" indicates that the target is a "favorite target". Further, the condition CD11 indicates that the type of action used for the determination is "search". Further, "condition 1" of the condition CD11 indicates that one condition "includes a character string indicating a target in the query". Further, "Condition 2" of the condition CD11 indicates that the two conditions include "joining a fan club" in the query.

In the example of FIG. 1, when the query used by the user included in a certain action information includes a character string indicating a target and the character string "fan club enrollment", the character string indicates in the action information. Indicates that a flag indicating that the target is liked is given. For example, in the condition CD11, when the query used by the user included in a certain action information (behavior information X) includes a character string indicating the entertainer "A group" and the character string "fan club enrollment", the action information X includes the character string. Indicates that a flag (for example, flag FG11) indicating that the A group is liked is given. For example, the flag FG11 indicates that the action information is information that can be used when the group A is the estimation target. For example, the flag FG11 shows the feature that the behavioral information is useful information about the A group. For example, the flag FG11 indicates that the action information is useful information for estimation or the like with respect to the A group. For example, the flag FG11 may be a flag used to generate a model for estimating whether the fan is a fan of group A. For example, the flag FG11 may be a flag used to improve the efficiency of model generation for estimating whether the fan is a fan of group A. For example, the flag FG11 may be a flag attached to the action information indicating that the probability of being a fan of the A group is a predetermined value (for example, 50% or more) or more. For example, the flag FG11 may be a flag attached to the action information indicating that the probability of being a fan of the A group is high. That is, the flag FG 11 may be a flag attached to significant behavior information when estimating whether the user is a fan of the A group.

For example, in the example shown in FIG. 1, the condition (condition CD12) identified by the condition ID "CD12" indicates that the target is the "parent's home". Further, the condition CD12 indicates that the type of action used for the determination is "gift". Further, "Condition 1" of the condition CD12 indicates that one condition is "two weeks before the day of event X". Further, "Condition 2" of the condition CD12 indicates that the two conditions include "specify the delivery destination of the purchased flower". It is assumed that a large number of conditions other than the conditions CD11 and CD12 are stored in the grant condition information storage unit 141.

For example, the terminal device 10 determines whether or not the acquired action information has a corresponding condition among the conditions such as the conditions CD11 and CD12 stored in the grant condition information storage unit 141. In FIG. 1, the terminal device 10 determines that the action information AC10 is not given a flag because the condition stored in the grant condition information storage unit 141 does not include the condition corresponding to the action information AC10. The terminal device 10 may transmit the action information AC10 to the server device 50. For example, the terminal device 10 may transmit the action information AC10 to the server device 50 at a predetermined timing after step S12. For example, the terminal device 10 may transmit the action information AC10 to the server device 50 together with the action information AC11 described later.

Then, the terminal device 10 acquires the action information of the user U1 (step S13). In the example of FIG. 1, the terminal device 10 acquires the action information indicating that the user U1 has performed a search for the A group at the date and time dt11. For example, the terminal device 10 acquires the action information AC11 indicating that the search was performed using the query "A group fan club enrollment" at the date and time dt11 at the date and time dt11. Specifically, the terminal device 10 acquires the action information AC11 indicating that the user U1 has performed a search combining the query "A group" and the query "fan club enrollment" at the date and time dt11.

As described above, in the example of FIG. 1, the terminal device 10 acquires the action information indicating that the user U1 has performed a search for the A group at the date and time dt11, as shown in the action information storage unit 142-2.

Then, the terminal device 10 that has acquired the action information determines whether to add a flag to the acquired action information (step S14). In the example of FIG. 1, the terminal device 10 determines whether to add a flag to the action information by using the information stored in the addition condition information storage unit 141.

For example, the terminal device 10 determines whether or not the acquired action information has a corresponding condition among the conditions such as the conditions CD11 and CD12 stored in the grant condition information storage unit 141. In FIG. 1, the terminal device 10 determines that the action information AC11 is flagged because the action information AC11 corresponds to the condition CD11 among the conditions stored in the grant condition information storage unit 141. For example, the terminal device 10 determines that the action information AC11 is given the flag FG11 indicating that the favorite target is the A group.

Then, the terminal device 10 gives the action information a flag determined to be given (step S15). In the example of FIG. 1, the terminal device 10 assigns the flag FG11 corresponding to the “A group fan” to the action information AC11. For example, the terminal device 10 adds the flag FG11 to the action information AC11 stored in the action information storage unit 142. For example, the terminal device 10 stores the flag FG11 in the action information storage unit 142 in association with the action information AC11. In this way, the terminal device 10 determines whether to add the flag at the timing when the action information is acquired, and if it is determined to add the flag, adds the flag to the action information. That is, the terminal device 10 gives the action information a flag that satisfies the condition at the timing when the action information is acquired.

Then, the terminal device 10 transmits the flagged action information to the server device 50 (step S16). In the example of FIG. 1, the terminal device 10 transmits the action information AC11 with the flag FG11 to the server device 50. For example, the terminal device 10 transmits the action information AC11 associated with the flag FG11 to the server device 50. For example, the terminal device 10 transmits the action information AC11 to the server device 50 together with the flag FG11. For example, the terminal device 10 transmits the action information AC11 to which the flag FG11 is added to the server device 50 at the date and time dt12. For example, the terminal device 10 may transmit the action information AC11 to the server device 50 immediately after step S15. For example, the terminal device 10 may transmit the action information AC10 to the server device 50 at a predetermined timing after step S15. For example, the terminal device 10 may periodically (for example, every hour, every other day, etc.) transmit the acquired action information to the server device 50.

The server device 50 that has received (acquired) the action information from the terminal device 10 saves the acquired action information as a log (step S17). In the example of FIG. 1, the server device 50 stores the action information AC11 acquired from the terminal device 10 as a log. For example, the server device 50 stores the action information AC11 as a log in a predetermined storage means (not shown) such as a database.
For example, the server device 50 stores the information that identifies the user U1 in association with the flag FG11 corresponding to the “A group fan”. For example, the server device 50 stores the user ID “U1” in association with the flag FG11 corresponding to the “A group fan”. The server device 50 may store the action information AC11 in association with the flag FG11. Then, the server device 50 provides various services using the action information AC11 and the flag FG11 saved as a log. For example, the server device 50 uses the action information AC11, the flag FG11, and the like saved as a log to generate a model for estimating the user's attribute from the action information. For example, the server device 50 uses the action information AC11, the flag FG11, and the like saved as a log to generate a model that estimates whether the user is a fan of the A group from the action information.

As described above, when the acquired action information satisfies a predetermined condition, the terminal device 10 which is an giving device gives a flag to the action information. As a result, the terminal device 10 can use the log information in consideration of the meaning of the log information. Further, for example, the terminal device 10 assigns the flag FG11 to the behavior information to generate a model more accurately when generating a model for estimating whether the fan is a fan of the A group (hereinafter, also referred to as an “estimated model”). It can be made possible to do. For example, since the behavior information to which the flag FG11 is given includes the behavior characteristics of the user who is a fan of the A group, the behavior information to which the flag FG11 is given by the terminal device 10 is effective for improving the efficiency of generating the estimation model. Behavioral information. Therefore, when the acquired behavior information satisfies a predetermined condition, the terminal device 10 can improve the accuracy of processing using the behavior information such as model generation by adding a flag to the behavior information.

[1-1. Grant timing]
Further, in the example of FIG. 1, the terminal device 10 determines whether to add a flag to the action information when the action information is acquired. In this way, the terminal device 10 determines whether to add the flag at the timing when the action information is acquired, and if it is determined to add the flag, adds the flag to the action information. That is, the terminal device 10 gives the action information a flag that satisfies the condition at the timing when the action information is acquired. That is, in the example of FIG. 1, it is determined whether or not to give a flag when a log (behavior information) is generated in the terminal device 10 on the client side. As a result, the terminal device 10 can make it possible to use the log information in consideration of the meaning of the log information in a timely manner.

[1-2. Transmission information]
In the example of FIG. 1, the case where the terminal device 10 transmits the behavior information with the flag added to the server device 50 is shown, but the terminal device 10 may transmit various information to the server device 50. For example, the terminal device 10 may transmit information (analysis information) regarding the analysis result to the server device 50 when the analysis result based on the plurality of flagged action information satisfies a predetermined condition.

For example, in the terminal device 10, when the number of action information to which the same flag is given exceeds a predetermined threshold value (for example, "5"), the user who uses the terminal device 10 transmits the analysis information related to the flag to the server device. It may be transmitted to 50. For example, in the terminal device 10, when the number of action information to which the same flag is given exceeds a predetermined threshold value (for example, "10"), the user who uses the terminal device 10 has an attribute corresponding to the flag. The analysis information indicating that may be transmitted to the server device 50.

For example, in the terminal device 10, when the number of action information to which the related flag of the fan of the A group is given becomes equal to or more than a predetermined threshold value (for example, "3"), the user who uses the terminal device 10 is the A group. Analytical information indicating that the fan is a fan of The value of the predetermined threshold value in the above determination may vary depending on the user and the attributes of the user.

