JP7354194B2 - Information provision device, information provision method, and information provision program - Google Patents

Description

The present invention relates to an information providing device, an information providing method, and an information providing program.

2. Description of the Related Art Conventionally, techniques for providing information such as advertisements according to user attributes are known. For example, Patent Document 1 discloses a technique for extracting advertisements according to user attributes and distributing the extracted advertisements to users.

Japanese Patent Application Publication No. 11-024603

However, the technology described in Patent Document 1 has room for improvement in terms of providing appropriate information to users.

The present application has been made in view of the above, and aims to provide an information providing device, an information providing method, and an information providing program that can appropriately provide information to users.

The information providing device according to the present application includes a distribution section, a specifying section, and a notification section. The distribution unit distributes the information to be distributed using a plurality of models that determine the destination of the information to be distributed. The specifying unit specifies the model for which the user has made an opt-out request among the plurality of models as the target model. The notification unit indicates a difference between a first information group distributed by the distribution unit when the target model is not opted out and a second information group distributed from the distribution unit when the target model is opted out. Notify the user who made the opt-out request of the difference information.

According to one aspect of the embodiment, it is possible to provide appropriate information to the user.

FIG. 1 is a diagram for explaining information provision processing according to an embodiment. FIG. 2 is a diagram illustrating an example of the configuration of the information providing system according to the embodiment. FIG. 3 is a diagram illustrating an example of the configuration of the terminal device according to the embodiment. FIG. 4 is a diagram illustrating an example of distribution information displayed on the display unit of the terminal device according to the embodiment. FIG. 5 is a diagram illustrating an example of opt-out inquiry information displayed on the display unit of the terminal device according to the embodiment. FIG. 6 is a diagram illustrating an example of the configuration of the information providing device according to the embodiment. FIG. 7 is a diagram illustrating an example of user information stored in the user information storage unit according to the embodiment. FIG. 8 is a diagram illustrating an example of model information stored in the model information storage unit according to the embodiment. FIG. 9 is a diagram illustrating an example of opt-out user information stored in the opt-out user information storage unit according to the embodiment. FIG. 10 is a diagram illustrating an example of difference information displayed on the display unit of the terminal device according to the embodiment. FIG. 11 is a diagram illustrating another example of difference information displayed on the display unit of the terminal device according to the embodiment. FIG. 12 is a diagram illustrating an example of recommendation information displayed on the display unit of the terminal device according to the embodiment. FIG. 13 is a diagram illustrating another example of recommendation information displayed on the display unit of the terminal device according to the embodiment. FIG. 14 is a flowchart illustrating an example of the flow of information processing by the processing unit of the information providing apparatus according to the embodiment. FIG. 15 is a flowchart illustrating an example of the flow of opt-out related processing by the processing unit of the information providing device according to the embodiment. FIG. 16 is a flowchart illustrating an example of the flow of opt-out cancellation recommendation processing by the processing unit of the information providing device according to the embodiment. FIG. 17 is a hardware configuration diagram showing an example of a computer that implements the functions of the information providing device according to the embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Below, an information providing apparatus, an information providing method, and a form for implementing an information providing program (hereinafter referred to as an "embodiment") according to the present application will be described in detail with reference to the drawings. Note that this embodiment does not limit the information providing apparatus, information providing method, and information providing program according to the present application. Moreover, each embodiment can be combined as appropriate within the range that does not conflict with the processing contents. Further, in each of the embodiments below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. Example of information provision processing]
First, an example of the information providing process according to the embodiment will be described using FIG. 1. FIG. 1 is a diagram for explaining information provision processing according to an embodiment.

As shown in FIG. 1, the information providing apparatus 1 according to the embodiment can communicate with terminal devices 2 ₁ , 2 ₂ , . . . , 2 _m used by users U ₁ , U ₂ , . . . , U _m It is connected to the terminal devices 2 ₁ , 2 ₂ , . . . , 2 _m and transmits and receives information thereto. For example, m is an integer of 3 or more. In the following, when each of the users _{U 1} , _{U 2 ,} . When each of _m is shown without being individually distinguished, it may be described as a terminal device 2.

The information providing device 1 delivers distribution information D ₁ , D ₂ , D ₃ , D ₄ , D ₅ , . . . , D _k , which is information to be distributed, to the user U. For example, k is an integer of 6 or more. Distribution information D ₁ , D ₂ , D ₃ , D ₄ , D ₅ , ..., D _k to user U is, for example, distributed information D ₁ , D ₂ , D ₃ , D ₄ , D ₅ , ..., D _k to the user U's terminal device 2.

In the following, when each of the distribution information D ₁ , D ₂ , D ₃ , D ₄ , D ₅ , . . . , D _k is indicated without being individually distinguished, it may be referred to as distribution information D. The distribution information D ₁ , D ₂ , D ₃ , D ₄ , D ₅ , ..., D _k is information displayed on the terminal device 2, and is, for example, at least one of text information and image information. Contains information. The image information is still image information, animation information, or moving image information.

The information providing device 1 uses a plurality of models M ₁ , _{M 2} , M ₃ , M ₄ , . To deliver. For example, n is an integer of 5 or more. For _example , the _plurality of models M ₁ , _{M 2 , M 3} , _{M 4 ,} . This is a model for determining whether U has an interest or not.

Specifically, the model _M1 is a model corresponding to the target _T1 , and it is determined whether the user U who is interested in the information of the target _T1 has an interest in the distribution information D. judge. The model _M2 is a model corresponding to the target _T2 , and it is determined whether the user U who is interested in the information of the target _T2 has an interest in the distribution information D.

Furthermore, the model M ₃ is a model corresponding to the target T ₃ , and it is determined whether the user U who has an interest in the information of the target T ₃ has an interest in the distribution information D or not. The model _M4 is a model corresponding to the target _T4 , and it is determined whether the user U who has an interest in the information on the target _T4 has an interest in the distribution information D or not. The model M _n is a model corresponding to the target T _n , and it is determined whether the user U who has an interest in the information of the target T _n has an interest in the distribution information D or not.

In the following, when _each of the _objects T ₁ , T ₂ , T ₃ , T ₄ , _. When each of M ₃ , M ₄ , . . . , M _n is shown without being individually distinguished, it may be referred to as model M.

When the information provided by the information providing device 1 is news content, the target T is, for example, politics, economy, international, business, entertainment, sports, hobbies, or society. Further, the object T may be a subdivided object, for example, a hobby may be subdivided into a car, a bicycle, a motorbike, a movie, music, camping, or travel. Further, the information provided by the information providing device 1 may be advertising content instead of or in addition to news content, or may be content other than news content and advertising content.

Model M is a learning model that receives distribution information D as input and outputs a score indicating the degree to which user U has an interest in distribution information D. For example, when information about object T ₁ is input to model M ₁ , the score output from model M ₁ becomes higher than when information about object T ₂ is input to model M ₁ . Furthermore, when information about the target T ₂ is input to the model M ₂ , the score output from the model M ₂ becomes higher than when inputting information about the target T ₁ to the model M ₂ .

For example, the model M uses a data set that includes information to be distributed and information indicating whether or not a user U who has an interest in the target T has an interest in the information to be distributed. Generated every T. For example, the model _M1 uses a data set that includes information to be distributed and information indicating whether a user U who has an interest in the target _T1 has an interest in the information to be distributed. generated by.

The model M is generated, for example, by machine learning using a neural network such as a convolutional neural network or a recurrent neural network, but is not limited to such examples. For example, the model M may be generated using machine learning using a learning algorithm such as linear regression or logistic regression instead of using a neural network.

When distributing the distribution information D, the information providing device 1 inputs the distribution information D into each _{of the} models M ₁ , M ₂ , M ₃ , _{M 4 ,} . The distribution information D is distributed to the user U associated with the model whose output score satisfies a preset distribution condition among M ₃ , M ₄ , . . . , M _n . The preset distribution condition is the model with the highest output score among the models M ₁ , M ₂ , M ₃ , M ₄ , ..., M _n , or the model whose output score is greater than or equal to a preset threshold. models, etc.

Here, it is assumed that models M ₁ , M ₂ , M ₃ , M ₄ , and M _n are associated with user U ₁ , distribution information D ₁ is information for target T ₁ , and distribution information D ₂ is information for target T 1. It is assumed that the distribution information _{D 3 is} the information of the target T ₃ , and the distribution information D ₄ is the information of the target T ₄ . Further, it is assumed that the distribution information _D5 is information on the target _Tn .

