JP7794785B2 - Information processing device, distribution method, and distribution program - Google Patents

Description

The present invention relates to an information processing device, a distribution method, and a distribution program.

Information is provided to people visiting various regions for purposes such as guiding them to tourist spots and promoting products. For example, one conventional technology for providing information to people visiting a certain region involves running machine learning on a machine learning model based on training data that predefines the relationship between the person's context (such as riding a train or running a marathon) and the information to be provided to the person, and then using this machine learning model to identify and distribute the information to be provided to the person.

Japanese Patent Application Laid-Open No. 2020-154864

However, with the above-mentioned conventional technology, there is a time lag between the person's situation used during machine learning and the person's situation at the time the information is provided, so there is room for improvement in terms of improving the accuracy of information provided.

This application has been made in light of the above, and aims to provide an information processing device, a learning method, and a learning program that can improve the accuracy of information provision.

The information processing device according to the present application has an acquisition unit, an identification unit, a determination unit, and a distribution unit. The acquisition unit acquires multiple vectors corresponding to multiple users, each generated using a machine learning model trained to generate similar vectors from sensor information of similar situations. The identification unit identifies a group of users with similar vectors based on the multiple vectors. The determination unit determines the content of information to be provided to the user group based on information about logged-in users included in the user group identified by the identification unit. The distribution unit distributes the determined information content to devices owned by each member of the user group.

According to one aspect of the embodiment, it is possible to improve the accuracy of information provision.

FIG. 1 is a diagram showing the configuration of an information processing system according to this embodiment. FIG. 2 is a diagram for explaining the processing of the information processing device according to this embodiment. FIG. 3 is a diagram illustrating an example of the data structure of the determination table. FIG. 4 is a diagram showing the configuration of a user terminal according to this embodiment. FIG. 5 is a diagram showing the configuration of an information processing apparatus according to this embodiment. FIG. 6 is a diagram illustrating an example of the data structure of the user management table. FIG. 7 is a diagram illustrating an example of the data structure of the vector table. FIG. 8 is a flowchart showing the processing procedure of the information processing device according to this embodiment. FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing apparatus according to the embodiment.

Below, detailed explanations are given of the information processing device, distribution method, and distribution program (hereinafter referred to as "embodiments") according to the present application, with reference to the drawings. Note that the information processing device, distribution method, and distribution program according to the present application are not limited to these embodiments. Furthermore, the embodiments can be combined as appropriate to the extent that the processing content is not contradictory. Furthermore, the same components in the following embodiments are designated by the same reference numerals, and redundant explanations will be omitted.

1. Configuration of Information Processing System 1
First, an example of the configuration of an information processing system 1 according to this embodiment will be described using Fig. 1. Fig. 1 is a diagram showing the configuration of the information processing system 1 according to this embodiment. For example, the information processing system 1 has user terminals 10a, 10b, 10c, and 10d, and an information processing device 100. The user terminals 10a to 10d and the information processing device 100 are connected to each other via a network 2.

User terminals 10a to 10d are terminal devices used by users. User terminals 10a to 10d correspond to tablet terminals, smartphones, notebook PCs (Personal Computers), etc. For example, users 3a, 3b, 3c, and 3d use user terminals 10a, 10b, 10c, and 10e, respectively.

User terminals 10a-10d may be connected to network 2 via base stations or the like. While user terminals 10a-10d are shown in Figure 1, other user terminals may also be included. In the following description, when there is no need to distinguish between user terminals 10a-10d, user terminals 10a-10d will be collectively referred to as "user terminal 10." Users 3a-3d will be collectively referred to as "user 3."

User 3 operates user terminal 10 to log in to a website provided by information processing device 100 and receive various services. User terminal 10 also has various sensors, which are used to generate sensor data in real time. Sensor data is data that associates time with various sensor values. For example, the various sensor values include illuminance, sound, position, air pressure, speed, images, etc.