For example, in the terminal device 10, when the user who uses the terminal device 10 is a male, and the number of behavior information to which the related flag of the fan of the A group is given becomes 10 or more, the user is the A group. Analytical information indicating that it is a fan may be transmitted to the server device 50. For example, when the terminal device 10 is the user U1 who uses the terminal device 10, when the number of behavior information to which the related flag of the fan of the A group is given becomes 10 or more, the user U2 is the fan of the A group. The analysis information indicating that is may be transmitted to the server device 50.

For example, in the terminal device 10, when the user who uses the terminal device 10 is a woman, and the number of behavior information to which the related flag of the fan of the A group is given becomes 3 or more, the user is the A group. Analytical information indicating that it is a fan may be transmitted to the server device 50. For example, when the terminal device 10 is a user U2 who uses the terminal device 10, when the number of action information to which the related flag of the fan of the A group is given becomes 3 or more, the user U2 is a fan of the A group. The analysis information indicating that is may be transmitted to the server device 50.

[2. Grant system configuration]
As shown in FIG. 2, the granting system 1 includes a terminal device 10 and a server device 50. The terminal device 10 and the server device 50 are communicably connected by wire or wirelessly via a predetermined network N. FIG. 2 is a diagram showing a configuration example of the grant system according to the embodiment. The granting system 1 shown in FIG. 2 may include a plurality of terminal devices 10 and a plurality of server devices 50.

The terminal device 10 is an information processing device used by the user. For example, the terminal device 10 is an giving device that gives a flag to the action information when a predetermined condition is satisfied. The terminal device 10 performs an addition process of adding a flag to the action information which is the action information related to the user's action and is stored as a log based on the condition related to the addition of the flag. The terminal device 10 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. 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.

Further, the terminal device 10 may detect various sensor information by various sensors such as a GPS (Global Positioning System) sensor. Further, the terminal device 10 has a function of an acceleration sensor, and detects and acquires acceleration information (sensor information) in the movement of the user. Further, 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 environmental 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 context 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 may be able to acquire information on the user's own heartbeat (pulse) by wearing a wristband type wearable device capable of communicating with the terminal device 10. ..

The server device 50 is an information processing device having a storage means for storing various information acquired from the terminal device 10. For example, the server device 50 stores the action information collected from the terminal device 10.

For example, the server device 50 provides a service for providing content to a user (content providing service). The server device 50 distributes the content displayed on the terminal device 10 in response to the request from the terminal device 10. For example, the server device 50 provides content according to the user characteristics of the user in response to a request from the terminal device 10 used by the user. Further, in the estimation system 1, the server device 50 provides various services such as a search service and an electronic commerce service. For example, the server device 50 provides the terminal device 10 with information (product information) of a product or service (hereinafter, also referred to as a “product”), or responds to the user with information indicating a purchase intention from the user. Provides an electronic commerce service that performs purchase processing such as delivery of products. Further, for example, the server device 50 provides a search service that provides the terminal device 10 with search results for a query (search query) acquired from the terminal device 10.

An external information processing device other than the server device 50 may provide a content providing service, a search service, an electronic commerce service, or the like. In this case, the estimation system 1 may include a service providing device that provides a content providing service, a search service, an electronic commerce service, and the like. Further, when an external information processing device provides a search service or an electronic commerce service, the server device 50 does not have to provide the content providing service, the search service, or the electronic commerce service. In this case, the server device 50 acquires various information from an external information processing device that provides a content providing service, a search service, an electronic commerce service, or the like, and based on the acquired various information, performs estimation processing or an external information processing device. Information may be provided.

[3. Terminal device configuration]
Next, the configuration of the terminal device 10 according to the first embodiment will be described with reference to FIG. FIG. 3 is a diagram showing a configuration example of the terminal device according to the first embodiment. As shown in FIG. 3, the terminal device 10 includes a communication unit 11, an input unit 12, an output unit 13, a storage unit 14, and a control unit 15.

(Communication unit 11)
The communication unit 11 is realized by, for example, a communication circuit or the like. Then, the communication unit 11 is connected to a predetermined communication network (not shown) by wire or wirelessly, and transmits / receives information to / from an external information processing device. For example, the communication unit 11 is connected to a predetermined communication network (not shown) by wire or wirelessly, and transmits / receives information to / from the server device 50.

(Input unit 12)
Various operations are input from the user to the input unit 12. For example, the input unit 12 may receive various operations from the user via the display surface (for example, the output unit 13) by the touch panel function. Further, the input unit 12 may accept various operations from the buttons provided on the terminal device 10 and the keyboard and mouse connected to the terminal device 10.

(Output unit 13)
The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information.

(Memory unit 14)
The storage unit 14 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. The storage unit 14 stores, for example, information about an application installed in the terminal device 10, such as a program. Further, as shown in FIG. 3, the storage unit 14 according to the first embodiment includes a grant condition information storage unit 141 and an action information storage unit 142.

(Granting condition information storage unit 141)
The grant condition information storage unit 141 according to the first embodiment stores various information related to the grant condition. FIG. 4 is a diagram showing an example of a grant condition information storage unit according to the first embodiment. For example, the grant condition information storage unit 141 stores information regarding the grant condition of each flag used in the grant process (hereinafter, also referred to as “condition information” or “grant condition information”). FIG. 4 shows an example of the grant condition information stored in the grant condition information storage unit 141. As shown in FIG. 4, the grant condition information storage unit 141 has items such as "condition ID", "target", "action type", "condition 1", and "condition 2" as the grant condition information. Although only "condition 1" and "condition 2" are shown in FIG. 4, even if conditions corresponding to the number of conditions corresponding to each condition ID such as "condition 3" and "condition 4" are stored. Good.

The "condition ID" indicates information for identifying the condition (granting condition) used for assigning the flag. “Target” indicates the target of the flag when the corresponding condition is satisfied. Further, the "behavior type" indicates the type of the user's action used to determine the corresponding condition. Further, "condition 1" and "condition 2" indicate specific conditions.

For example, in the example shown in FIG. 4, the condition (condition CD11) identified by the condition ID "CD11" indicates that the target is a "favorite target". Further, the condition CD11 indicates that the type of action used for the determination is "search". Further, "condition 1" of the condition CD11 indicates that one condition "includes a character string indicating a target in the query". Further, "Condition 2" of the condition CD11 indicates that the two conditions include "joining a fan club" in the query.

In the example of FIG. 4, in the condition CD11, when the query used by the user included in a certain action information includes a character string indicating a target and the character string "fan club enrollment", the character string indicates in the action information. Indicates that a flag indicating that the target is liked is given. For example, in the condition CD11, when the query used by the user included in a certain action information (behavior information X) includes a character string indicating the entertainer "E actor" and the character string "fan club enrollment", the action information X includes the character string. E Indicates that an actor is given a flag indicating that he / she likes it.

The grant condition information storage unit 141 may store various grant condition information depending on the purpose. For example, the grant condition information storage unit 141 may store the grant condition information for each favorite object, for example, for each group A or B.

(Behavior information storage unit 142)
The behavior information storage unit 142 according to the first 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 first embodiment. For example, the behavior information storage unit 142 stores the behavior information of the user who uses the terminal device 10. The behavior information storage unit 142 of FIG. 5 shows the behavior information storage unit in the terminal device 10 of the user U1. The action information storage unit 142 shown in FIG. 5 includes items such as "action ID", "date and time", "type", "content", and "flag".

The "behavior ID" indicates information that identifies the user's behavior. The "date and time" indicates the date and time when the corresponding user action was performed. In the example of FIG. 5, although it is illustrated by "dt10" or the like, a specific date and time such as "September 11, 2017 23:18:56" may be stored in the "date and time". Further, "type" indicates information regarding the type of action of the corresponding user. In addition, "content" indicates the specific content of the corresponding user's behavior. The "flag" indicates a flag given to the action (behavior information) of the corresponding user.

For example, in the example shown in FIG. 5, it is shown that the user U1 has performed an action identified by the action ID “AC10”, the action ID “AC11”, or the like.

For example, in the example shown in FIG. 5, it is shown that the user U1 has browsed the content CT1 at the date and time dt10 as shown in the action AC10. Further, as shown in the action AC10, the category of the content CT1 viewed by the user U1 at the date and time dt10 is "entertainment" and indicates that the content is related to "D drama". Further, the flag of the action AC10 is "-", indicating that the flag is not given to the action AC10.

For example, in the example shown in FIG. 5, it is shown that the user U1 performed the search at the date and time dt11 as shown in the information (behavior) identified by the action ID “AC11”. Further, as shown in the information (behavior) identified by the action ID "AC11", the user U1 indicates that the search was performed using the query "A group fan club enrollment" at the date and time dt11. That is, it indicates that the user U1 performed a search combining the query "A group" and the query "fan club enrollment" at the date and time dt11, as shown in the information (behavior) identified by the action ID "AC11". .. Further, in the example shown in FIG. 5, it is shown that the flag FG11 corresponding to the “A group fan” is given to the information (behavior) identified by the action ID “AC11”.

The behavior information storage unit 142 is not limited to the above, and may store various information depending on the purpose.