In this case, the information providing device 1 uses the models M ₁ , M ₂ , M ₃ , M ₄ , and M _n to select one of the distribution destinations of the distribution information D ₁ , D ₂ , D ₃ , D ₄ , and D ₅ . The user U ₁ is determined, and the distribution information D ₁ , D ₂ , D ₃ , D ₄ , D ₅ is distributed to the user U ₁ (step S1). In the example shown in FIG. 1, the distribution information D ₁ , D ₂ , D ₃ , D ₄ , D ₅ is distributed to the user U ₁ by transmitting the distribution information D ₁ , D ₂ , D ₃ , D ₄ , D ₅ to the terminal. This is done by distributing the data to the device ₂₁ .

The user U ₁ to whom the distribution information D ₁ , D ₂ , D ₃ , D ₄ , and D ₅ has been distributed receives the distribution information D ₁ among these distribution information D ₁ , D ₂ , D ₃ , D ₄ , and D ₅ . If it is determined that the model _M1 is not desirable, the user wishes to opt out of the model M1 (step S2). The user U ₁ 's desire to opt out of the model M ₁ indicates the user U's intention to refuse notification of information distributed using the model M ₁ , and for example, the user U 1's desire to opt out of the model M 1 indicates the user U's intention to refuse notification of information distributed using the model M ₁ . This is performed by user _U1 's operation.

When the user U ₁ wishes to opt out of the model M ₁ , an opt-out request, which is information indicating that he/she wishes to opt out of the model M ₁ , is transmitted from the terminal device 2 ₁ to the information providing device 1 ( Step S3).

When the information providing device 1 receives an opt-out request from the terminal device 2 ₁ , the information providing device 1 sets the model M ₁ as the target model, and selects the first information group distributed when the target model is not opted out and the target model is opted out. Difference information indicating the difference from the second information group distributed when the information is distributed is generated (step S4). Then, the information providing device 1 transmits the generated difference information to the terminal device ₂₁ (step S5).

When the terminal device ₂₁ receives the difference information from the information providing device 1, it displays the difference information (step S6). In the example shown in FIG. 1, the difference information displayed on the terminal device 2 ₁ includes distribution information D ₁ , D ₂ , D ₃ , and D ₄ that is distributed when model M ₁ , which is the target model, is not opted out. It includes a first information group and a second information group including distribution information D ₂ , D ₃ , D ₄ , and D ₅ that is distributed when model M ₁ is opted out.

As a result, the user U ₁ can understand whether or not the group of information distributed is different before and after the model M ₁ who requested to opt out is opted out, by referring to the difference information. . Therefore, the user U ₁ can appropriately determine whether or not to opt out of the model M ₁ from which he or she wishes to opt out. In this way, when the user U wishes to opt out, the information providing device 1 can inform the user U of the disadvantages of opting out for the model M, and can provide appropriate information to the user U.

Note that the difference information is not limited to the example shown in FIG. 1, and may be information that alternately presents the first information group and the second information group to the user U, for example. Further, the difference information may be information that clearly indicates information included in the first information group but not included in the second information group and information included in the second information group but not included in the first information group. good.

[2. Information provision system 100]
FIG. 2 is a diagram showing an example of the configuration of the information providing system 100 according to the embodiment. As shown in FIG. 2, the information providing system 100 according to the embodiment includes an information providing device 1 and terminal devices 2 ₁ , 2 ₂ , . . . , 2 _m . The terminal devices 2 ₁ , 2 ₂ , . . . , 2 _m are, for example, smartphones, tablet PCs (Personal Computers), or notebook PCs.

The information providing device 1 is capable of transmitting and receiving information to and from the terminal devices 2 ₁ , 2 ₂ , . . . , 2 _m via the communication network 3 . The communication network 3 is, for example, a WAN (Wide Area Network) such as the Internet or a LAN (Local Area Network). Note that the communication network 3 has a configuration including, for example, a mobile communication system such as 4G (4th Generation) or 5G (5th Generation), but is not limited to such an example.

[3. Terminal device 2]
FIG. 3 is a diagram showing an example of the configuration of the terminal device 2 according to the embodiment. As shown in FIG. 3, the terminal device 2 according to the embodiment includes a communication section 10, a display section 11, an operation section 12, a sensor group 13, a storage section 14, and a processing section 15.

[3.1. Communication department 10]
The communication unit 10 is realized by, for example, a NIC (Network Interface Card). The communication unit 10 is connected to the communication network 3 by wire or wirelessly, and transmits and receives information to and from the information providing device 1 via the communication network 3.

[3.2. Display section 11]
The display unit 11 is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display.

[3.3. Operation unit 12]
The operation unit 12 includes, for example, a keyboard including keys for inputting letters, numbers, and spaces, an enter key, and arrow keys, a mouse, a power button, and the like. When the display unit 11 is a touch panel display, the operation unit 12 may be a touch panel.

[3.4. Sensor group 13]
The sensor group 13 includes, for example, an acceleration sensor, a gyro sensor, a geomagnetic sensor, an illumination sensor, an image sensor, and the like. The acceleration sensor is a sensor that detects the acceleration of the terminal device 2. The gyro sensor is a sensor that detects postures such as tilt and rotation of the terminal device 2. A geomagnetic sensor is a sensor that detects geomagnetism. The illuminance sensor is a sensor that detects illuminance indicating brightness and darkness around the terminal device 2, and the image sensor is a sensor that takes an image of the surroundings of the terminal device 2.

[3.5. Storage 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, or a storage device such as a hard disk or an optical disk.

The storage unit 14 stores, for example, information transmitted from the information providing device 1 and acquired by the processing unit 15 via the communication network 3 and the communication unit 10, and detection information that is information detected by the sensor group 13. Ru.

[3.6. Processing unit 15]
The processing unit 15 is a controller, and various programs stored in the storage device inside the terminal device 2 use the RAM as a work area by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). This is achieved through execution.

Furthermore, the processing unit 15 may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The processing section 15 includes an information acquisition section 16, a display processing section 17, and an output section 18.

[3.6.1. Information acquisition unit 16]
The information acquisition unit 16 acquires information transmitted from the information providing device 1 and received by the communication unit 10 via the communication network 3. The information transmitted from the information providing device 1 is, for example, distribution information D.

[3.6.2. Display processing unit 17]
The display processing unit 17 causes the display unit 11 to display the information acquired by the information acquisition unit 16. For example, the display processing unit 17 causes the display unit 11 to display a screen including the distribution information D acquired by the information acquisition unit 16 and the like.

FIG. 4 is a diagram showing an example of distribution information displayed on the display unit 11 of the terminal device 2 according to the embodiment. As shown in FIG. 4, on the display unit 11 of the terminal device 2, the display processing unit 17 displays distribution information D ₁ , D ₂ , D ₃ , and D ₄ in a timeline.

In the example shown in FIG. 4, distribution information _D1 is news information about entertainment, distribution information _D2 is news information about companies, distribution information _D3 is news information about weather forecasts, Distribution information _D4 is information on news related to society.

Each of the distribution information D ₁ , D ₂ , D ₃ , and D ₄ is information including images and characters, and when selected by a tap operation or a click operation, more detailed information is distributed from the information providing device 1. , such detailed information is displayed on the display unit 11 by the display processing unit 17. Such detailed information is, for example, landing page information.

Further, each distribution information D ₁ , D ₂ , D ₃ , D ₄ includes a mark 50 for selecting opt-out, and when the user U selects the mark 50 by operating the operation unit 12 , opt-out inquiry information for selecting opt-out is displayed on the display unit 11.

FIG. 5 is a diagram showing an example of opt-out inquiry information displayed on the display unit 11 of the terminal device 2 according to the embodiment. Opt-out inquiry information 51 shown in FIG. 5 includes a distribution information area 52, an inquiry information area 53, a Yes button 54, and a No button 55.

In the example shown in FIG. 5, distribution information _D1 is displayed in the distribution information area 52, and the inquiry information area 53 includes the words "Do you wish to opt out (stop distribution)?" . When the user U selects the Yes button 54 by operating the operation unit 12, the output unit 18 transmits an opt-out request to the information providing device 1, as described later.

Further, when the user U selects the No button 55 by operating the operation unit 12, the display processing unit 17 distributes the information to be displayed on the display unit 11 from the opt-out inquiry information 51 shown in FIG. 5 to the distribution shown in FIG. Return to information D. Further, even when the user U selects the Yes button 54 by operating the operation unit 12, the display processing unit 17 changes the information to be displayed on the display unit 11 from the opt-out inquiry information 51 shown in FIG. 5 to the information shown in FIG. Return to distribution information D.

Note that the method for confirming the desire to opt out is not limited to the above example. For example, when the mark 50 shown in FIG. 4 is tapped or right-clicked, characters such as "Do you wish to opt out (stop distribution)?" appear on the distribution information D corresponding to the mark 50. A column may be displayed in a selectable manner, and when such a character string is selected, an opt-out request may be transmitted from the terminal device 2 to the information providing device 1.