The user terminal 10 has a machine learning model that has been distributed in advance. This machine learning model is a model (such as a neural network) that has been trained in advance with sensor data as input and vector data as output (correct label). The machine learning model is also trained so that when it receives inputs of multiple pieces of sensor data generated under similar circumstances, it outputs multiple pieces of vector data that are similar to each other. For example, if the cosine similarity between a vector and another vector is equal to or greater than a threshold, the vector and the other vector are similar to each other.

For example, if user 3a and user 3b are in the same area (a busy shopping district) and are engaged in similar behavior (for example, standing still and operating user terminal 10), the vector data generated based on the sensor data of user terminal 10a and the vector data generated based on the sensor data of user terminal 10b will be similar vectors.

Furthermore, if user 3c and user 3d are in the same area (an airport) and are engaged in similar activities (for example, pulling a cart), the vector data generated based on the sensor data of user terminal 10c and the vector data generated based on the sensor data of user terminal 10d will be similar vectors.

The user terminal 10 generates vector data in real time by inputting sensor data acquired in real time into a machine learning model. The user terminal 10 transmits the vector data generated in real time to the information processing device 100, regardless of whether the user 3 is logged in. Information identifying the user terminal 10 is attached to the vector data. In the following description, information that uniquely identifies the user terminal 10 is referred to as "terminal identification data." The terminal identification data is the IP address, device ID, cookie, etc. of the user terminal 10.

In addition to the vector data, the user terminal 10 transmits sensor data to the information processing device 100 while logged in to a website provided by the information processing device 100 through the operation of the user 3. The sensor data is accompanied by terminal identification data.

The information processing device 100 is a server device that provides websites and the like and offers various services to user terminals 10 that have logged in. The information processing device 100 also acquires vector data in real time from all user terminals 10 that are located in a pre-specified area, regardless of whether they have logged in. Based on the acquired vector data, the information processing device 100 determines the content of the information to be provided to the user 3, and distributes the determined information content to the user terminal 10. An example of the processing of the information processing device 100 is described below.

Figure 2 is a diagram for explaining the processing of the information processing device 100 according to this embodiment. As an example, in Figure 2, the vector data acquired by the information processing device 100 from the user terminals 10 included in the specified area are vector data v1a, v1b, v1c, v1d, v1e, v1f, v1g, v2a, v2b, v2c, v2d, v2e, v2f, v2g, v2h, v2a, v2b, v2c, v2d, v2e, and v2f.

In the following description, when we refer to "user corresponding to vector data," we mean user 3 who uses the user terminal 10 that is the sender of the vector data. For example, if the user terminal 10 that is the sender of vector data v1a is user terminal 10a shown in Figure 1, then user 3 of vector data v1a is user 3a.

The information processing device 100 classifies similar vector data into the same group by performing clustering or the like on multiple vector data. In the example shown in FIG. 2, the information processing device 100 classifies vector data v1a to v1g into group G1. The information processing device 100 classifies vector data v2a to v2h into group G2. The information processing device 100 classifies vector data v3a to v3f into group G3.

For example, of the multiple users corresponding to vector data v1a-v1g included in group G1, the users corresponding to vector data v1a-v1c are considered to be logged-in users (hereinafter referred to as logged-in users, as appropriate). Of the multiple users corresponding to vector data v2a-v2h included in group G2, the users corresponding to vector data v2b, v2e, and v2g are considered to be logged-in users. Of the multiple users corresponding to vector data v3a-v3f included in group G3, the user corresponding to vector data v3a is considered to be the logged-in user.

The information processing device 100 determines the content of information to be distributed to the user terminals 10 of multiple users corresponding to the vector data v1a-v1g included in group G1 based on the attribute data of the logged-in user corresponding to the vector data v1a-v1c. In the following description, the user terminals 10 of multiple users corresponding to the vector data v1a-v1g included in group G1 will be referred to as "user terminals 10 of group G1."