(Control unit 15)
The control unit 15 is a controller, and for example, various programs stored in a storage device such as a storage unit 14 inside the terminal device 10 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like can be stored. It is realized by executing the RAM as a work area. For example, these various programs include a program of an application that performs grant processing. Further, the control unit 15 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 15 includes an acquisition unit 151, a determination unit 152, an addition unit 153, and a transmission unit 154, and realizes or executes the function or operation of the addition process described below. .. The internal configuration of the control unit 15 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it is configured to perform the imparting process described later. Further, the connection relationship of each processing unit included in the control unit 15 is not limited to the connection relationship shown in FIG. 3, and may be another connection relationship.

(Acquisition unit 151)
The acquisition unit 151 acquires various types of information. For example, the acquisition unit 151 acquires various information from an external information processing device. The acquisition unit 151 acquires behavior information related to the user's behavior. The acquisition unit 151 acquires behavior information related to the user's behavior from the terminal device 10. In addition, the acquisition unit 151 acquires behavior information regarding the behavior of the user on the Internet. For example, the acquisition unit 151 acquires behavioral information regarding user behavior in a content providing service, a search service, an electronic commerce service, or the like.

For example, the acquisition unit 151 acquires various information from the storage unit 14. The acquisition unit 151 acquires various information from the grant condition information storage unit 141 and the action information storage unit 142. For example, the acquisition unit 151 acquires the sensor information detected by the sensor unit.

In the example of FIG. 1, the acquisition unit 151 acquires the action information of the user U1. The acquisition unit 151 acquires the action information indicating that the user U1 has browsed the content CT1 at the date and time dt10. The acquisition unit 151 acquires the action information AC10 indicating that the user U1 has browsed the content CT1 at the date and time dt10. In addition, the acquisition unit 151 acquires the action information of the user U1.

In the example of FIG. 1, the acquisition unit 151 acquires the action information indicating that the user U1 has performed a search for the A group at the date and time dt11. The acquisition unit 151 acquires the action information AC11 indicating that the search was performed using the query "A group fan club enrollment" at the date and time dt11 at the date and time dt11. The acquisition unit 151 acquires the action information AC11 indicating that the user U1 has performed a search combining the query "A group" and the query "fan club enrollment" at the date and time dt11.

(Judgment unit 152)
The determination unit 152 determines various information. For example, the determination unit 152 determines various information using various information stored in the storage unit 14. The determination unit 152 determines various information by using various information stored in the grant condition information storage unit 141 and the action information storage unit 142. For example, the determination unit 152 determines various information using various information acquired by the acquisition unit 151.

For example, the determination unit 152 determines whether to add a flag to the action information. For example, the determination unit 152 determines whether to add a flag to the action information based on the information stored in the addition condition information storage unit 141. For example, the determination unit 152 determines whether to add a flag to the action information stored in the action information storage unit 142.

The determination unit 152 determines whether to add a flag to the action information acquired by the acquisition unit 151 and stored as a log. In addition, the determination unit 152 determines whether to add a flag to the action information based on the conditions for adding a flag indicating the characteristics of the action information. In addition, the determination unit 152 determines whether to add a flag to the action information based on the conditions for adding a flag indicating the validity of the action information.

In addition, the determination unit 152 determines whether to add a flag to the action information based on the conditions for adding a flag indicating an estimation target for which the action information can be used. Further, the determination unit 152 determines whether to add a flag to the action information based on the conditions for adding the flag used for generating a predetermined model. Further, the determination unit 152 determines whether to add a flag to the action information based on the condition for adding a flag used for improving the efficiency of generating a predetermined model.

Further, the determination unit 152 determines whether to add a flag to the action information at the timing when the action information is acquired by the acquisition unit 151. In addition, the determination unit 152 determines whether to add a flag to the action information by using the condition information indicating the condition for adding the flag. For example, the determination unit 152 determines whether to add a flag to the action information by using the condition information stored in the addition condition information storage unit 141. Further, the determination unit 152 may determine whether to add a flag to the action information by using a determination model for determining whether to add a flag. For example, the determination unit 152 may determine whether to add a flag to the action information by using the determination model (see FIG. 8) stored in the storage unit 14.

In the example of FIG. 1, the determination unit 152 determines whether to add a flag to the acquired action information. The determination unit 152 determines whether to add a flag to the action information by using the information stored in the addition condition information storage unit 141. Further, the determination unit 152 determines whether or not there is a condition to which the acquired action information corresponds among the conditions such as the conditions CD11 and CD12 stored in the grant condition information storage unit 141. In the example of FIG. 1, the determination unit 152 determines that the action information AC10 is not given a flag because the condition stored in the grant condition information storage unit 141 does not include the condition corresponding to the action information AC10.

In the example of FIG. 1, the determination unit 152 determines whether to add a flag to the acquired action information. Further, the determination unit 152 determines whether to add a flag to the action information by using the information stored in the addition condition information storage unit 141. Further, the determination unit 152 determines whether or not there is a condition to which the acquired action information corresponds among the conditions such as the conditions CD11 and CD12 stored in the grant condition information storage unit 141. In the example of FIG. 1, the determination unit 152 determines that the action information AC11 is given a flag because the action information AC11 corresponds to the condition CD11 among the conditions stored in the grant condition information storage unit 141. For example, the determination unit 152 determines that the action information AC11 is given the flag FG11 indicating that the favorite target is the A group.

(Granting part 153)
The giving unit 153 gives various information. For example, the granting unit 153 grants various information using various information stored in the storage unit 14. The granting unit 153 grants various information using various information stored in the granting condition information storage unit 141 and the action information storage unit 142. For example, the granting unit 153 grants various information using the various information acquired by the acquisition unit 151. For example, the granting unit 153 grants various information using various information determined by the determination unit 152.

For example, the granting unit 153 imparts the flag to the action information determined to be flagged by the determining unit 152. For example, when the determination unit 152 determines that the action information is to be flagged, the granting unit 153 adds the flag to the action information stored in the action information storage unit 142. For example, when the determination unit 152 determines that the action information is to be given a flag, the granting unit 153 stores the flag in the action information storage unit 142 in association with the action information. For example, the granting unit 153 does not add a flag to the action information determined by the determination unit 152 not to give a flag.

The granting unit 153 adds a flag to the action information acquired by the acquisition unit 151 and stored as a log based on the conditions for adding the flag. In addition, the granting unit 153 adds a flag to the action information based on the conditions for adding a flag indicating the characteristics of the action information. In addition, the granting unit 153 adds a flag to the action information based on the conditions for adding a flag indicating the validity of the action information.

In addition, the granting unit 153 adds a flag to the action information based on the conditions for adding a flag indicating an estimation target for which the action information can be used. In addition, the granting unit 153 adds a flag to the action information based on the conditions for adding the flag used for generating a predetermined model. In addition, the granting unit 153 adds a flag to the action information based on the condition regarding the addition of the flag used for improving the efficiency of the generation of the predetermined model.

Further, the granting unit 153 adds a flag to the action information at the timing when the action information is acquired by the acquisition unit 151, based on the conditions for adding the flag. Further, the granting unit 153 adds a flag to the action information at the timing when the determination unit 152 determines to add the flag to the action information. The giving unit 153 gives a flag to the action information according to the determination using the condition information indicating the condition for giving the flag. Further, the giving unit 153 may give a flag to the action information according to the judgment using the judgment model for determining whether to give the flag.

In addition, the granting unit 153 assigns a flag determined to be granted to the action information. In the example of FIG. 1, the granting unit 153 grants the flag FG11 corresponding to the “A group fan” to the action information AC11. For example, the granting unit 153 assigns the flag FG11 to the behavior information AC11 stored in the behavior information storage unit 142. For example, the granting unit 153 stores the flag FG11 in the behavior information storage unit 142 in association with the behavior information AC11. In this way, the granting unit 153 determines whether to add the flag at the timing when the action information is acquired, and if it is determined to add the flag, adds the flag to the action information. That is, the granting unit 153 adds a flag satisfying the condition to the action information at the timing when the action information is acquired.

(Transmission unit 154)
The transmission unit 154 transmits various information to an external information processing device. The transmission unit 154 transmits various information to the terminal device 10. The transmission unit 154 transmits various information stored in the storage unit 14 to an external information processing device. The transmission unit 154 transmits various information to the terminal device 10. The transmission unit 154 transmits various information acquired by the acquisition unit 151 to an external information processing device. The transmission unit 154 transmits various information determined by the determination unit 152 to an external information processing device. The transmission unit 154 transmits various information given by the granting unit 153 to an external information processing device.

The transmission unit 154 transmits the action information flagged by the granting unit 153 to an external information processing device. The transmission unit 154 transmits the action information flagged by the granting unit 153 to the server device 50.

In the example of FIG. 1, the transmission unit 154 transmits the flagged action information to the server device 50. The transmission unit 154 transmits the action information AC11 with the flag FG11 to the server device 50. For example, the transmission unit 154 transmits the action information AC11 associated with the flag FG11 to the server device 50. For example, the transmission unit 154 transmits the action information AC11 to the server device 50 together with the flag FG11. For example, the transmission unit 154 transmits the action information AC11 to which the flag FG11 is added to the server device 50 at the date and time dt12. For example, the transmission unit 154 may transmit the action information AC11 to the server device 50 immediately after step S15. For example, the transmission unit 154 may transmit the action information AC10 to the server device 50 at a predetermined timing after step S15. For example, the transmission unit 154 may transmit the acquired behavior information to the server device 50 on a regular basis (for example, every hour or every other day).