In the examples shown in FIGS. 4 and 5, the distribution information D and the opt-out inquiry information 51 are web content, but the content acquired and displayed on the terminal device 2 may be used instead of or in addition to the web content. , may be email content.

[3.6.3. Output section 18]
The output unit 18 transmits operation information, which is information corresponding to an operation on the operation unit 12 by the user U, to the information providing device 1 via the communication unit 10, for example.

For example, when the user U wishes to opt out by operating the operation unit 12, the output unit 18 transmits opt-out information to the information providing device 1 via the communication unit 10. For example, when the Yes button 54 is selected by the user U operating the operation unit 12, the output unit 18 transmits an opt-out request to the information providing device 1 via the communication unit 10. The opt-out request includes identification information unique to the model M or distribution information D for which the customer wishes to opt-out, or identification information unique to the store for which the customer wishes to opt-out.

The output unit 18 transmits opt-out information to the information providing device 1 via the communication unit 10 when the user U selects opt-out by operating the operation unit 12. The opt-out information includes identification information specific to the model M or distribution information D for which opt-out is selected, or identification information specific to the store for which opt-out is selected.

Further, the output unit 18 transmits detection information, which is information detected by the sensor group 13, to the information providing device 1 via the communication unit 10.

[4. Information provision device 1]
FIG. 6 is a diagram showing an example of the configuration of the information providing device 1 according to the embodiment. As shown in FIG. 6, the information providing device 1 according to the embodiment includes a communication section 20, a storage section 21, and a processing section 22.

[4.1. Communication department 20]
The communication unit 20 is realized by, for example, a NIC. The communication unit 20 is connected to the communication network 3 by wire or wirelessly, and transmits and receives information to and from the terminal device 2 via the communication network 3.

[4.2. Storage unit 21]
The storage unit 21 is realized by, for example, a semiconductor memory device such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 21 includes a user information storage unit 30, a model information storage unit 31, a distribution information storage unit 32, an opt-out user information storage unit 33, and a store information storage unit 34.

[4.2.1. User information storage unit 30]
The user information storage unit 30 stores user information including information on users U ₁ , U ₂ , . . . , U _m . FIG. 7 is a diagram illustrating an example of user information stored in the user information storage unit 30 according to the embodiment.

As shown in FIG. 7, the user information stored in the user information storage unit 30 includes information such as "user ID (identifier)" and "attribute" for each user U. “User ID” is identification information unique to each user U.

“Attribute” is information indicating the user U's attribute. User U's attributes include, for example, demographic attributes and psychographic attributes. The demographic attributes are demographic attributes of the user U, such as gender, age, address, occupation, or annual income. The psychographic attributes are attributes that indicate the values, lifestyle, personality, preferences, etc. of the user U.

In the example shown in FIG. 7, the user U with the user ID "UA1" has a gender of "male," an age of "30s," and is interested in "clothes." Further, the user U with the user ID "UA2" has a gender of "female", an age of "20s", and has an interest in "clothes" and the like. Further, the user U with the user ID "UA3" has a gender of "male", an age of "40s", and has an interest in "cars" and the like.

[4.2.2. Model information storage unit 31]
The model information storage unit 31 shown in FIG. 6 stores model information including information on models M ₁ , M ₂ , M ₃ , M ₄ , . . . , M _n . FIG. 8 is a diagram showing an example of model information stored in the model information storage unit 31 according to the embodiment.

As shown in FIG. 8, the user information stored in the model information storage unit 31 includes information such as "model ID", "model", and "user list" for each model M. “Model ID” is identification information unique to each model M. “Model” is information on a model M that determines the distribution destination of information to be distributed.

Each of the plurality of models M is a model for determining whether or not the user U has an interest in the distribution information D, for example. The plurality of models M are, for example, models corresponding to mutually different objects T. In the following, a model for determining whether the user U has an interest in the distribution information D may be referred to as an interest model.

For example, when the information provided from the information providing device 1 is web content information, the target T indicates the type of web content. When the information provided by the information providing device 1 is news web content, the type of web content is, for example, political, economic, international, corporate, entertainment, sports, hobby, or social. Further, the object T may be, for example, a subdivided object such as a car, a bicycle, a motorbike, a movie, music, camping, or travel, etc. as a subdivided object of hobbies. .

In addition, if the information provided by the information providing device 1 is video content, the type of web content may be, for example, domestic movie, domestic drama, domestic anime, foreign movie, foreign drama, foreign anime, variety, documentary, sports, etc. Or news, etc.

Furthermore, for example, when the information provided from the information providing device 1 is e-mail information, the target T indicates the type of information shown in the e-mail. If the information provided by the information providing device 1 is related to hobbies, the information shown in the e-mail may be, for example, cars, bicycles, motorcycles, movies, music, camping, or travel.

Further, the plurality of models M may include, for example, a model for each user context. In this case, the model M is, for example, a model that determines whether or not the context of the user U is a context defined by the model. Determine whether the context is specified by the model. For example, model M is a model that estimates various user contexts such as "bought a PC (Personal Computer)," "went to store A," or "prepared food." Below, a model for each user context may be referred to as a user context model.

The "user list" is a list of users U associated with model M, and is a user ID of each user U associated with model M. In the example shown in FIG. 8, the model with model ID "MA1" is "model M ₁ ", and user IDs such as "UA1", "UA2", and "UA3" are associated with the model. The model with model ID "MA2" is "model M ₂ ", and user IDs such as "UA2", "UA4", and "UA5" are associated with the model.

Further, the model with model ID "MA3" is "model M ₃ ", and user IDs such as "UA1", "UA3", and "UA6" are associated with the model. The model with model ID "MA4" is "model M ₄ ", and user IDs such as "UA3", "UA4", and "UA5" are associated with the model.

[4.2.3. Distribution information storage unit 32]
The distribution information storage unit 32 shown in FIG. 6 stores distribution information D, which is information distributed to the user U. The distribution information D stored in the distribution information storage unit 32 is web content such as news or information provided to the user U by e-mail, and may include advertising content. When the distribution information D is web content such as news, the distribution information D is displayed in a timeline on the terminal device 2, but the distribution information D is not limited to information displayed in a timeline on the terminal device 2.

[4.2.4. Opt-out user information storage unit 33]
The opt-out user information storage unit 33 shown in FIG. 6 stores opt-out user information including the user ID of the user U for whom opt-out is set for each model M. FIG. 9 is a diagram showing an example of opt-out user information stored in the opt-out user information storage unit 33 according to the embodiment.

As shown in FIG. 9, the opt-out user information stored in the opt-out user information storage unit 33 includes information such as "model ID" and "opt-out user list" for each model M. "Model ID" is identification information unique to each model M, and is the same as the model ID shown in FIG.

The "opt-out user list" is a list of users U who have selected opt-out for model M, and includes the user ID of each user U who has selected opt-out for model M. In the example shown in FIG. 9, the model with model ID "MA1" is set with the user ID "UA4" as an opt-out user, and the model with model ID "MA2" is set with the user ID of user U as the opt-out user. is not set.

[4.2.5. Store information storage unit 34]
The store information storage unit 34 shown in FIG. 6 stores store information that is information for each store (not shown). Store information for each store is information regarding the corresponding store, and includes, for example, event information, sale item information, new product information, new service information, and the like. Store information is information provided to user U by e-mail, for example, but may also be information provided to user U as web content.

In addition, the store information storage unit 34 stores a distribution exclusion user list for each store. The distribution excluded user list includes user IDs of users U who do not receive store information distributed from the information providing device 1.

[4.3. Processing unit 22]
The processing unit 22 shown in FIG. 6 is a controller, and various programs (corresponding to an example of an information providing program) stored in a storage device inside the information providing device 1 use a RAM as a work area by, for example, a CPU or an MPU. This is achieved by executing as . Further, the processing unit 22 may be realized by, for example, an integrated circuit such as an ASIC or an FPGA.

The processing unit 22 transmits and receives information to and from the terminal devices 2 ₁ , 2 ₂ , ..., 2 _m based on the information acquired by the communication unit 20 and the information stored in the storage unit 21 . conduct. The processing unit 22 includes an acquisition unit 40, a distribution unit 41, a reception unit 42, a specification unit 43, a notification unit 44, and a recommendation unit 45.

[4.3.1. Acquisition unit 40]
The acquisition unit 40 acquires information transmitted from the terminal device 2 via the communication network 3. The information transmitted from the terminal device 2 is, for example, operation information that is information corresponding to an operation on the operation unit 12 by the user U, or detection information that is information detected by the sensor group 13. The operation information transmitted from the terminal device 2 includes, for example, an opt-out request or opt-out information.