The information processing device 100 determines the content of information to be distributed to the user terminals 10 of multiple users corresponding to vector data v2a to v2h included in group G2 based on the attribute data of the logged-in users corresponding to vector data v2b, v2e, and v2g. In the following description, the user terminals 10 of multiple users corresponding to vector data v2a to v2h included in group G2 will be referred to as "user terminals 10 of group G2."

The information processing device 100 determines the content of the information to be distributed to the user terminals 10 of multiple users corresponding to the vector data v3a-v3f included in group G3 based on the attribute data of the logged-in user corresponding to the vector data v3a. In the following description, the user terminals 10 of multiple users corresponding to the vector data v3a-v3f included in group G3 will be referred to as "user terminals 10 of group G3."

For example, when determining the content of information to be distributed, the information processing device 100 may use the decision table described below. Figure 3 is a diagram showing an example of the data structure of a decision table. As shown in Figure 3, the decision table 141 associates item numbers, occupations, annual income, time periods, temperatures, speeds, locations, and distribution data.

The item number is a number that identifies each record in the decision table 141. The occupation and annual income are the occupation and annual income of the logged-in user, and are set in the attribute data of the logged-in user. The time period is the current time period obtained from a timer or the like. The temperature, speed, and location are information (sensor data) obtained from the logged-in user's user terminal 10, and correspond to the temperature, speed, and location information measured by the logged-in user's user terminal 10. The distribution data indicates the data to be distributed to all user terminals 10 belonging to the corresponding group.

When multiple logged-in users are included in the same group, the information processing device 100 may identify and use attribute data common to the multiple logged-in users. When multiple logged-in users are included in the same group, the information processing device 100 may identify attribute data by majority vote, etc. When multiple logged-in users are included in the same group, the information processing device 100 may use the average value, median value, etc. of sensor data acquired from the user terminals 10 of each logged-in user.

For example, suppose the attribute data of a logged-in user in group G1 is set to "Occupation: Company Employee," and the current time period obtained from the timer is between 9:00 AM and 5:00 PM. Furthermore, suppose the sensor data of the user terminal 10 used by the logged-in user in group G1 indicates that the temperature is "less than C1 degrees," the speed is "between V1 and V2," and the location is "downtown A." In this case, the information processing device 100 determines that the content of the information to be distributed to the user terminals 10 in group G1 is "gym advertising data," and distributes the "gym advertising data" to all user terminals 10 in group G1.

For example, suppose the attribute data of the logged-in users in group G2 includes an "annual income" of "above threshold," and the time period obtained from the timer is between "9:00 AM and 5:00 PM." Furthermore, the sensor data of the user terminals 10 used by the logged-in users in group G2 indicates that the temperature is "between C2 and C3 degrees," the speed is "below V1 (stopped)," and the location is "downtown A." In this case, the information processing device 100 determines that the content of the information to be distributed to the user terminals 10 in group G2 is "beauty advertising data," and distributes the "beauty advertising data" to all user terminals 10 in group G2.

For example, suppose the attribute data of the logged-in users in group G3 includes an "annual income" of "above threshold" and the time period obtained from the timer is "9:00 AM to 5:00 PM." Furthermore, the sensor data of the user terminals 10 used by the logged-in users in group G3 indicates that the temperature is "between C2 and C3 degrees," the speed is "between V1 and V2," and the location is "downtown A." In this case, the information processing device 100 determines that the content of the information to be distributed to the user terminals 10 in group G3 is "cruising cruiser advertising data," and distributes the "cruising cruiser advertising data" to all user terminals 10 in group G3.

As described above, the information processing device 200 classifies vector data acquired in real time from the user terminal 10 into groups based on similar vector data, regardless of whether the user is logged in. Then, the information processing device 200 determines the distribution data to be provided to users in the same group based on the attribute data of the logged-in user among multiple users included in the same group, and distributes the determined distribution data. This improves the accuracy of information provision.