When the above-mentioned processing such as the granting process by the control unit 15 is performed by a predetermined application, each unit of the control unit 15 may be realized by, for example, a predetermined application. For example, processing such as grant processing by the control unit 15 may be realized by control information received from an external information processing device. Further, when the terminal device 10 is a dedicated device for performing the giving process, the terminal device 10 does not have to have the input unit 12 and the output unit 13.

Further, the terminal device 10 may have a sensor unit (not shown). The sensor unit detects predetermined information. For example, the sensor unit detects information outside the terminal device 10. For example, the sensor unit is realized by a GPS sensor. The number of sensor units may be plural. The sensor unit may be any sensor as long as it can detect the information used for the addition process. For example, when the terminal device 10 uses the image information captured by the camera function for the addition process, the terminal device 10 may have a camera as a sensor unit. Further, when the position information of the terminal device 10 is acquired as action information, the position of the terminal device 10 estimated by using the position information of the base station communicating with the terminal device 10 or the radio wave of WiFi (registered trademark) (Wireless Fidelity). Information may be obtained.

[4. Flow of grant processing]
Next, the procedure of the granting process by the terminal device 10 according to the first embodiment will be described with reference to FIG. FIG. 6 is a flowchart showing a grant processing procedure by the terminal device according to the first embodiment.

As shown in FIG. 6, the terminal device 10 which is the granting device acquires the user's action information (step S101). In the example of FIG. 1, the terminal device 10 acquires the action information AC11 indicating that the user U1 has performed a search combining the query “A group” and the query “fan club enrollment” at the date and time dt11.

Then, the terminal device 10 determines whether or not the acquired action information satisfies the condition (step S102). In the example of FIG. 1, the terminal device 10 determines that the action information AC11 is given a flag because the action information AC11 corresponds to the condition CD11 among the conditions stored in the grant condition information storage unit 141.

Then, when the acquired action information satisfies the condition (step S102: Yes), the terminal device 10 adds a flag to the acquired action information (step S103). In the example of FIG. 1, the terminal device 10 assigns the flag FG11 corresponding to the “A group fan” to the action information AC11. On the other hand, when the acquired action information does not satisfy the condition (step S102: No), the terminal device 10 ends the process without adding a flag to the acquired action information.

[5. Modification example]
The terminal device 10 according to the first embodiment described above is not limited to the above-mentioned granting process, and may perform the granting process based on various information and conditions. For example, the terminal device 10A may determine whether to add a flag to the action information by using a determination model (also simply referred to as a “model”) that determines the flag assignment. For example, the terminal device 10A may determine whether to add a flag to the behavior information based on a model generated based on the history of the behavior information. That is, the terminal device 10A may perform the granting process using the model generated based on the history of the behavior information. This point will be described with reference to FIGS. 7 and 8. The same components as those in the first embodiment are designated by the same reference numerals, and the description thereof will be omitted.

[5-1. Terminal device configuration]
Next, the configuration of the terminal device 10A according to the modified example will be described with reference to FIG. 7. FIG. 7 is a diagram showing a configuration example of a terminal device according to a modified example. As shown in FIG. 7, the terminal device 10A includes a communication unit 11, an input unit 12, an output unit 13, a storage unit 14A, and a control unit 15A.

(Memory unit 14A)
The storage unit 14A is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 14A stores, for example, information about an application installed in the terminal device 10A, for example, a program or the like. Further, as shown in FIG. 7, the storage unit 14A according to the modified example has a model information storage unit 141A and an action information storage unit 142.

(Model information storage unit 141A)
The model information storage unit 141A according to the modified example stores information about the model. For example, the model information storage unit 141A stores model information (model data) generated by the generation process. FIG. 8 is a diagram showing an example of a model information storage unit according to a modified example. The model information storage unit 141A shown in FIG. 8 includes items such as "model ID", "determination target", and "model data". Although only the models M1 and M2 are shown in FIG. 8, a large amount of model information may be stored according to each determination target (things to be flagged) such as M3, M4, and M5.

The "model ID" indicates identification information for identifying the model. For example, the model identified by the model ID "M1" corresponds to the model M1 shown in the example of FIG. “Determination target” indicates the target of the flag that the corresponding model is used to determine the flag assignment. Further, "model data" indicates data of the associated corresponding model. For example, "model data" includes information including nodes in each layer, functions adopted by each node, connection relationships of nodes, and connection coefficients set for connections between nodes.

For example, in the example shown in FIG. 8, the model (model M1) identified by the model ID “M1” indicates that the target determination target is the “A group fan”. That is, it is shown that the model M1 is used for determining whether or not to add a flag related to the fan of the A group to the behavior information when the behavior information of the user is input. Further, it is shown that the model data of the model M1 is the model data MDT1.

The model M1 (model data MDT1) includes an input layer into which user action information is input, an output layer, and a first element that is any layer from the input layer to the output layer and belongs to a layer other than the output layer. , A second element whose value is calculated based on the first element and the weight of the first element, and each element belonging to each layer other than the output layer with respect to the user information input to the input layer is first. To make the computer function to output the score value used for determining whether to add a flag to the action information from the output layer by performing an operation based on the first element and the weight of the first element as an element. It is a model of.

Here, it is assumed that the models M1, M2 and the like are realized by the regression model represented by "y = a1 * x1 + a2 * x2 + ... + ai * xi". In this case, for example, the first element included in the model M1 corresponds to input data (xi) such as x1 and x2. Further, the weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element corresponds to any node of the input layer, and the second element can be regarded as the node of the output layer.

Further, it is assumed that the models M1, M2 and the like are realized by a neural network having one or a plurality of intermediate layers such as DNN. In this case, for example, the first element included in the model M1 corresponds to either the node of the input layer or the intermediate layer. Further, the second element corresponds to a node in the next stage, which is a node to which a value is transmitted from a node corresponding to the first element. Further, the weight of the first element corresponds to a connection coefficient which is a weight considered for the value transmitted from the node corresponding to the first element to the node corresponding to the second element.

The model information storage unit 141A is not limited to the above, and may store various model information depending on the purpose.

(Control unit 15A)
In the control unit 15A, for example, various programs stored in a storage device such as a storage unit 14A inside the terminal device 10A are executed by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like using the RAM as a work area. It is realized by. For example, these various programs include a program of an application that performs grant processing. Further, the control unit 15A is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control unit 15A is any one of an input layer, an output layer, and an input layer to an output layer into which user action information is input by information processing according to a model M1 or the like stored in the model information storage unit 141A. A user input to the input layer, including a first element which is a layer of the above and belongs to a layer other than the output layer, and a second element whose value is calculated based on the weights of the first element and the first element. For information, each element belonging to each layer other than the output layer is set as the first element, and an operation is performed based on the weights of the first element and the first element, which is used to determine whether to add a flag to the action information. The score value is output from the output layer.

For example, the terminal device 10A calculates a score used for determining whether to add a flag to the behavior information by using a model having an arbitrary structure such as the regression model or the neural network described above. Specifically, the models M1, M2, etc. are used to determine whether to add a flag to the behavior information when the user's behavior information (that is, each element used for calculating the score described above) is input. The coefficients are set to output a score (ie, a score that suggests how likely the user is to be associated with the object corresponding to the flag). The information providing device 10 calculates the score of the user's behavior information by using such models M1, M2 and the like.

In the above example, the models M1, M2, and the like are models that output a score used for determining whether to add a flag to the behavior information when the behavior information of the user is input. However, the models M1, M2, and the like according to the embodiment may be models generated based on the result obtained by repeating the input / output of data. For example, the model may be a model (model M1b) trained to input the user's behavior information and output the score output by the model M1. Alternatively, the model may be a model trained to input the user's behavior information and output the output value of the model M1b.

Further, when the terminal device 10A performs an imparting process (determination process) using GAN (Generative Adversarial Networks), the models M1, M2 and the like may be models constituting a part of the GAN.

As shown in FIG. 7, the control unit 15A includes an acquisition unit 151, a determination unit 152A, an addition unit 153, a transmission unit 154, and a learning unit 155, and functions and actions of the addition process described below. To realize or execute. The internal configuration of the control unit 15A is not limited to the configuration shown in FIG. 7, and may be any other configuration as long as it is configured to perform the imparting process described later. Further, the connection relationship of each processing unit included in the control unit 15A is not limited to the connection relationship shown in FIG. 7, and may be another connection relationship.

(Learning Department 155)
The learning unit 155 performs various learning. The learning unit 155 generates various models. The learning unit 155 generates a model to be used for the giving process by learning. For example, the learning unit 155 generates a model based on the history of behavior information. For example, the learning unit 155 may generate a model based on the history of the behavior information stored in the storage unit 14A. For example, the learning unit 155 may generate a model based on the history of the behavior information stored in the behavior information storage unit 142. The learning unit 155 may generate a model based on a given feature. In this case, the learning unit 155 may calculate the weight for each given feature and generate a model. Further, the learning unit 155 may automatically extract the features and generate a model based on the extracted features. In this case, the learning unit 155 may calculate the weight for each feature automatically extracted and generate a model. In addition, each feature may be any information.