[4.3.2. Distribution department 41]
The distribution unit 41 transmits the distribution information D to the terminal device 2 via the communication unit 20 and the communication network 3 using a plurality of models M that determine the distribution destination of the information to be distributed. Deliver to user U.

When the model M is an interest model, the distribution unit 41 inputs the distribution information D to the plurality of models M, and selects the user U associated with the model M that satisfies the preset distribution condition among the plurality of models M. The distribution information D is determined as the distribution destination, and the distribution information D is distributed to the user U of the determined distribution destination. The preset distribution condition is, for example, a model M whose output score is equal to or greater than a preset threshold and outputs the highest score among the plurality of models M, but is not limited to such an example.

For example, when the distribution information D ₁ is input to the models M ₁ , M ₂ , M ₃ , M ₄ , ..., M _n , the models M ₁ , M ₂ , M ₃ , M ₄ , ..., M It is assumed that the highest score among the scores output from _n is greater than or equal to a preset threshold and is the score output from model _M1 . Further, it is assumed that the model information stored in the model information storage section 31 is in the state shown in FIG. In this case, the distribution unit 41 determines the users U whose user IDs are "UA1,""UA2," and "UA3" as the users U to whom the distribution information _D1 will be distributed.

Furthermore, when the distribution information D ₂ is input to the models M ₁ , M ₂ , M ₃ , M ₄ , ..., M _n , the models M ₁ , M ₂ , M ₃ , M ₄ , ..., M It is assumed that the highest score among the scores output from _n is greater than or equal to a preset threshold and is the score output from model _M2 . Further, it is assumed that the model information stored in the model information storage section 31 is in the state shown in FIG. In this case, the distribution unit 41 determines the users U whose user IDs are "UA2,""UA4," and "UA5" as the users U who will be the distribution destinations.

Further, when the model M is a user context model, the distribution unit 41 inputs the detection information transmitted from the terminal device 2 and acquired by the acquisition unit 40 to each user context model, and calculates the score output by each user context model. Among them, a user context model that satisfies preset distribution conditions is determined. The preset distribution condition is, for example, that the output score is greater than or equal to a preset threshold, but is not limited to this example.

Distribution information D is associated with each user context model, and the distribution unit 41 transmits the distribution information D associated with the user context model that outputs a score equal to or higher than a preset threshold to the user U corresponding to the detected information. Deliver to.

For example, assume that model M ₁ is a user context model and distribution information D ₁ is associated with model M ₁ . It is also assumed that when the detection information from the terminal device 2 ₁ of the user U ₁ is input to the model M ₁ , the score output from the model M ₁ is equal to or higher than a preset threshold. In this case, the distribution unit 41 distributes the distribution information _D1 to the user _U1 .

Moreover, instead of or in addition to the detected information, the distribution unit 41 distributes the operation history of the terminal device 2 by the user U, the position information of the terminal device 2, the schedule information of the user U, etc. as input information to the model M. The previous user U can also be determined.

Further, when the distributed distribution information D is selected by the user U, the distribution unit 41 transmits detailed information of the distribution information D selected by the user U to the terminal device 2 via the communication unit 20 and the communication network 3. By doing so, detailed information of the distribution information D selected by the user U is distributed to the user U.

For example, when a plurality of distribution information D is input to a plurality of models M, the distribution unit 41 inputs the plurality of distribution information D so that the distribution information D with a higher score outputted from the model M is preferentially displayed at a higher rank. can be delivered.

For example, assume that the scores output from the model M are higher in the order of distribution information D ₃ , distribution information D ₂ , distribution information D ₁ , distribution information D ₅ , and distribution information D ₄ . In this case, the distribution unit 41 displays the distribution information _D3 at the top, the distribution information _D2 at the second highest, the distribution information _D1 at the third highest, and the distribution information _D5 . The distribution information D ₁ , D ₂ , D 3 , D ₄ , and _{D 5 are} distributed so that the distribution information D 4 is displayed at the 4th highest rank, and the distribution information D ₄ is displayed at the 5th highest rank.

Further, it is assumed that the plural pieces of distribution information D are news contents, and the plural pieces of distribution information D are displayed in a timeline on the terminal device 2. In this case, the distribution unit 41 arranges that if the news is from the same time period, the higher the score output from model M is, the higher the score is displayed, and if the news is from different times, the news that is closer to the current time is displayed higher. , multiple pieces of distribution information D are distributed. Each model M can be weighted, and by increasing the weight, the score output from model M can be increased, and by decreasing the weight, the score output from model M can be decreased. can.

Note that in the model information storage unit 31, the user ID of the user U who has selected opt-out is excluded from the association with the model M for which opt-out has been selected. Therefore, information to be distributed corresponding to model M for which user U has selected opt-out is not distributed to user U who has selected opt-out.

Further, the distribution unit 41 does not need to associate the user U with the model M in advance. In this case, the distribution unit 41 can estimate the interests of the user U based on the estimation model for estimating the interests of the user U. This estimation model is a model that receives user information as input and determines whether the user U has an interest in the target T, and is provided for each target T. Then, the distribution unit 41 can associate the user U with the model M by identifying the model M corresponding to the target T that matches or is similar to the estimated interests of the user U.

Further, the distribution unit 41 can distribute the store information to the user U by transmitting the store information stored in the store information storage unit 34 to the terminal device 2 via the communication unit 20 and the communication network 3. . The distribution unit 41 estimates the users U who are interested in the store by inputting the attribute information of each user U into an estimation model that estimates whether the user U is interested in the store for each store. , performs a process of distributing store information to the estimated user U for each store.

Note that when the distribution exclusion user list is stored in the store information storage unit 34, the distribution unit 41 selects users U who are estimated to have an interest in the store other than the users U whose user ID is included in the distribution exclusion user list. Store information is distributed to user U.

[4.3.3. Reception Department 42]
The reception unit 42 accepts an opt-out request received by the communication unit 20 via the communication network 3. The opt-out request is information indicating a desire to opt-out of the information to be distributed, and the types of opt-out requests include an opt-out request for Model M and an opt-out request for the store.

Further, the reception unit 42 accepts the distribution target for which the user U has selected opt-out as an opt-out target. The opt-out target is, for example, target T or a store. The receiving unit 42 receives the opt-out information received by the communication unit 20 via the communication network 3 as opt-out target information.

The reception unit 42 receives the model information stored in the model information storage unit 31 or the opt-out user information storage unit 33 based on the opt-out information received by the communication unit 20 via the communication network 3. Update opt-out user information. The opt-out information is opt-out information for model M or opt-out information for the store.

For example, when accepting opt-out information for model M ₁ by user U ₁ , the reception unit 42 changes the state in which the user ID of user U ₁ is associated with model M ₁ in the model information in the model information storage unit 31 . Change to unassociated state. Further, when accepting opt-out information for model M ₁ by user U ₁ , reception unit 42 inputs the user ID of user U ₁ for model M ₁ in opt-out user information in opt-out user information storage unit 33 . Associate with the target model.

In addition, when accepting opt-out information for a store, the receiving unit 42 selects opt-out in the distribution-excluded user list of the store for which opt-out is selected from the distribution-excluded user list stored in the store information storage unit 34. Add the user ID of the opt-out user, user U.

Further, the reception unit 42 accepts an opt-out cancellation request received by the communication unit 20 via the communication network 3. For example, when the received opt-out cancellation request is an opt-out cancellation request for model M, the receiving unit 42 selects the model information stored in the model information storage unit 31 or the opt-out user information storage unit 33. Update opt-out user information.

Further, if the received opt-out cancellation request is an opt-out cancellation request for a store, the reception unit 42 excludes the store corresponding to the opt-out cancellation request from the distribution exclusion user list stored in the store information storage unit 34. Delete the user ID of the opt-out user from the user list.

[4.3.4. Specification part 43]
The identifying unit 43 identifies the model M for which the user U has made an opt-out request among the plurality of models M as the target model. For example, when the acceptance unit 42 receives an opt-out request for the model M ₁ from the user U ₁ , the identification unit 43 identifies the model M ₁ as the target model.

[4.3.5. Notification section 44]
The notification unit 44 notifies the opt-out requesting user, who is the user U who made the opt-out request, of the difference information. The difference information is the difference between the first information group distributed from the distribution unit 41 when the target model is not opted out and the second information group distributed from the distribution unit 41 when the target model is opted out. This is information indicating. The notification to the opt-out requesting user is performed by transmitting the difference information to the terminal device 2 of the opt-out requesting user.

FIG. 10 is a diagram showing an example of difference information displayed on the display unit 11 of the terminal device 2 according to the embodiment. The difference information 60 shown in FIG. 10 includes an inquiry information area 61, a first information group 62, a second information group 63, a Yes button 64, and a No button 65.