2. Configuration of User Terminal 10
Next, an example of the configuration of the user terminal 10 (for example, user terminals 10a to 10d) shown in Fig. 1 will be described. Fig. 4 is a diagram showing the configuration of the user terminal 10 according to this embodiment. As shown in Fig. 4, the user terminal 10 has a communication unit 11, an input unit 12, a display unit 13, a sensor group 14, a storage unit 15, and a control unit 16.

The communication unit 11 is realized by a NIC (Network Interface Card) or the like. The communication unit 11 is wirelessly connected to the network 2 via a base station or the like, and transmits and receives information to and from various other devices. For example, the control unit 16 (described below) uses the communication unit 11 to transmit and receive information to and from the information processing device 100.

The input unit 12 is a device for inputting various types of information to the control unit 16 of the user terminal 10. The input unit 12 is an input device such as a keyboard, mouse, or touch panel. The user 3 operates the input unit 12 to access the information processing device 100 and perform login operations, etc.

The display unit 13 is a device for displaying information output from the control unit 16. The display unit 13 is a display device such as a display or touch panel. For example, the display unit 13 displays the screen of a website provided by the information processing device 100, a login screen, and advertising data determined by the information processing device 100 through the above processing.

The sensor group 14 is a plurality of sensors for measuring the above-mentioned sensor data. The sensor group 14 repeatedly executes a process of storing the measured sensor data in the memory unit 15 as sensor data 15a. For example, the sensor group 14 includes an illuminance sensor, an acoustic sensor, a GPS (Global Positioning System), a barometric pressure sensor, a temperature sensor, an acceleration sensor, a gyro sensor, an image sensor, etc.

The memory unit 15 is realized by a semiconductor memory element such as a flash memory, or a storage device such as a hard disk. For example, the memory unit 15 has sensor data 15a and a machine learning model 15b.

Sensor data 15a is data measured by the sensor group 14. For example, sensor data 15a is data that associates time with various sensor values. The various sensor values include illuminance, sound, position, air pressure, speed, images, etc.

Machine learning model 15b is a machine learning model that has been distributed in advance. When sensor data is input, machine learning model 15b outputs vector data. Other explanations regarding machine learning model 15b are the same as those regarding the machine learning model described above.

The control unit 16 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs stored in a storage device (e.g., the storage unit 15) within the user terminal 10 using RAM as a working area. The control unit 16 is also a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

The control unit 16 has an access unit 16a, a generation unit 16b, a transmission unit 16c, and a display processing unit 16d, and realizes or executes the functions and actions of the processes described below. Note that the internal configuration of the control unit 16 is not limited to the configuration shown in Figure 4, and may be any other configuration that performs the processes described below.

When the access unit 16a receives an access request to the information processing device 100 from the user 3 operating the input unit 12, it accesses the information processing device 100 and accepts various services from the information processing device 100. Furthermore, when the access unit 16a receives a login operation to the information processing device 100 from the user 3 operating the input unit 12, it transmits login data to the information processing device 100. For example, the login data includes a user ID, password, terminal identification data, etc. that identify the user 3.

On the other hand, when the access unit 16a receives a logoff operation for the information processing device 100 from the user 3 operating the input unit 12, the access unit 16a transmits logoff data to the information processing device 100. For example, the logoff data includes a user ID that identifies the user 3, a logoff request, terminal identification data, etc.

The user terminal 10 is in a state of being logged in to the information processing device 100 during the period from when the access unit 16a transmits login data to the information processing device 100 until when it transmits logoff data to the information processing device 100.

The generation unit 16b generates vector data by inputting the sensor data 15a into the machine learning model 15b. The generation unit 16b outputs the generated vector data to the transmission unit 16c. For example, the generation unit 16b repeatedly executes the above process at predetermined time intervals.

The transmitting unit 16c assigns terminal identification data to the vector data generated by the generating unit 16b, and transmits the vector data with the assigned terminal identification data to the information processing device 100. Although this will not be explained further below, it is assumed that the vector data has been assigned terminal identification data. The transmitting unit 16c transmits the vector data to the information processing device 100 regardless of whether or not the user has logged in to the information processing device 100.