The learning unit 155 generates a model as shown in the model information storage unit 141A. For example, the learning unit 155 generates a model used for determining whether to add a flag to the behavior information based on the learning data acquired by the acquisition unit 151. For example, the learning unit 155 is a model used to determine whether to give a flag to the behavior information based on the learning data including the behavior information of the user and the correct answer information indicating the target related to the flag associated with the behavior information. To generate. For example, the learning unit 155 is based on learning data including behavior information of a user who is a fan of group A and correct answer information (flag) indicating that the user corresponding to the behavior information is a fan of group A. A model M1 used for determining whether to give a flag (for example, flag FG11) corresponding to a fan of group A to the action information is generated.

For example, the learning unit 155 generates models M1, M2, etc., and stores the generated models M1, M2, etc. in the model information storage unit 141A. The learning unit 155 may generate models M1, M2, etc. using any learning algorithm. For example, the learning unit 155 generates models M1, M2, and the like using learning algorithms such as a neural network, a support vector machine (SVM), clustering, and reinforcement learning. As an example, when the learning unit 155 generates models M1, M2, etc. using a neural network, the models M1, M2, etc. include an input layer containing one or more neurons and an intermediate layer containing one or more neurons. It has an output layer containing the above neurons.

The learning unit 155 generates a model, and stores the generated model in the model information storage unit 141A. Specifically, the learning unit 155 is a first element that is any of an input layer into which user action information is input, an output layer, and a layer from the input layer to the output layer, and belongs to a layer other than the output layer. A second element whose value is calculated based on the first element and the weight of the first element, and each element belonging to each layer other than the output layer with respect to the user information input to the input layer. By performing an operation based on the first element and the weight of the first element as one element, a model is generated in which the score value used for determining whether to add a flag to the action information is output from the output layer.

When model information such as models M1 and M2 is acquired from an external information processing device by the acquisition unit 151, the control unit 15A does not have to have the learning unit 155.

(Judgment unit 152A)
The determination unit 152A determines whether to add a flag to the action information acquired by the acquisition unit 151 based on the model generated based on the history of the action information. For example, the determination unit 152A determines whether to add a flag to the action information acquired by the acquisition unit 151 based on the model information stored in the model information storage unit 141A. For example, the determination unit 152A determines whether to add a flag to the action information acquired by the acquisition unit 151 based on the model information stored in the model information storage unit 141A. For example, the determination unit 152A determines whether to add a flag corresponding to the fan of the A group to the action information acquired by the acquisition unit 151 based on the model M1 in which the determination target is the fan of the A group.

For example, the determination unit 152A inputs the user's behavior information into the model M1, and when the score output by the model M1 is equal to or higher than a predetermined threshold value (for example, "0.5"), the behavior information of the group A is added to the behavior information. It is determined that the flag corresponding to the fan is given. For example, the determination unit 152A inputs the user's behavior information into the model M1, and if the score output by the model M1 is less than a predetermined threshold value, determines that the behavior information is not given a flag corresponding to the fans of the A group. To do. The above is an example, and the determination unit 152A may determine whether to give a label to the behavior information using various models. The determination unit 152A may determine a flag to be given to the behavior information by using a model that performs multi-class classification.

Further, the granting unit 153 according to the modified example adds a flag to the action information according to the determination of the determination unit 152A. The giving unit 153 gives a flag to the action information according to the judgment using the judgment model for determining whether to give the flag. The giving unit 153 adds a flag to the action information according to the determination using the model M1 stored in the model information storage unit 141A. The granting unit 153 adds a flag to the action information according to the determination by the determination unit 152A using the model M1.

When the above-mentioned processing such as the granting process by the control unit 15A is performed by a predetermined application, each unit of the control unit 15A may be realized by, for example, a predetermined application. For example, processing such as grant processing by the control unit 15A may be realized by control information received from an external information processing device. Further, when the terminal device 10A is a dedicated device for performing the giving process, the terminal device 10A does not have to have the input unit 12, the output unit 13, and the display unit 154.

[5-2. Learning on the server device]
Further, when the terminal side (client side) determines the flag assignment using the model as in the terminal device 10A, the server side, that is, the server device 50 may also perform learning. In this case, the server device 50 may have a learning unit that generates a model used for the assignment process by learning. For example, the server device 50 may generate (learn) a model based on the behavior information acquired from each terminal device 10A. For example, the server device 50 may generate a model based on the behavior information acquired from the plurality of terminal devices 10A used by each of a large number of users. In this way, the server device 50 may generate a model common to a plurality of users. Further, the server device 50 may provide the generated model to each terminal device 10A.

For example, the terminal device 10A may generate a model for more accurately determining the behavior information of the user who uses the terminal device 10A by updating the model provided by the server device 50. That is, the terminal device 10A may improve the model determination system for the behavior information of the user who uses the terminal device 10A by updating the model provided by the server device 50. Then, the terminal device 10A may perform the imparting process by using an updated model of the model provided by the server device 50. As a result, the terminal device 10A updates the model generated based on the behavior information of a large number of users to a model specialized for the user who uses the terminal device 10A, and uses it for the assignment process with higher accuracy. A flag can be added to the action information. The model update is not limited to the above, and may be in various modes. For example, the terminal device 10A transmits a model generated using the behavior information of the user who uses the terminal device 10A to the server device 50, and the server device 50 updates the model using the behavior information of another user. You may. Then, the terminal device 10A may acquire the updated model from the server device 50 and use the acquired model for the assignment process.

(Second Embodiment)
[6. Grant process]
In the above-mentioned example, the case where the terminal device 10 or the terminal device 10A used by the user performs the granting process is shown, but the granting process may be performed by a device other than the terminal device 10 or the terminal device 10A. For example, a device other than the terminal device owned by the user may perform the grant process. This point will be described with reference to FIGS. 9 to 13.

In the examples shown in FIGS. 9 to 13, the server device 100 performs the granting process as shown in FIG. In the second embodiment, the granting process is performed on the server side of the estimation system 2 as the client-server system, that is, on the server device 100. For example, in the estimation system 2, the server device 100 adds a flag to the user's behavior information. For example, in the estimation system 2, the terminal device 10 only acquires (collects) the action information, and transmits the action information to the server device 100. Further, for example, when the server device 100 saves the action information acquired from the terminal device 10 as a log, it determines whether to give a flag, and if it is determined to give the flag, the flag is given.

For example, in the second embodiment, the server device 100 performs the granting process as in steps S11 to S14 and S16 shown in FIG. For example, in the second embodiment, the terminal device 20 transmits the action information to the server device 100, so that the server device 100 acquires the user's action information. Then, the server device 100 performs an addition process on the action information acquired from the terminal device 20. That is, in the second embodiment, the terminal device 20 in the processes of steps S11 to S14 and S16 shown in FIG. 1 is read as the server device 100. The same components as those in the second embodiment are designated by the same reference numerals and the description thereof will be omitted.

[7. Grant system configuration]
As shown in FIG. 9, the granting system 2 includes a terminal device 20, a server device 100, and a service providing device 200. The terminal device 20 and the server device 100 are communicably connected by wire or wirelessly via a predetermined network N. FIG. 9 is a diagram showing a configuration example of the grant system according to the second embodiment. The granting system 2 shown in FIG. 9 may include a plurality of terminal devices 20, a plurality of server devices 100, and a plurality of service providing devices 200.

The terminal device 20 is an information processing device used by the user. The terminal device 20 transmits the collected action information to the server device 100. For example, the terminal device 20 transmits the collected user action information to the server device 100 without performing processing such as determination of flag assignment. For example, the terminal device 20 may transmit the collected action information to the server device 100 at the timing when the user's action information is collected. Further, for example, the terminal device 20 may transmit behavior information to the server device 100 on a regular basis (for example, every hour or every other day). The terminal device 20 is realized by, for example, a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, a PDA, or the like. In the following, the terminal device 20 may be referred to as a user. That is, in the following, the user can be read as the terminal device 20.

The server device 100 is a computer that assigns a flag to the acquired behavior information regarding the user's behavior, which is stored as a log, based on the conditions for adding the flag. For example, when the acquired user action information satisfies a certain flag granting condition, the server device 100 performs a granting process of granting the flag. For example, the server device 100 is a granting device that grants the acquired user behavior information when it is determined that a certain flag granting condition is satisfied.

The service providing device 200 is an information processing device that performs various services using the information provided by the server device 100. For example, the service providing device 200 provides various services by using the information about the model and the user provided by the server device 100. For example, the service providing device 200 provides a content providing service that provides content to a user. The service providing device 200 distributes the content displayed on the terminal device 20 in response to the request from the terminal device 20. For example, the service providing device 200 provides content according to the user characteristics of the user in response to a request from the terminal device 20 used by the user. Further, in the estimation system 2, the service providing device 200 provides various services such as a search service and an electronic commerce service. For example, the service providing device 200 provides an electronic commerce service that provides product information to the terminal device 20 and performs purchase processing such as delivery of a product to the user in response to information indicating a purchase intention from the user. To do. Further, for example, the service providing device 200 provides a search service that provides the terminal device 20 with search results for a query (search query) acquired from the terminal device 20.

For example, the service providing device 200 may provide the information of the user collected by providing the content providing service, the search service, or the electronic commerce service to the server device 100. For example, the service providing device 200 provides the server device 100 with user behavior information in a content providing service, a search service, and an electronic commerce service. In this way, the server device 100 may acquire the user's behavior information from the service providing device 200. The server device 100 may be integrated with the service providing device 200. In this case, the estimation system 2 may not include the service providing device 200.