The inquiry information area 61 includes information inquiring whether or not to select opt-out, and in the example shown in FIG. 10, "The following differences will appear before and after opt-out. Are you sure you want to opt-out?" Contains the string.

The first information group 62 shows an example of a plurality of pieces of distribution information D distributed from the distribution unit 41 when the target model is not opted out. In the example shown in FIG. 10, the first information group 62 includes a plurality of distribution information D ₁ , D ₂ , D ₃ , and D ₄ .

The second information group 63 shows an example of a plurality of pieces of distribution information D distributed from the distribution unit 41 when the target model is opted out. In the example shown in FIG. 10, the second information group 63 includes a plurality of distribution information D ₂ , D ₃ , D ₄ , and D ₅ .

The user U opts out of the terminal device 2 by operating the operation unit 12 and selecting the Yes button 64 while the difference information 60 shown in FIG. 10 is displayed on the display unit 11 of the terminal device 2. Information is transmitted to the information providing device 1. Such opt-out information is received by the reception unit 42, and the model information stored in the model information storage unit 31 and the opt-out user information stored in the opt-out user information storage unit 33 are updated by the reception unit 42. .

When the user U selects the No button 65 by operating the operation unit 12 while the difference information 60 shown in FIG. 10 is displayed on the display unit 11 of the terminal device 2, the information displayed on the display unit 11 transitions to the state shown in FIG. 4, for example. Further, when the user U selects the Yes button 64 by operating the operation unit 12, the information displayed on the display unit 11 shifts to the state shown in FIG. 4, for example.

Each of the first information group 62 and the second information group 63 includes, for example, a preset number of distribution information D, but is not limited to this example. For example, when the user U performs a scroll operation or the like by operating the operation unit 12, the notification unit 44 increases the number of distribution information D included in each of the first information group 62 and the second information group 63. You can also do that.

In the example shown in FIG. 10, the difference information 60 is information in which the first information group 62 and the second information group 63 are simultaneously displayed and presented on the display unit 11, but the first information group 62 and the second information group The group 63 may be displayed and presented on the display unit 11 alternately.

Further, the difference information 60 specifies information that is included in the first information group 62 and not included in the second information group 63 and information that is included in the second information group 63 and not included in the first information group 62. It may be information. FIG. 11 is a diagram showing another example of the difference information 60 displayed on the display unit 11 of the terminal device 2 according to the embodiment.

In the example shown in FIG. 11, distribution information D1 is highlighted and clearly displayed as information included in the first information group 62 and not included in the second information group 63, and distribution information _D1 is clearly displayed as information included in the second information group 63 and not included in the second information group 63. As the information not included in the 1 information group 62, the distribution information _D5 is highlighted and clearly displayed.

Note that the distribution information D included in the difference information 60 is the distribution information D included in the first information group 62 but not included in the second information group 63 and the distribution information D included in the second information group 63 and in the first information group 62. It may also be limited to the distribution information D that is not included. With this also, the notification unit 44 can distinguish between information included in the first information group 62 and not included in the second information group 63 and information included in the second information group 63 and included in the first information group 62 based on the difference information 60. It is possible to clearly indicate the information that is not included.

When the distribution information D or store information is information displayed on a timeline, the distribution information D or store information included in the first information group 62 and second information group 63 of the difference information 60 distributed from the notification unit 44 is displayed on a timeline. Although displayed as a line, the example is not limited to this example.

Further, when the distribution information D or the store information is information distributed by e-mail, the first information group 62 is the distribution information included in the first information group 62 and the second information group 63 of the difference information 60 to be distributed. D or store information is displayed as a list, but is not limited to this example.

The notification unit 44 also generates difference information 60 that includes, as a first information group, a group of information that is distributed from the distribution unit 41 when the target model is not opted out while the weight of the target model with respect to the opt-out requesting user is increased. It is also possible to notify the opt-out requesting user.

In this way, by increasing the weight of the target model, the probability that the distribution information D selected by the target model among the plurality of distribution information D included in the first information group is displayed on the display unit 11 of the terminal device 2 is increased. You can increase the number of items and display them preferentially. By preferentially displaying the distribution information D selected by the target model at the top, it is possible to emphasize the distribution information D selected using the target model.

The notification unit 44 may also include in the difference information 60 information that the greater the difference between the first information group 62 and the second information group 63, the more strongly the opt-out requesting user is restrained. can.

For example, when including an incentive to be given to an opt-out requesting user in the difference information 60, the notification unit 44 indicates that the larger the difference between the first information group 62 and the second information group 63, the more likely the user will be able to opt out if the user does not opt out. Increase incentives given to requesting users. Thereby, the larger the difference between the first information group 62 and the second information group 63, the more strongly the notification unit 44 can restrict the opt-out requesting user. The incentive is, for example, the granting of points or the granting of qualifications to participate in a lottery for presents.

The notification unit 44 can also change the weight of the target model for the opt-out requesting user based on the attributes of the opt-out requesting user. For example, the notification unit 44 can increase the weight of the target model as the user U whose attribute is more rare among the users U associated with the target model. The notification unit 44 determines which users U are highly rare based on the distribution of attributes of the users U associated with the target model. The fewer the number of users U who have the same attribute among the multiple users U associated with the target model, the higher the rarity of the attribute.

In addition, when the opt-out requesting user has a specific attribute or when the opt-out requesting user does not have a specific attribute, the notification unit 44 assigns a higher weight to the target model than when the opt-out requesting user does not have a specific attribute. can do.

Further, the notification unit 44 can also increase the weight of the target model as the period from being associated with the target model to opting out is longer. Furthermore, the notification unit 44 can also increase the weight of the target model as the number or frequency of past opt-outs increases.

Further, the notification unit 44 can also increase the weight of the target model as the number of times or frequency that the opt-out requesting user has made an opt-out request for the target model in the past is greater.

In addition, the notification unit 44 determines that when the opt-out requesting user is a user U who did not select opt-out after making an opt-out request for a related model that is a model M related to the target model, compared to a case where this is not the case. It is also possible to increase the weight of the target model.

The related model is, for example, a model M whose user list, which is a list of a plurality of associated users U, is similar to a list of a plurality of users U associated with the target model, and for example, a list of all associated users U. The model M is one in which the proportion of users U who are also associated with the target model is greater than or equal to a preset proportion.

Further, the notification unit 44 can extract the user U whose attributes are similar to the opt-out requesting user as a similar user, and further notify the opt-out requesting user of the opt-out status of the similar user for the target model. Thereby, the notification unit 44 can prevent the opt-out requesting user from selecting opt-out, for example, when most similar users have not opted out. The notification unit 44 determines the opt-out status of similar users based on the opt-out user information stored in the opt-out user information storage unit 33.

A similar user is a user U whose attributes indicated by the user information are similar to those of the opt-out requesting user, and for example, the distance between the attributes indicated by the opt-out requesting user's user information and the attributes indicated by the similar user's user information is The user U is within a preset range. Note that the distance between attributes is, for example, Euclidean distance, Manhattan distance, Chebyshev distance, or Mahalanobis distance.

In addition to the target model, the notification unit 44 also includes information including, as a second information group 63, a group of information distributed from the distribution unit 41 when a similar model, which is a model M similar to the target model, is opted out. The opt-out requesting user can also be notified as the difference information 60. In this case, when the opt-out requesting user selects opt-out for the target model, opt-out for the similar model is automatically set by the reception unit 42.

[4.3.6. Recommendation section 45]
After the distribution unit 41 starts distributing information on multiple distribution targets other than the opt-out target to the opt-out user, the recommendation unit 45 sends recommended information that recommends cancellation of opt-out to the opt-out target to the opt-out user. to notify. The opt-out target is a distribution target for which opt-out is selected by the opt-out user, and is, for example, target T, model M, or a store.

The recommendation information is, for example, information that notifies the opt-out user of the benefits of canceling the opt-out of the opt-out target, and thereby can urge the opt-out user to cancel the opt-out.

For example, the recommendation information includes information that is distributed from the distribution unit 41 to the opt-out user when the opt-out user does not select an opt-out as an opt-out target. Thereby, the opt-out user can easily understand the merits of canceling the opt-out of the opt-out target.

FIG. 12 is a diagram showing an example of recommendation information displayed on the display unit 11 of the terminal device 2 according to the embodiment. Recommendation information 70 shown in FIG. 12 includes an inquiry information area 71, a non-opt-out information area 72, a Yes button 74, and a No button 75.

The inquiry information area 71 includes information inquiring whether or not to cancel the opt-out, and in the example shown in FIG. Contains the string "Do you want to return it?"