Furthermore, the transmitter 16c transmits the sensor data 15a to the information processing device 100 in addition to the vector data via the access unit 16a while the user terminal 10 is logged in to the information processing device 100. In other words, the transmitter 16c transmits the sensor data 15a to the information processing device 100 together with the vector data while the user terminal 10 is logged in to the information processing device 100.

The display processing unit 16d outputs various information transmitted from the information processing device 100 to the display unit 13 for display. For example, the display processing unit 16d receives website screens, login screens, advertising data, etc. transmitted from the information processing device 100 and displays them on the display unit 13.

3. Configuration of information processing device 100
Next, an example of the configuration of the information processing device 100 shown in Fig. 1 will be described. Fig. 5 is a diagram showing the configuration of the information processing device 100 according to this embodiment. As shown in Fig. 5, the information processing device 100 includes a timer 105, a communication unit 110, an input unit 120, a display unit 130, a storage unit 140, and a control unit 150.

The timer 105 is a device that outputs the current time to the control unit 150.

The communication unit 210 is realized by a NIC or the like. The communication unit 110 is connected to the network via a wired or wireless connection, and transmits and receives information to and from various other devices. For example, the control unit 150, described below, uses the communication unit 110 to transmit and receive information to and from the user terminal 10.

The input unit 120 is a device for inputting various types of information to the control unit 150 of the information processing device 100. The input unit 120 is an input device such as a keyboard, mouse, or touch panel.

The display unit 130 is a device for displaying information output from the control unit 150. The display unit 130 is a display device such as a display or touch panel.

The memory unit 140 is implemented by a semiconductor memory element (non-volatile memory) such as a flash memory, or a storage device such as a hard disk. For example, the memory unit 140 has a decision table 141, a user management table 142, and a vector table 143.

Decision table 141 is used when determining the information to be delivered to the user terminal 10. The explanation of decision table 141 is the same as that given in Figure 3.

The user management table 142 is a table that holds various information related to users. Figure 6 shows an example of the data structure of the user management table 142. As shown in Figure 6, the user management table 142 associates a user ID, login flag, terminal identification data, name, and attribute data.

The user ID is information that uniquely identifies a user. The login flag is a flag that indicates whether the user in question is logged in or not. If the user is logged in, the login flag is "on", and if the user is logged off, the login flag is "off". The terminal identification data is information that identifies the user terminal 10 used when the user performed the login operation, and includes the IP address, device ID, cookies, etc. of the user terminal 10. The name is the user's name. The attribute data includes information such as occupation, annual income, and hobbies. In the example shown in Figure 6, occupation, annual income, and hobbies are shown as attribute data, but the attribute data may also include other attributes.

Each piece of data in the user management table 142 is registered in advance by the user. The user may operate the user terminal 10 to access the information processing device 100 and update their own data (terminal identification data, name, attribute data) as appropriate.

The vector table 143 is a table that holds vector data acquired in real time from all user terminals 10 included in a pre-specified area. Figure 7 is a diagram showing an example of the data structure of the vector table 143. In the example shown in Figure 7, the vector table 143 associates terminal identification data, vector data, and sensor data.

As described above, the information processing device 100 acquires vector data from all user terminals 10 within the specified area and registers it in the vector table 143. Note that since vector data and sensor data are sent from the user terminal 10 of the logged-in user, the information processing device registers the vector data and sensor data in the vector table 143. Note that the information processing device 100 may also register sensor data in a table separate from the vector table 143.

The control unit 150 is a controller, and is realized, for example, by a processor such as a CPU or MPU, which executes various programs stored in a storage device (for example, the storage unit 140) within the information processing device 100 using RAM as a working area. The control unit 150 is also a controller, and is realized, for example, by an integrated circuit such as an ASIC or FPGA.