[8. Server device configuration]
Next, the configuration of the server device 100 according to the second embodiment will be described with reference to FIG. FIG. 10 is a diagram showing a configuration example of the server device according to the second embodiment. As shown in FIG. 10, the server device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(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 the network by wire or wirelessly, and transmits / receives information to / from the terminal device 20.

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 10, the storage unit 120 according to the second embodiment includes a grant condition information storage unit 121 and an action information storage unit 122.

(Granting condition information storage unit 121)
The grant condition information storage unit 121 according to the second embodiment stores various information related to the grant condition. FIG. 11 is a diagram showing an example of the grant condition information storage unit according to the second embodiment. For example, the grant condition information storage unit 121 stores information (grant condition information) regarding the grant condition of each flag used in the grant process. FIG. 11 shows an example of the grant condition information stored in the grant condition information storage unit 121. As shown in FIG. 11, the grant condition information storage unit 121 includes items such as "condition ID", "target", "relevance", "action type", "condition 1", and "condition 2" as the grant condition information. Has.

The "relevance degree" indicates the relevance degree when the conditions corresponding to each condition ID are satisfied. For example, in the example of FIG. 11, when the condition CD11 is satisfied, the relevance of the flag relating to the favorite object is "10". For example, the larger the value of "relevance", the stronger the behavioral information indicates the characteristics of the object. For example, the larger the value of "relevance", the stronger the relevance of the behavior information to the target and the higher the importance of the information. For example, the larger the value of "relevance", the more effective the behavioral information is as information about the target. The information stored in the grant condition information storage unit 121 shown in FIG. 11 is the same as the information stored in the grant condition information storage unit 141 shown in FIG. 4, except for the “relevance”, and thus the description thereof is omitted. To do.

The grant condition information storage unit 121 may store various grant condition information depending on the purpose. For example, the grant condition information storage unit 121 may store the grant condition information for each user or for each predetermined user classification.

(Behavior information storage unit 122)
The behavior information storage unit 122 according to the second embodiment stores various information related to the user's behavior. FIG. 12 is a diagram showing an example of the behavior information storage unit according to the second embodiment. For example, the behavior information storage unit 122 stores various behavior information such as the behavior of each user. The action information storage unit 122 shown in FIG. 12 includes items such as "user ID", "action ID", "date and time", "type", "content", and "flag".

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. The "date and time" indicates the date and time when the corresponding user action was performed. In the example of FIG. 12, although it is illustrated by "dt10" or the like, a specific date and time such as "September 8, 2017 23:18:56" may be stored in the "date and time". Further, "type" indicates information regarding the type of action of the corresponding user. In addition, "content" indicates the specific content of the corresponding user's behavior. The "flag" indicates a flag given to the action (behavior information) of the corresponding user.

For example, in the example shown in FIG. 12, it is shown that the user (user U1) identified by the user ID “U1” has performed an action identified by the action ID “AC10”, the action ID “AC11”, or the like.

For example, in the example shown in FIG. 12, it is shown that the user U1 has browsed the content CT1 at the date and time dt10 as shown in the action AC10. Further, as shown in the action AC10, the category of the content CT1 viewed by the user U1 at the date and time dt10 is "entertainment" and indicates that the content is related to "D drama". Further, the flag of the action AC10 is "-", indicating that the flag is not given to the action AC10.

For example, in the example shown in FIG. 12, the user U1 indicates that the search was performed at the date and time dt11 as shown in the action AC11. Further, as shown in the action AC11, the user U1 indicates that the search was performed using the query “A group fan club enrollment” at the date and time dt11. That is, as shown in the action AC11, the user U1 indicates that the search is performed by combining the query "A group" and the query "fan club enrollment" at the date and time dt11.

Further, in the example shown in FIG. 12, it is shown that the action AC11 is given the flag FG11 corresponding to the “A group fan”. It also indicates that the degree of relevance of the flag FG11 given to the action AC11 is "10". For example, the larger the value of the degree of relevance, the stronger the relationship with the target. For example, the larger the relevance value, the longer the fan period, indicating that the fan is an enthusiastic fan of Group A.

Further, for example, in the example shown in FIG. 12, the user U2 indicates that he / she purchased the C flower at the date and time dt21 as shown in the action AC21. Further, the user U2 indicates that the position LC21 (address of F prefecture) is specified as the delivery destination of the C flower purchased at the date and time dt21 as shown in the action AC21. That is, in the example shown in FIG. 12, as shown in the action AC21, the user U2 makes a purchase to give the C flower to the user residing at the position LC21 at the date and time dt21.

Further, in the example shown in FIG. 12, it is shown that the action AC21 is given the flag FG21 corresponding to “parent's house = F prefecture”. It also indicates that the degree of relevance of the flag FG21 given to the action AC21 is "20". For example, the larger the value of the degree of relevance, the stronger the relationship with the target. For example, the higher the relevance value, the more likely the area is the home (hometown).

The behavior information storage unit 122 is not limited to the above, and may store various information depending on the purpose. Further, although FIG. 12 shows a case where the action information is stored in the action information storage unit 122 for each user ID, the action information is not limited to each user ID and may be stored, for example, in chronological order.

(Control unit 130)
The control unit 130 is a controller, and for example, various programs stored in a storage device such as a storage unit 120 inside the server device 100 are executed by a CPU, MPU, or the like using the RAM as a work area. It will be realized. For example, these various programs include programs of installed travel apps. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC or FPGA.

As shown in FIG. 10, the control unit 130 includes an acquisition unit 131, a determination unit 132, an imparting unit 133, and a providing unit 134, and realizes or executes a function or operation of the giving process described below. .. The internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 10, and may be another configuration as long as it is configured to perform the imparting process described later. Further, the connection relationship of each processing unit included in the control unit 130 is not limited to the connection relationship shown in FIG. 10, and may be another connection relationship.

(Acquisition unit 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various information from an external information processing device. The acquisition unit 131 acquires behavior information related to the user's behavior. The acquisition unit 131 acquires behavior information related to the user's behavior from the terminal device 20. In addition, the acquisition unit 131 acquires behavior information regarding the behavior of the user on the Internet. For example, the acquisition unit 131 acquires behavioral information regarding user behavior in a content providing service, a search service, an electronic commerce service, or the like.

For example, the acquisition unit 131 acquires various information from the storage unit 120. The acquisition unit 131 acquires various information from the grant condition information storage unit 121 and the action information storage unit 122.

The acquisition unit 131 acquires behavior information related to the user's behavior from an external information processing device. The acquisition unit 131 acquires the user's action information from the terminal device 20. For example, the acquisition unit 131 acquires behavior information including sensor information from the terminal device 20. For example, the acquisition unit 131 acquires user behavior information from the service providing device 200.

For example, the acquisition unit 131 acquires the behavior information of the user U1 (see FIG. 1). The acquisition unit 131 acquires the action information indicating that the user U1 has browsed the content CT1 at the date and time dt10. The acquisition unit 131 acquires the action information AC10 indicating that the user U1 has browsed the content CT1 at the date and time dt10. In addition, the acquisition unit 131 acquires the action information of the user U1.

For example, the acquisition unit 131 acquires the action information indicating that the user U1 has performed a search for the A group at the date and time dt11. The acquisition unit 131 acquires the action information AC11 indicating that the search was performed using the query “A group fan club enrollment” at the date and time dt11 on the date and time dt11. The acquisition unit 131 acquires the action information AC11 indicating that the user U1 has performed a search combining the query "A group" and the query "fan club enrollment" at the date and time dt11.

(Judgment unit 132)
The determination unit 132 determines various information. For example, the determination unit 132 determines various information using various information stored in the storage unit 120. The determination unit 132 determines various information using various information stored in the grant condition information storage unit 121 and the action information storage unit 122. For example, the determination unit 132 determines various information using various information acquired by the acquisition unit 131.

For example, the determination unit 132 determines whether to add a flag to the action information. For example, the determination unit 132 determines whether to add a flag to the action information based on the information stored in the grant condition information storage unit 121. For example, the determination unit 132 determines whether to add a flag to the action information stored in the action information storage unit 122.

The determination unit 132 determines whether to add a flag to the action information acquired by the acquisition unit 131 and stored as a log. In addition, the determination unit 132 determines whether to add a flag to the action information based on the conditions for adding the flag indicating the characteristics of the action information. In addition, the determination unit 132 determines whether to add a flag to the action information based on the conditions for adding a flag indicating the validity of the action information.

In addition, the determination unit 132 determines whether to add a flag to the action information based on the conditions for adding a flag indicating an estimation target for which the action information can be used. In addition, the determination unit 132 determines whether to add a flag to the action information based on the condition for adding the flag used for generating a predetermined model. Further, the determination unit 132 determines whether to add a flag to the action information based on the condition for adding a flag used for improving the efficiency of generating a predetermined model.