The non-opt-out information area 72 includes non-opt-out information that is information distributed from the distribution unit 41 to the opt-out user when the opt-out user does not select an opt-out as an opt-out target. Non-opt-out information is information distributed to the opt-out user from the distribution unit 41 before the opt-out user selects the opt-out that is the target of opt-out, or information that the opt-out user does not select the opt-out that is the target of opt-out. This is the information distributed from the distribution unit 41 when it is assumed that

When the user U selects the Yes button 74 by operating the operation unit 12 of the terminal device 2, an opt-out cancellation request is transmitted from the terminal device 2 to the information providing device 1. In this case, the display processing unit 17 of the terminal device 2 can change the information displayed on the display unit 11 from the recommendation information 70 shown in FIG. 12 back to the distribution information D shown in FIG. 4, for example.

Further, when the user U selects the No button 75 by operating the operation unit 12, the display processing unit 17 of the terminal device 2 changes the information to be displayed on the display unit 11 from the recommendation information 70 shown in FIG. Return to distribution information D shown in .

The non-opt-out information is, for example, distribution information D that is distributed using the model M that is the opt-out target. For example, in the non-opt-out information, if the opt-out target is target _T1 and the model M of target _T1 is model _M1 , the score output from model _M1 satisfies the preset distribution condition. This is distribution information D.

In addition, the non-opt-out information is information about the distribution target that is distributed to the opt-out user from the distribution unit 41 before the opt-out user selects the opt-out target for opting out, and is the information about the distribution target that is distributed to the opt-out user from the distribution unit 41 after the opt-out. The information may include information on a distribution target that is different from information on a distribution target distributed to out-users by a predetermined difference or more.

The information on the distribution target that is distributed from the distribution unit 41 to the opt-out user before the opt-out user selects the opt-out target is displayed on the screen displayed on the display unit 11 of the terminal device 2 by the recommendation unit 45, for example. information captured or similar to such information.

In addition, the non-opt-out information is difference presentation information that presents the difference in the information to be distributed from the distribution unit 41 to the opt-out user before and after the opt-out user selects the opt-out to be opted out. The information may include.

In this case, the recommendation unit 45 includes, for example, pre-opt-out information, which is information to be distributed from the distribution unit 41 to the opt-out user before the opt-out user selects opt-out, and from the distribution unit 41 after opting out. Compare with the post-opt-out information that is the information to be distributed to the opt-out user.

If there is pre-opt-out information among the pre-opt-out information that satisfies a predetermined condition, the recommendation unit 45 determines that the difference from the post-opt-out information is greater than or equal to a predetermined threshold. Information including pre-opt-out information is distributed to the opt-out user as recommendation information 70.

When the information to be distributed is information on target T, the difference between the pre-opt-out information and the post-opt-out information is expressed by a score SC obtained based on the type of target T or the difference in the number of each target T. . For example, the recommendation unit 45 may set the score SC to be the number of subjects T whose types are different between the pre-opt-out information and the post-opt-out information, or the number of subjects T whose types are different between the pre-opt-out information and the post-opt-out information. The sum of the differences in numbers can be used as the score SC.

In addition, the recommendation unit 45 sets the number of targets T whose types are different between the pre-opt-out information and the post-opt-out information as a score SC1, and calculates the number of each target T between the pre-opt-out information and the post-opt-out information. The sum of the differences can be set as the score SC2, and the sum of the score SC1 and the score SC2 can be set as the score SC.

Furthermore, if the information to be distributed is store information, the difference between the pre-opt-out information and the post-opt-out information is expressed by a score SC obtained based on the type of store information or the difference in the number of each store information. . For example, the recommendation unit 45 may set the score SC to be the number of different types of store information between pre-opt-out information and post-opt-out information, or set the score SC to the number of different types of store information between pre-opt-out information and post-opt-out information, or The sum of the differences in numbers can be used as the score SC.

In addition, the recommendation unit 45 sets the number of store information of different types between the pre-opt-out information and the post-opt-out information as a score SC1, and sets the number of store information with different types between the pre-opt-out information and the post-opt-out information. The sum of the differences can be set as the score SC2, and the sum of the score SC1 and the score SC2 can be set as the score SC.

FIG. 13 is a diagram showing another example of the recommendation information 70 displayed on the display unit 11 of the terminal device 2 according to the embodiment. The recommendation information 70 shown in FIG. 13 includes an inquiry information area 71, a non-opt-out information area 72, a current distribution information area 73, a Yes button 74, and a No button 75.

The non-opt-out information area 72 includes, for example, pre-opt-out information whose difference from the post-opt-out information is equal to or greater than a predetermined threshold, and the current distribution information area 73 includes, for example, pre-opt-out information. Includes post-opt-out information for which the difference between Thereby, the opt-out user can easily understand the merits of canceling the opt-out of the opt-out target.

The pre-opt-out information may be distribution target information that is distributed from the distribution unit 41 to the opt-out user when it is assumed that the opt-out user has not selected the opt-out target. In this case, the recommendation unit 45 selects the information distributed by the distribution unit 41 when the weight of the opt-out target from which the opt-out user has opted out is increased and the target model is not opted out. It can also be information.

Increasing the weight of the opt-out target means increasing the weight of the opt-out target model M when information on the opt-out target is distributed using the opt-out target model M. In addition, increasing the weight of the opt-out target means increasing the weight of the estimation model that estimates whether the opt-out user is interested in the opt-out store if the information to opt-out is store information. things to do, etc.

When the difference between the pre-opt-out information and the post-opt-out information exceeds a predetermined threshold, the recommendation unit 45 determines that it is time to recommend canceling the opt-out, and sends the recommended information 70 to the opt-out user. Can be notified.

In addition, the recommendation unit 45 recommends cancellation of opt-out when the frequency or number of times that the difference between the pre-opt-out information and the post-opt-out information exceeds a predetermined threshold is greater than or equal to a predetermined threshold. It is possible to determine that the timing has come and notify the opt-out user of the recommendation information 70.

When the number of distribution targets who have been opted out exceeds a preset number, the recommendation unit 45 determines that it is time to recommend canceling the opt-out, and notifies the opt-out user of the recommended information 70. can. The number of distribution targets who have been opted out is the number of model M and/or stores who have been opted out. In addition, the recommendation unit 45 sets the number of distribution targets for which the number of times the opt-out user was urged to cancel the opt-out is less than a preset number of distribution targets among the opted-out distribution targets as the number of distribution targets who have been opted out. can be handled.

Further, the recommendation unit 45 can also determine the recommendation timing for canceling opt-out based on the attributes of the opt-out user. The recommendation unit 45 calculates, for each attribute of the opt-out user, the timing at which the probability that the opt-out user makes an opt-out cancellation request becomes greater than or equal to a threshold value. Based on the opt-out user's attributes, the recommendation unit 45 determines the timing at which the probability that the opt-out user requests opt-out cancellation is equal to or greater than a threshold value as the recommendation timing for opt-out cancellation.

Further, the recommendation unit 45 can also determine the recommendation timing for canceling opt-out based on the type of opt-out target. For example, when the opt-out target is related to a hobby, the recommendation unit 45 can determine after 6:00 pm on weekdays or on holidays as the recommended timing for canceling the opt-out.

Further, the recommendation unit 45 may notify the recommended information 70 to the opt-out users when the rarity of the opt-out users among the users U to whom the opt-out target information is distributed satisfies a predetermined recommendation condition. can. For example, the recommendation unit 45, if among the users U to whom opt-out target information is distributed, the user U whose attribute rarity level is equal to or higher than a preset threshold is an opt-out user, Recommendation information 70 can be notified to opt-out users.

In addition, when there are multiple opt-out targets, the recommendation unit 45 recommends information that would be distributed from the distribution unit 41 to the opt-out user if the opt-out user did not select opt-out for these multiple opt-out targets. The information included may be non-opt-out information or pre-opt-out information, but is not limited to such examples.

For example, the recommendation unit 45 includes information that is distributed from the distribution unit 41 to the opt-out user when it is assumed that the opt-out target that has a high influence on the difference between the pre-opt-out information and the post-opt-out information is not selected. The information can be non-opt-out information or pre-opt-out information. Opt-out targets that have a high impact on the difference between pre-opt-out information and post-opt-out information are, for example, a preset number of opt-out targets in descending order of the impact on the difference between pre-opt-out information and post-opt-out information. It is an opt-out target or an opt-out target whose influence is above the threshold.

Further, for example, when the number of opt-out targets exceeds a preset number, the recommendation unit 45 selects an opt-out target for these opt-out targets, assuming that the opt-out user did not select opt-out. It is also possible to notify the opt-out user of information including information distributed from the distribution unit 41 to the user as recommendation information 70.