The control unit 150 has a service providing unit 151, an acquiring unit 152, an identifying unit 153, a determining unit 154, and a distributing unit 155, and realizes or executes the functions and actions of the processes described below. Note that the internal configuration of the control unit 150 is not limited to the configuration shown in FIG. 5, and may be any other configuration that performs the processes described below.

The service providing unit 151 accepts access from the user terminal 10, displays websites and the like, and provides various services. When the service providing unit 151 accepts access from the user terminal 10, it displays a login screen and receives login data from the user terminal 10. Based on the login data and the user management table 142, the service providing unit 151 sets the login flag corresponding to the logged-in user to "on." On the other hand, when the service providing unit 151 receives log-off data from the user terminal 10, it sets the corresponding login flag to "off."

The acquisition unit 152 acquires vector data from all user terminals 10 within the specified area and registers it in the vector table 143. Since vector data and sensor data are sent from the user terminal 10 of the logged-in user, the acquisition unit 152 registers the vector data and sensor data in the vector table 143. The acquisition unit 152 updates the vector table 143 each time it acquires vector data and sensor data.

The identification unit 153 performs clustering on all vector data registered in the vector table 143, thereby classifying similar vector data into the same group. For example, the identification unit 153 may use the K-Means method or the like when performing clustering. The clustering performed by the identification unit 153 corresponds to the clustering described in FIG. 2. The identification unit 153 outputs the clustering results to the determination unit 154.

For each group, the clustering results include device identification data corresponding to the vectors included in the group. For example, in the example shown in Figure 2, device identification data corresponding to vector data v1a to v1g is set in association with group G1. Device identification data corresponding to vector data v2a to v2h is set in association with group G2. Device identification data corresponding to vector data v3a to v3f is set in association with group G3.

The determination unit 154 determines the distribution data to be provided to user terminals 10 (users 3) classified in the same group based on the attribute data of the logged-in users of user terminals 10 classified in the same group. An example of the processing of the determination unit 154 is described below.

The determination unit 154 obtains multiple pieces of terminal identification data classified into a certain group (here, group G1) from the clustering results, and compares the obtained terminal identification data with the user management table 142 to identify the terminal identification data of logged-in users in group G1.

The determination unit 154 obtains attribute data corresponding to the terminal identification data of the logged-in users of group G1 from the user management table 142. The determination unit 154 obtains sensor data corresponding to the terminal identification data of the logged-in users of group G1 from the vector table 143. The determination unit 154 also obtains the current time from the timer 105.

The determination unit 154 determines the distribution data based on the acquired current time, attribute data corresponding to the logged-in user of group G1, vector data, and determination table 141. For example, if the attribute data corresponding to the logged-in user of group G1 includes "office worker," the current time is within the time period "9:00 AM - 5:00 PM," and the temperature, speed, and location (position) (sensor data) are below C1 degrees, between V1 and V2, and downtown A, respectively, the determination unit 154 determines the distribution data to be "gym advertising data."

The determination unit 154 outputs to the distribution unit 155 information on the determination result that associates the terminal identification data included in group G1 with the determined distribution data "gym advertising data."

The determination unit 154 repeats the above process for other groups (groups G2 and G3).

When multiple logged-in users are included in the same group, the determination unit 154 may identify and use attribute data common to the multiple logged-in users. When multiple logged-in users are included in the same group, the determination unit 154 may identify attribute data by majority vote, etc. When multiple logged-in users are included in the same group, the determination unit 154 may use the average value, median, etc. of sensor data acquired from the user terminals 10 of each logged-in user.

The distribution unit 155 obtains the determination result from the determination unit 154 and distributes the determined distribution data for each group.

4. Processing Procedure of Information Processing Device 100
Next, an example of a processing procedure of the information processing device 100 according to this embodiment will be described. Fig. 8 is a flowchart showing the processing procedure of the information processing device 100 according to this embodiment. As shown in Fig. 8, the service providing unit 151 of the information processing device 100 updates the login flag in the user management table 142 every time login data or logoff data is received from the user terminal 10 (step S101).