Further, the determination unit 132 determines whether to add a flag to the action information at the timing when the action information is acquired by the acquisition unit 131. In addition, the determination unit 132 determines whether to add a flag to the action information by using the condition information indicating the condition for adding the flag. For example, the determination unit 132 determines whether to add a flag to the action information by using the condition information stored in the addition condition information storage unit 121. Further, the determination unit 132 may determine whether to add a flag to the action information by using a determination model for determining whether to add a flag. For example, the determination unit 132 may determine whether to add a flag to the action information by using the determination model (see FIG. 8) stored in the storage unit 120.

For example, the determination unit 132 determines whether to add a flag to the acquired action information. The determination unit 132 determines whether to add a flag to the action information by using the information stored in the addition condition information storage unit 121. Further, the determination unit 132 determines whether or not there is a condition to which the acquired action information corresponds among the conditions such as the conditions CD11 and CD12 stored in the grant condition information storage unit 121. The determination unit 132 determines that the action information AC10 is not given a flag because the action information AC10 does not have a corresponding condition in the conditions stored in the grant condition information storage unit 121.

For example, the determination unit 132 determines whether to add a flag to the acquired action information. Further, the determination unit 132 determines whether to add a flag to the action information by using the information stored in the addition condition information storage unit 121. Further, the determination unit 132 determines whether or not there is a condition to which the acquired action information corresponds among the conditions such as the conditions CD11 and CD12 stored in the grant condition information storage unit 121. For example, the determination unit 132 determines that the action information AC11 is given a flag because the action information AC11 corresponds to the condition CD11 among the conditions stored in the grant condition information storage unit 121. For example, the determination unit 132 determines that the action information AC11 is given the flag FG11 indicating that the favorite target is the A group.

Note that the server device 100 may perform the granting process based on the model as in the terminal device 10A shown in FIGS. 7 and 8. In this case, the determination unit 132 determines whether to add a flag to the action information acquired by the acquisition unit 131 based on the model generated based on the history of the action information. In this case, the server device 100 may have a learning unit that generates a model used for the assignment process by learning. Then, the server device 100 generates a model based on the history of the behavior information by the learning unit. In this case, the server device 100 may generate a model common to a plurality of users, or may generate a model for each user.

(Granting unit 133)
The giving unit 133 gives various information. For example, the giving unit 133 gives various information by using various information stored in the storage unit 120. The granting unit 133 grants various information using various information stored in the granting condition information storage unit 121 and the action information storage unit 122. For example, the granting unit 133 grants various information using the various information acquired by the acquisition unit 131. For example, the granting unit 133 grants various information using various information determined by the determination unit 132.

For example, the granting unit 133 assigns the flag to the action information determined to be flagged by the determining unit 132. For example, when the determination unit 132 determines that the action information is to be flagged, the granting unit 133 adds the flag to the action information stored in the action information storage unit 122. For example, when the determination unit 132 determines that the action information is to be given a flag, the granting unit 133 stores the flag in the action information storage unit 122 in association with the action information. For example, the granting unit 133 does not give a flag to the action information determined by the determination unit 132 that the flag is not given.

The granting unit 133 adds a flag to the action information acquired by the acquisition unit 131 and is stored as a log, based on the conditions for adding the flag. In addition, the granting unit 133 assigns a flag to the action information based on the conditions for adding the flag indicating the characteristics of the action information. In addition, the granting unit 133 assigns a flag to the action information based on the conditions for adding the flag indicating the validity of the action information.

In addition, the granting unit 133 assigns a flag to the action information based on the conditions for adding a flag indicating an estimation target for which the action information can be used. In addition, the granting unit 133 assigns a flag to the action information based on the conditions for assigning the flag used for generating a predetermined model. In addition, the granting unit 133 assigns a flag to the action information based on the condition for adding a flag used for improving the efficiency of generating a predetermined model.

In addition, the granting unit 133 assigns a flag to the action information at the timing when the action information is acquired by the acquisition unit 131, based on the conditions for adding the flag. Further, the granting unit 133 adds a flag to the action information at the timing when the determination unit 132 determines that the action information is to be flagged. The granting unit 133 assigns a flag to the action information according to the determination using the condition information indicating the condition for assigning the flag. Further, the giving unit 133 may give a flag to the action information according to the determination using the determination model for determining whether to give the flag.

In addition, the granting unit 133 assigns a flag determined to be granted to the action information. For example, the granting unit 133 assigns the flag FG11 corresponding to the “A group fan” to the action information AC11. For example, the granting unit 133 assigns the flag FG11 to the behavior information AC11 stored in the behavior information storage unit 122. For example, the granting unit 133 stores the flag FG11 in the behavior information storage unit 122 in association with the behavior information AC11. In this way, the granting unit 133 determines whether to add the flag at the timing when the action information is acquired, and if it is determined to add the flag, adds the flag to the action information. That is, the granting unit 133 assigns a flag satisfying the condition to the action information at the timing when the action information is acquired.

(Providing section 134)
The providing unit 134 provides various information to an external information processing device. For example, the providing unit 134 provides various services to an external information processing device. For example, the providing unit 134 may provide information to the service providing device 200. For example, the providing unit 134 may provide the behavior information of the user with the label attached to the external information processing device that generates the model. Further, for example, when the server device 100 has a learning unit, the providing unit 134 may provide the model generated by the learning unit to an external information processing device. Further, for example, the providing unit 134 may provide the service providing device 200 with the behavior information and the model of the user to which the label is attached.

[9. Terminal device configuration]
Next, the configuration of the terminal device 20 according to the second embodiment will be described with reference to FIG. FIG. 13 is a diagram showing a configuration example of the terminal device according to the second embodiment. In the terminal device 20 shown in FIG. 13, for the same configuration as in FIG. 3, the code (“2 *” or “2 **”) in which the numerical value of the most significant digit is changed from “1” to “2”). The duplicate description is omitted by adding. As shown in FIG. 13, the terminal device 20 includes a communication unit 21, an input unit 22, an output unit 23, a storage unit 24, and a control unit 25. For example, the configuration of the terminal device 20 according to the second embodiment is a configuration excluding the function of the granting process in the terminal device 10 according to the first embodiment. In the following, the parts that are different from the terminal device 10 of each part will be mainly described.

(Control unit 25)
The control unit 25 is realized by, for example, a CPU, an MPU, or the like executing various programs stored in a storage device such as a storage unit 24 inside the terminal device 20 using the RAM as a work area. For example, these various programs include a program of an application that performs grant processing. Further, the control unit 25 is realized by, for example, an integrated circuit such as an ASIC or FPGA.

As shown in FIG. 13, the control unit 25 has an acquisition unit 251 and a transmission unit 254, and realizes or executes the function or operation of the granting process described below. That is, the terminal device 20 is different from the terminal device 10 in that it does not have a determination unit. The internal configuration of the control unit 25 is not limited to the configuration shown in FIG. 13, and may be any other configuration as long as it is configured to perform the imparting process described later. Further, the connection relationship of each processing unit included in the control unit 25 is not limited to the connection relationship shown in FIG. 13, and may be another connection relationship.

(Acquisition unit 251)
The acquisition unit 251 acquires various types of information. For example, the acquisition unit 251 acquires various information from an external information processing device. The acquisition unit 251 acquires behavioral information regarding the user's behavior. In addition, the acquisition unit 251 acquires behavior information regarding the behavior of the user on the Internet. For example, the acquisition unit 251 acquires behavioral information regarding user behavior in a content providing service, a search service, an electronic commerce service, or the like.

For example, the acquisition unit 251 acquires various information from the storage unit 24. For example, the acquisition unit 251 acquires the sensor information detected by the sensor unit.

(Transmission unit 254)
The transmission unit 254 transmits various information to an external information processing device. For example, the transmission unit 254 transmits the action information acquired by the acquisition unit 251 to the server device 100.

[10. effect〕
As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment are the acquisition units 151 and 131 and the grant units 153 and 133. And have. The acquisition units 151 and 131 acquire behavior information related to the user's behavior. Further, the granting units 153 and 133 assign a flag to the action information acquired by the acquisition units 151 and 131 and stored as a log based on the conditions for adding the flag.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment are acquired behavior information and are stored as a log. By adding a flag to the action information based on the conditions for adding the flag, it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment, the granting units 153 and 133 assign flags indicating the characteristics of the behavior information. Flag the behavioral information based on the conditions related to.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment are based on the conditions for adding a flag indicating the characteristics of the behavior information. , By adding a flag to the action information, it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment, the granting units 153 and 133 are flags indicating the validity of the action information. Flag the action information based on the conditions for granting.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment are based on the conditions for adding a flag indicating the validity of the action information. By adding a flag to the action information, it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment, the granting units 153 and 133 target estimation targets for which action information can be used. A flag is added to the action information based on the conditions for adding the indicated flag.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment relate to the addition of a flag indicating an estimation target for which action information can be used. By adding a flag to the action information based on the condition, it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment, the granting units 153 and 133 are flags used to generate a predetermined model. Flag the action information based on the conditions for granting.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment are based on the conditions for adding a flag used for generating a predetermined model. By adding a flag to the action information, it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment, the granting units 153 and 133 are used to improve the efficiency of generating a predetermined model. A flag is added to the action information based on the conditions for adding the flag to be used.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment relate to the addition of flags used for improving the efficiency of generation of a predetermined model. By adding a flag to the action information based on the condition, it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment, the granting units 153 and 133 are provided with action information by the acquisition units 151 and 131. At the acquired timing, a flag is added to the action information based on the conditions for adding the flag.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment are subject to the conditions for adding the flag at the timing when the action information is acquired. By adding a flag to the action information based on the above, it is possible to use the log information in consideration of the meaning of the log information in a timely manner.