In addition to the non-opt-out information or the difference presentation information, the recommendation unit 45 also generates information including information indicating the frequency with which the difference between the pre-opt-out information and the post-opt-out information satisfies a predetermined recommendation condition. It is also possible to notify the opt-out user as recommendation information 70. The predetermined recommendation condition is, for example, a condition that the recommendation condition is greater than or equal to a predetermined threshold, but is not limited to this example.

In addition, if the information to be distributed is information to be notified to the opt-out user by e-mail, the recommendation information 70 may be "Instead of this e-mail, if you do not opt out at that time, you will receive an e-mail about a bicycle instead of a car." It may also include information such as "I was there!" In this case, "car" is an example of information to be distributed from the distribution unit 41 to the opt-out user after the opt-out user selects opt-out, and "bicycle" is an example of the information to be distributed to the opt-out user after the opt-out user selects opt-out. This is an example of distribution target information distributed from the distribution unit 41 to the opt-out user before selection.

In addition, the recommendation unit 45 extracts a user U who has similar attributes and the same opt-out target as the opt-out user as a similar user, and further notifies the opt-out user of the opt-out cancellation status of the opt-out target in the similar user. can do. Thereby, the notification unit 44 can prompt the opt-out users to choose to cancel their opt-out, for example, when most of the opt-out users have canceled their opt-out.

Note that the recommendation unit 45 can notify the recommendation information only to specific users U who are some of the users U who have opted out of the opt-out target. Thereby, the load on the recommendation section 45 can be reduced.

For example, assume that the information to be distributed provided by the distribution unit 41 is advertising content. In this case, the recommendation unit 45 notifies a user U whose click rate of advertising content has decreased to a threshold value or more after opting out for a specific opt-out target or two or more opt-out targets as a specific user U, and notifies the user U of recommendation information. In addition, the recommendation unit 45 selects a user U for whom the difference between the predicted CTR and the actual CTR is equal to or greater than a threshold after opting out for a specific opt-out target or two or more opt-out targets, or for a user U whose predicted CTR and actual CVR are Recommendation information can also be notified to a user U whose difference is equal to or greater than a threshold value as a specific user U.

The recommendation unit 45 also recommends a user U whose response rate to recommended information has decreased below a threshold value or a user whose response rate to recommended information has increased below a threshold value after opting out for a specific opt-out target or two or more opt-out targets. Recommendation information can also be notified using U as a specific user U.

In addition, the recommendation unit 45 notifies a randomly selected preset number or percentage of users U as specific users U from among the users U who have opted out of the opt-out target whose opt-out ratio is equal to or higher than the threshold value, and notifies them of recommendation information as specific users U. You can also.

[5. Processing procedure]
Next, a procedure of information processing by the processing unit 22 of the information providing device 1 according to the embodiment will be explained. FIG. 14 is a flowchart showing an example of the flow of information processing by the processing unit 22 of the information providing device 1 according to the embodiment.

As shown in FIG. 14, the processing unit 22 of the information providing device 1 distributes the information to be distributed to the user U (step S10). Next, the processing unit 22 performs opt-out related processing (step S11). The opt-out related process shown in step S11 is the process in steps S20 to S24 shown in FIG. 15, and will be described in detail later.

Next, the processing unit 22 performs opt-out cancellation recommendation processing (step S12). The opt-out cancellation recommendation process shown in step S12 is the process of steps S30 to S34 shown in FIG. 16, and will be described in detail later.

When the processing in step S12 is completed, the processing unit 22 determines whether or not the timing to end the operation has come (step S13). For example, when the information providing apparatus 1 is powered off or when it is determined that an end operation has been performed by operating the operation section 12, the processing section 22 determines that the operation end timing has come.

If the processing unit 22 determines that the operation end timing has not yet come (step S13: No), the process proceeds to step S10, and if it determines that the operation end timing has come (step S13: Yes), the process proceeds to FIG. The indicated process ends.

FIG. 15 is a flowchart illustrating an example of the flow of opt-out related processing by the processing unit 22 of the information providing device 1 according to the embodiment. As shown in FIG. 15, the processing unit 22 determines whether there is an opt-out request from the user U (step S20).

When the processing unit 22 determines that there is an opt-out request (step S20: Yes), the processing unit 22 sets the model M corresponding to the opt-out request as the target model, and sets the first information distributed when the target model is not opted out. Difference information 60 indicating the difference between the group and the second information group distributed when the target model is opted out is generated (step S21).

Next, the processing unit 22 distributes the difference information 60 generated in step S21 to the opt-out user who is the user U who is the sender of the opt-out request (step S22). The processing unit 22 determines whether there is an opt-out selection for the target model by the opt-out user who distributed the difference information 60 (step S23).

When the processing unit 22 determines that the opt-out user has selected opt-out for the target model (step S23: Yes), the processing unit 22 performs opt-out processing (step S24). The opt-out process in step S24 is performed, for example, by canceling the association of the opt-out user with the target model.

When the process of step S24 is completed, when the processing unit 22 determines that there is no opt-out selection for the target model by the opt-out user (step S23: No), or when it determines that there is no opt-out request (step S20: No), the process shown in FIG. 15 ends.

FIG. 16 is a flowchart illustrating an example of the flow of opt-out cancellation recommendation processing by the processing unit 22 of the information providing device 1 according to the embodiment. As shown in FIG. 16, the processing unit 22 determines whether the recommendation timing for canceling opt-out has arrived (step S30). In the process of step S30, the processing unit 22 determines that the recommendation timing for canceling the opt-out has arrived, for example, when the difference between the pre-opt-out information and the post-opt-out information is equal to or greater than a predetermined threshold.

When the processing unit 22 determines that it is time to recommend canceling opt-out (step S30: Yes), the processing unit 22 generates recommendation information 70 that recommends canceling opt-out for the opt-out target to the opt-out user (step S31). ). The recommended information 70 is information that includes information that is distributed from the distribution unit 41 to the user U when it is assumed that the opt-out user does not select the opt-out option.

Next, the processing unit 22 distributes the recommendation information 70 generated in step S31 to the opt-out user (step S32). After that, the processing unit 22 determines whether there is an opt-out cancellation request by the opt-out user (step S33).

If the processing unit 22 determines that there is an opt-out cancellation request (step S33: Yes), it performs opt-out cancellation processing (step S34). As opt-out cancellation processing in step S34, the processing unit 22 associates the opt-out user with the model M for which cancellation of opt-out has been selected, or selects the opt-out user from the distribution excluded user list of the store for which cancellation of opt-out has been selected. This can be done by deleting the user ID of the user.

When the processing unit 22 completes the process of step S34, when it determines that there is no opt-out cancellation request (step S33: No), or when it determines that the recommendation timing for opt-out cancellation has not come (step S30: No), the process shown in FIG. 16 is executed.

[6. Modified example]
The notification unit 44 can also distribute the difference information 60 if preset distribution conditions are met, and not distribute the difference information 60 if not. For example, the notification unit 44 determines that the preset distribution condition is satisfied when the frequency of displaying detailed information for the distribution information D selected by the target model is equal to or higher than a preset frequency. , otherwise, it can be determined that the preset distribution conditions are not satisfied.

Furthermore, the notification unit 44 determines that the preset distribution condition is satisfied when the frequency with which the distribution information D selected by the target model is distributed to the opt-out requesting user is equal to or higher than a preset threshold; Otherwise, it can be determined that the preset distribution conditions are not met. The frequency described above is the ratio of the number of times the distribution information D selected by the target model is distributed to the opt-out requesting users to the total number of distribution information distributed to the opt-out requesting users.

Further, the recommendation unit 45 may include the benefit of canceling the opt-out of the opt-out target, including the provision of benefits. The granting of benefits is, for example, the granting of points, the granting of qualifications to participate in a prize lottery, or the weighting of the model M that selects the distribution information D for which the frequency of displaying detailed information is equal to or higher than a preset frequency. For example, increasing the

The recommendation unit 45 may also distribute the recommendation information 70 to the users U who have opted out of the opt-out target when the number or percentage of the users U who have opted out of the opt-out target is equal to or higher than a preset threshold. can.

[7. Hardware configuration]
The information providing device 1 or the terminal device 2 according to the embodiments described above is realized by, for example, a computer 80 having a configuration as shown in FIG. 17. The information providing device 1 will be described below as an example. FIG. 17 is a hardware configuration diagram showing an example of a computer 80 that implements the functions of the information providing device 1 according to the embodiment. The computer 80 includes a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I/F) 85, an input/output interface (I/F) 86, and a media interface (I/F). )87.

The CPU 81 operates based on a program stored in the ROM 83 or HDD 84 and controls each part. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started, programs depending on the hardware of the computer 80, and the like.