The acquisition unit 152 of the information processing device 100 acquires vector data from all user terminals 10 included in the specified area and registers it in the vector table 143 (step S102).

The identification unit 153 of the information processing device 100 performs clustering on all vector data registered in the vector table 143, thereby classifying similar vector data into the same group (step S103).

The determination unit 154 of the information processing device 100 acquires the attribute data, sensor data, and current time of the logged-in user from among the multiple users included in the group (step S105). The determination unit 154 determines the distribution data to be distributed to the user terminals 10 of the group based on the acquired attribute data, sensor data, current time, and the determination table 141 (step S105).

The distribution unit 155 of the information processing device 100 distributes the determined distribution data to all user terminals 10 included in the group (step S106). If the information processing device 100 continues processing (step S107, Yes), it proceeds to step S101. On the other hand, if the information processing device 100 does not continue processing (step S107, No), it ends processing.

5. Hardware Configuration
The user terminal 10 or the information processing device 100 according to the above-described embodiment is realized by a computer 80 having a configuration as shown in Fig. 7, for example. The following description will be given using the information processing device 100 as an example. Fig. 9 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 100 according to the embodiment. The computer 80 has 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 programs stored in the ROM 83 or HDD 84 and controls each component. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, as well as programs that depend on the computer 80's hardware.

The HDD 84 stores programs executed by the CPU 81 and data used by such programs. The communication interface 85 receives data from other devices via the network and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

The CPU 81 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input/output interface 86. The CPU 81 acquires data from the input devices via the input/output interface 86. The CPU 81 also outputs data generated via the input/output interface 86 to the output devices.

The media interface 87 reads programs or data stored on the recording medium 88 and provides them to the CPU 81 via the RAM 82. The CPU 81 loads the programs from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded programs. The recording medium 88 may be, 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.

For example, when the computer 80 functions as the information processing device 100 according to the embodiment, the CPU 81 of the computer 80 executes programs loaded onto the RAM 82 to realize the functions of the control unit 150. In addition, the HDD 84 stores data in the storage unit 140. The CPU 81 of the computer 80 reads and executes these programs from the recording medium 88, but as another example, these programs may be obtained from another device via the network N.

[6. Other]
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 all or part of the processes described as being performed manually can be performed automatically using known methods. Furthermore, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

Furthermore, the components of each device shown in the figure are functional concepts and do not necessarily have to be physically configured as shown. In other words, the specific form of distribution and integration of each device is not limited to that shown, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

For example, the information processing device 100 described above may be implemented using multiple server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

Furthermore, the above-described embodiments and variations can be combined as appropriate to the extent that the processing content is not contradictory.

For example, the sensor data is data including sensor values such as illuminance, sound, position, air pressure, speed, and images. The user terminal 10 generates vector data by inputting the sensor data into a trained machine learning model 15b, but which sensor values are emphasized is set during machine learning by the machine learning model 15b. For example, a machine learning model in which machine learning was performed focusing only on position and air pressure out of the sensor values such as illuminance, sound, position, air pressure, speed, and images may be used.

Furthermore, while the information processing device 100 described above receives vector data from the user terminal 10, the information processing device 100 may also store a machine learning model and generate vector data from sensor data transmitted from the user terminal 10.

7. Effects
As described above, the information processing device 200 according to the embodiment includes an acquisition unit 152, an identification unit 153, a determination unit 154, and a distribution unit 155. The acquisition unit 152 acquires a plurality of vectors corresponding to a plurality of users, each of which is generated using a machine learning model trained to generate similar vectors from sensor information of similar situations. The identification unit 153 identifies a user group having similar vectors based on the plurality of vectors. The determination unit 154 determines the content of information to be provided to the user group based on information on logged-in users included in the user group identified by the identification unit 153. The distribution unit 155 distributes the determined information to the devices owned by each of the user group. This improves the accuracy of information provision.