Further, in the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment, the granting units 153 and 133 indicate conditions for granting a flag. A flag is added to the action information according to the judgment using the condition information.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment use the condition information indicating the condition for adding the flag. By adding a flag to the action information according to the determination, it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10A according to the modified example, the granting unit 153 adds a flag to the action information according to the determination using the determination model for determining whether to assign the flag.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment are determined by using a determination model for determining whether to add a flag. By adding a flag to the action information according to the above, it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment, the acquisition units 151 and 131 provide behavior information regarding user behavior on the Internet. To get.

As described above, the terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment acquire behavior information regarding the behavior of the user on the Internet. , It is possible to use log information in consideration of the meaning of behavior information (log information) regarding user behavior on the Internet.

Further, the terminal device 10 according to the first embodiment and the terminal device 10A according to the modified example have a transmission unit 154. The transmission unit 154 transmits information regarding behavioral information satisfying the conditions for transmission to the predetermined external device to the predetermined external device.

As described above, the terminal device 10 according to the first embodiment and the terminal device 10A according to the modified example provide information regarding behavior information satisfying the conditions for transmission to the predetermined external device to the predetermined external device (first embodiment). In the form, by transmitting to the server device 50), it is possible to use the log information in consideration of the meaning of the log information.

Further, in the terminal device 10 according to the first embodiment and the terminal device 10A according to the modified example, the transmission unit 154 transmits the action information to which the flag is added.

As described above, the terminal device 10 according to the first embodiment and the terminal device 10A according to the modified example can use the log information in consideration of the meaning of the log information by transmitting the behavior information to which the flag is added. Can be.

Further, in the terminal device 10 according to the first embodiment and the terminal device 10A according to the modified example, the transmission unit 154 is a condition for transmitting the analysis result based on a plurality of flagged action information to a predetermined external device. If, information about the analysis results is sent.

As described above, in the terminal device 10 according to the first embodiment and the terminal device 10A according to the modified example, when the analysis result based on the plurality of flagged action information satisfies the condition for transmission to a predetermined external device. By transmitting information about the analysis result, it is possible to use the log information in consideration of the meaning of the log information.

[11. program〕
The processing by the terminal devices 10 and 10A and the server device 100 described above is realized by the grant program according to the present application. For example, the determination unit 152 related to the terminal device 10 is realized by the CPU, MPU, or the like of the terminal device 10 executing the determination procedure related to the grant program with the RAM as the work area. For example, the granting unit 153 related to the terminal device 10 is realized by the CPU, MPU, or the like of the terminal device 10 executing the granting procedure related to the granting program with the RAM as a work area. Similarly, other processing units related to the terminal device 100 are also realized by executing each procedure by the grant program.

It should be noted that all the processes executed by the terminal device 100 according to the present application do not necessarily have to be realized by the granting program. For example, the sensor unit detects information outside the terminal device 10. At this time, information or the like outside the terminal device 10 may be detected by the OS (Operating System) of the terminal device 10. That is, the granting program itself does not execute the process executed by the terminal device 10 as described above, but acquires it by using the data acquired by the OS (for example, the sensor or circuit of the terminal device 10). The processing of the terminal device 10 described above may be realized by receiving or detecting the data).

[12. Hardware configuration]
The terminal device 10 according to the first embodiment, the terminal device 10A according to the modified example, and the server device 100 according to the second embodiment described above are realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 14 is a hardware configuration diagram showing an example of a computer that realizes the functions of the terminal device and the server device. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 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 starts up, a program dependent 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 a predetermined network (for example, network N in FIG. 2) and sends the data to the CPU 1100, and transmits the data generated by the CPU 1100 to the other device via the predetermined network. To do.

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 terminal device 10 according to the first embodiment, the terminal device 10A according to the modification, or the server device 100 according to the second embodiment, the CPU 1100 of the computer 1000 is loaded on the RAM 1200. The functions of the control units 15, 15A, and 130 are realized by executing the program or data (for example, models M1, M2, etc.). The CPU 1100 of the computer 1000 reads these programs or data (for example, models M1, M2, etc.) from the recording medium 1800 and executes them, but as another example, these programs are executed from another device via a predetermined network. You may get it.

Although some of the embodiments and modifications of the present application have been described in detail with reference to the drawings, these are examples and vary 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 another form obtained by modifying or improving the above.

[13. Others]
Further, among the processes described in the above embodiments and modifications, all or a part of the processes described as being automatically performed can be manually performed, or can be performed manually. It is also possible to automatically perform all or part of the described processing by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

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 the device is functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. It can be integrated and configured.

In addition, the above-described embodiments and modifications 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.

10 Terminal device (granting device)
141 Grant condition information storage unit 142 Action information storage unit 15 Control unit 151 Acquisition unit 152 Judgment unit 153 Grant unit 154 Transmission unit 100 Server device (grant device)
121 Grant condition information storage unit 122 Action information storage unit 130 Control unit 131 Acquisition unit 132 Judgment unit 133 Grant unit 134 Provision unit 50 Server device 200 Service provision device

Claims (16)

An acquisition unit that acquires behavior information related to user behavior saved as a log ,
To have been the action information acquired by the acquisition unit, the a condition regarding grant flag on behavior information stored as a log, based on the action type indicating the type of action of the subject indicated by the flag user The first condition for estimating the target and the second condition different from the first condition, which are defined conditions and include information for determining the action indicated by the action type. And, based on the condition configured including
A granting device characterized by being equipped with. The granting part
Based on the conditions related to grant of the flag indicating the characteristics of the action information, applying apparatus according to claim 1, characterized by applying the flag to the action information. The granting part
The granting device according to claim 1 or 2 , wherein the flag is fastened to the behavioral information based on a condition for granting the flag indicating the validity of the behavioral information. The granting part
The granting device according to any one of claims 1 to 3 , wherein the flag is fastened to the behavioral information based on a condition for granting the flag indicating an estimation target for which the behavioral information can be used. .. The granting part
The granting device according to any one of claims 1 to 4 , wherein the flag is fastened to the action information based on the conditions for granting the flag used for generating a predetermined model. The granting part
The granting device according to any one of claims 1 to 5 , wherein the flag is fastened to the behavioral information based on a condition relating to the granting of the flag used for improving the efficiency of generation of a predetermined model. The granting part
The present invention according to any one of claims 1 to 6 , wherein the flag is given to the action information at the timing when the action information is acquired by the acquisition unit based on the condition for giving the flag. Grant device. The granting part
The granting device according to any one of claims 1 to 7 , wherein the flag is given to the action information in response to a determination using condition information indicating a condition for granting the flag. The granting part
The granting device according to any one of claims 1 to 8 , wherein the flag is imparted to the action information according to a determination using a determination model for determining whether to assign the flag. The acquisition unit
The granting device according to any one of claims 1 to 9 , wherein the behavior information regarding the behavior of the user on the Internet is acquired. A transmission unit that transmits information related to the behavior information satisfying the conditions for transmission to the predetermined external device to the predetermined external device.
The granting device according to any one of claims 1 to 10 , further comprising. The transmitter
The granting device according to claim 11 , wherein the behavior information to which the flag is added is transmitted. The transmitter
The 11th or 12th claim, wherein the information on the analysis result is transmitted when the analysis result based on the plurality of behavioral information to which the flag is given satisfies the condition for transmission to the predetermined external device. Grant device. It ’s a computer-executed granting method.
The acquisition process to acquire behavior information related to user behavior saved as a log ,
Said obtaining step said action information acquired by the a condition regarding grant flag on behavior information stored as a log, based on the action type indicating the type of action of the subject indicated by the flag user The first condition for estimating the target and the second condition different from the first condition, which are defined conditions and include information for determining the action indicated by the action type. And, based on the condition configured including
A granting method characterized by including. Acquisition procedure to acquire behavior information about user behavior saved as a log ,
The acquisition procedure has been the action information acquired by the a condition regarding grant flag on behavior information stored as a log, based on the action type indicating the type of action of the subject indicated by the flag user The first condition for estimating the target and the second condition different from the first condition, which are defined conditions and include information for determining the action indicated by the action type. And, based on the condition configured including
A granting program characterized by having a computer execute. It is a program that makes the computer function as a model that learns the user's behavior information saved as a log as input data and the score value for determining the addition of a flag to the behavior information as correct answer data.
The input layer where user behavior information is input and
Output that outputs the value of the score used for determining whether to give a flag determined based on the target indicated by the flag and the action type indicating the action type of the user to the action information input to the input layer. Layer and
A first element that is any layer from the input layer to the output layer and belongs to a layer other than the output layer.
Includes the first element and a second element whose value is calculated based on the weight of the first element.
To action information input to the input layer, each element belonging to the other layers except the output layer as the first element, by performing a computation based on the weight of said first element and said first element, said a first condition for estimating the target, a second condition different from the said first condition, is used and the second condition includes information for determining an activity in which the behavioral type shown, in the determination by As a model that outputs the score value from the output layer ,
A program to make a computer work.

Images