The HDD 84 stores programs executed by the CPU 81 and data used by the programs. The communication interface 85 receives data from other devices via the communication network 3 (see FIG. 2) and sends it to the CPU 81, and sends data generated by the CPU 81 to the other devices via the communication network 3.

The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse via an input/output interface 86. The CPU 81 obtains data from an input device via the input/output interface 86. Further, the CPU 81 outputs the generated data to an output device via the input/output interface 86.

Media interface 87 reads programs or data stored in recording medium 88 and provides them to CPU 81 via RAM 82. The CPU 81 loads this program from the recording medium 88 onto the RAM 82 via the media interface 87, and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 80 functions as the information providing device 1 according to the embodiment, the CPU 81 of the computer 80 realizes the functions of the processing unit 22 by executing a program loaded onto the RAM 82. Furthermore, the data in the storage unit 21 is stored in the HDD 84 . The CPU 81 of the computer 80 reads these programs from the recording medium 88 and executes them, but as another example, these programs may be acquired from another device via the communication network 3.

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

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured. For example, two or more of the acquisition unit 40, distribution unit 41, reception unit 42, identification unit 43, notification unit 44, and recommendation unit 45 shown in FIG. 6 may be integrated. Further, for example, the information stored in the storage unit 21 may be stored in a predetermined external storage device via the communication network 3.

Further, the information providing device 1 may be configured with two or more server devices, and in this case, the information providing device 1 has a configuration including, for example, a processing server and a storage server. Furthermore, the embodiments and modifications described above can be combined as appropriate within a range that does not conflict with the processing contents.

[9. effect〕
As described above, the information providing device 1 according to the embodiment includes the distribution section 41, the identification section 43, and the notification section 44. The distribution unit 41 distributes the information to be distributed using a plurality of models M that determine the destination of the information to be distributed. The identifying unit 43 identifies the model M for which the user U has made an opt-out request among the plurality of models M as the target model. The notification unit 44 includes a first information group 62 that is distributed from the distribution unit 41 when the target model is not opted out, and a second information group 63 that is distributed from the distribution unit 41 when the target model is opted out. The user U who made the opt-out request is notified of the difference information 60 indicating the difference between the two. Thereby, the information providing device 1 can inform the user U of the disadvantages of opting out of the model M, and can provide appropriate information to the user U.

Furthermore, the notification unit 44 notifies the user U who has made the opt-out request of information including the first information group 62 and the second information group 63 as the difference information 60. Thereby, the difference information 60 provided by the information providing device 1 allows the user U who has made an opt-out request to easily understand the difference between the information groups distributed from the distribution unit 41 before and after opting out.

Furthermore, the notification unit 44 notifies the user U who has made the opt-out request as the difference information 60 of information in which the first information group 62 and the second information group 63 are presented alternately. Thereby, the difference information 60 provided by the information providing device 1 allows the user U who has made an opt-out request to more easily understand the difference between the information groups distributed from the distribution unit 41 before and after opting out.

Further, the notification unit 44 notifies the user U who made the opt-out request as the difference information 60 of information that presents the first information group 62 and the second information group 63 at the same time. Thereby, the difference information 60 provided by the information providing device 1 allows the user U who has made an opt-out request to more easily understand the difference between the information groups distributed from the distribution unit 41 before and after opting out.

Furthermore, the notification unit 44 sends a first information group 62 a group of information to be distributed from the distribution unit 41 when the target model is not opted out with the weight of the target model for the user U who has made the opt-out request increased. The user U who made the opt-out request is notified of the information included as the difference information 60. Thereby, the difference information 60 provided by the information providing device 1 allows the user U who made the opt-out request to appropriately understand the information distributed using the target model for which the user has opted out.

Furthermore, the notification unit 44 changes the weight of the target model for the user U who has made the opt-out request, based on the attributes of the user U who has made the opt-out request. Thereby, the information providing apparatus 1 can make the user U who made the opt-out request appropriately understand the information distributed using the target model with a weight according to the user U.

Furthermore, the notification unit 44 clearly indicates information that is included in the first information group 62 and not included in the second information group 63 and information that is included in the second information group 63 and not included in the first information group 62. The user U who made the opt-out request is notified of the information as difference information 60. Thereby, the information providing device 1 can make the user U who has made the opt-out request more easily understand the difference between the information groups distributed from the distribution unit 41 before and after opting out.

In addition, the notification unit 44 extracts a user U whose attributes are similar to the user U who made the opt-out request as a similar user, and informs the user U who made the opt-out request of the opt-out status of the similar user for the target model. Further notice. Thereby, the information providing device 1 can notify the opt-out user of the opt-out status of other users U, and the opt-out user can inform the opt-out status of the other user U so that the opt-out user can select opt-out. It can be considered as an indicator of

Further, the information to be distributed distributed by the distribution unit 41 is information displayed on the user U's terminal device 2 on a timeline. Thereby, the information providing device 1 can inform the user U of the disadvantages of opting out of the model M that determines the distribution destination of the information to be distributed displayed on the timeline.

Although the embodiments of the present application have been described above in detail based on the drawings, this is merely an example, and various modifications and improvements can be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to implement the invention in other forms.

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

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various changes or improvements can be made to the embodiments described above. Furthermore, it is clear from the claims that forms with such changes or improvements may also be included within the technical scope of the present invention.

1 Information providing device 2, _{2 1} , 2 ₂ ,..., 2 _m terminal device 3 Communication network 10, 20 Communication section 11 Display section 12 Operation section 13 Sensor group 14, 21 Storage section 15, 22 Processing section 16 Information acquisition Units 17 Display processing unit 18 Output unit 30 User information storage unit 31 Model information storage unit 32 Distribution information storage unit 33 Opt-out user information storage unit 34 Store information storage unit 40 Acquisition unit 41 Distribution unit 42 Reception unit 43 Specification unit 44 Notification unit 45 Recommendation section 60 Difference information 62 First information group 63 Second information group 70 Recommendation information

Claims (11)

a distribution unit that distributes the information to be distributed using a plurality of models that determine a destination of the information to be distributed;
an identification unit that identifies a model for which a user has made an opt-out request among the plurality of models as a target model;
Indicates a difference between a first information group distributed from the distribution unit when the target model is not opted out and a second information group distributed from the distribution unit when the target model is opted out. An information providing device comprising: a notification unit that notifies the user who has made the opt-out request of the difference information. The notification section is
The information providing device according to claim 1, wherein information including the first information group and the second information group is notified to the user who made the opt-out request as the difference information. The notification section is
3. The information providing apparatus according to claim 2, wherein information in which the first information group and the second information group are presented alternately is notified to the user who made the opt-out request as the difference information. The notification section is
3. The information providing apparatus according to claim 2, wherein information that presents the first information group and the second information group simultaneously is notified to the user who made the opt-out request as the difference information. The notification section is
the information including, as the first information group, a group of information distributed by the distribution unit when the target model is not opted out with a larger weight of the target model for the user who has made the opt-out request; 5. The information providing device according to claim 1, wherein the information providing device is configured to notify the user who made the opt-out request as difference information. The notification section is
The information providing apparatus according to claim 5, wherein the weight of the target model for the user who has made the opt-out request is changed based on an attribute of the user who has made the opt-out request. The notification section is
The difference information includes information that clearly indicates information included in the first information group and not included in the second information group and information included in the second information group but not included in the first information group. The information providing device according to any one of claims 1 to 6, wherein the information providing device notifies a user who has made an opt-out request. The notification section is
A user who has similar attributes to the user who made the opt-out request is extracted as a similar user, and the user who made the opt-out request is further notified of the opt-out status of the similar user for the target model. The information providing device according to any one of claims 1 to 7. The information providing device according to any one of claims 1 to 8, wherein the information to be distributed distributed by the distribution unit is information displayed on a timeline on the user's terminal device. An information provision method executed by a computer, the method comprising:
a distribution step of distributing the information to be distributed using a plurality of models that determine the distribution destination of the information to be distributed;
an identification step of identifying a model for which a user has made an opt-out request among the plurality of models as a target model;
Indicates a difference between a first information group distributed in the distribution process when the target model is not opted out and a second information group distributed in the distribution process when the target model is opted out. An information provision method comprising: a notification step of notifying the user who made the opt-out request of the difference information. a distribution procedure for distributing the information to be distributed using a plurality of models that determine the destination of the information to be distributed;
an identification step of identifying a model for which a user has made an opt-out request among the plurality of models as a target model;
Indicates a difference between a first information group distributed in the distribution procedure when the target model is not opted out and a second information group distributed in the distribution procedure when the target model is opted out. An information providing program that causes a computer to execute a notification procedure for notifying the user who has made the opt-out request of the difference information.

Images