Furthermore, when there are multiple logged-in users, the determination unit 154 identifies common information among the information of the multiple logged-in users and determines the content of the information to be provided to the group of users based on the identified common information. This makes it possible to determine the information to be distributed even when multiple logged-in users are included in the same group.

In addition, the acquisition unit 152 further acquires sensor information measured by the terminals of logged-in users, and the determination unit 154 further uses the acquired sensor information to determine the content of the information to be provided to the user group. This further improves the accuracy of information provision.

In addition, the sensor information acquired by the acquisition unit 152 includes at least one sensor value from among illuminance, sound, position, air pressure, speed, and image, and the determination unit 154 determines the content of the information to be provided to the user group based on the sensor information acquired by the acquisition unit 152. This makes it possible to further improve the accuracy of information provision.

The determination unit 154 also uses time information to determine the content of the information to be provided to the user group. This allows appropriate information to be provided according to the time of day.

The above describes in detail the embodiments of the present application based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that incorporate various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the Disclosure of the Invention section.

Furthermore, the "parts" (section, module, unit) mentioned above can be read as "means" or "circuit." For example, an acquisition unit can be read as an acquisition means or an acquisition circuit.

10 User terminal 11, 110 Communication unit 12, 120 Input unit 13, 130 Display unit 14 Sensor group 15, 140 Storage unit 15a Sensor data 15b Machine learning model 16, 150 Control unit 16a Access unit 16b Generation unit 16c Transmission unit 16d Display processing unit 100 Information processing device 105 Timer 141 Decision table 142 User management table 143 Vector table 151 Service providing unit 152 Acquisition unit 153 Identification unit 154 Decision unit 155 Distribution unit

Claims (7)

an acquisition unit that acquires a plurality of vectors corresponding to a plurality of users, the vectors being generated using a machine learning model trained to generate similar vectors from sensor information of similar situations;
an identification unit that identifies a group of users having similar vectors based on the plurality of vectors;
a determination unit that determines the content of information to be provided to the user group based on information of logged-in users among the users included in the user group identified by the identification unit;
a distribution unit that distributes the information on the determined content to terminals respectively possessed by the user group. The information processing device described in claim 1, characterized in that, when there are multiple logged-in users, the determination unit identifies common information among the information of the multiple logged-in users, and determines the content of the information to be provided to the group of users based on the identified common information. The information processing device described in claim 1, characterized in that the acquisition unit further acquires sensor information measured by the terminal of the logged-in user, and the determination unit further uses the acquired sensor information to determine the content of the information to be provided to the user group. The information processing device described in claim 3, characterized in that the sensor information acquired by the acquisition unit includes at least one sensor value from among illuminance, sound, position, air pressure, speed, and image, and the determination unit determines the content of the information to be provided to the user group based on the sensor information acquired by the acquisition unit. The information processing device described in claim 1, characterized in that the determination unit further uses time information to determine the content of the information to be provided to the user group. 1. A computer-implemented distribution method comprising:
an acquisition step of acquiring a plurality of vectors corresponding to a plurality of users, the vectors being generated using a machine learning model trained to generate similar vectors from sensor information of similar situations;
an identification step of identifying a group of users having similar vectors based on the plurality of vectors;
a determination step of determining the content of information to be provided to the user group based on information of logged-in users among the users included in the user group identified in the identification step;
a distribution step of distributing information on the determined content to terminals owned by each of the user group. an acquisition step of acquiring a plurality of vectors corresponding to a plurality of users, the vectors being generated using a machine learning model trained to generate similar vectors from sensor information of similar situations;
an identification step of identifying a group of users having similar vectors based on the plurality of vectors;
a determination step of determining the content of information to be provided to the user group based on information of logged-in users among the users included in the user group identified in the identification step;
and a distribution procedure for distributing the information on the determined content to terminals owned by each of the user group.