JP7407152B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

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

A technique for sending training data to a server device for causing the server device to perform machine learning has been disclosed.

Patent No. 6880290

As in the prior art described above, machine learning is generally performed by a server device. However, if the data includes information that can identify individual behavior, etc., it may not be desirable to send the data to an external server device such as a company. Furthermore, there are various restrictions on the transmission and reception of data that includes information that can identify the actions of individuals, so it may not be easy to freely transmit and receive data. In this case, users perform on-device machine learning on their own devices to build and update local models without sending data to a server. However, in the past, although the local model on the terminal side (local model) and the global model (overall model) on the server side were sometimes compared, the local models of each user were not directly compared.

The present application has been made in view of the above, and aims to allow users to share a model, perform evolutionary calculations, and update the model.

The information processing device according to the present application is an information processing device used as a terminal device carried by a user, and includes a receiving unit that receives a model distributed from a server side, and a function of the terminal device as data used for learning. an acquisition unit that acquires data measured or recorded by the device; and a local model on the terminal side and a global model on the server side, based on predetermined rules such as data content or context when acquiring the data. It is determined which model should be used for machine learning, and if it is determined that machine learning is to be performed using the local model on the terminal side, a learning section that performs on-device machine learning of the model using the data, and a learning section that performs on-device machine learning of the model using the data, and In order to match and unify models while determining their superiority or inferiority, exchange models with other people's information processing devices and obtain other people's models that have undergone machine learning on the other people's information processing devices. When exchanging local models between the exchange unit and the terminal device, the models are pitted against each other, and the accuracy of inference between the current model and the other person's model is compared and evaluated using the data to determine superiority or inferiority. a determining unit; and an updating unit that updates its own model to a model with higher inference accuracy between the current model and the other person's model as a result of the comparative study, thereby updating the model to a model that has won the battle. It is characterized by having the following.

According to one aspect of the embodiment, users can share a model, perform evolutionary calculations, and update the model.

FIG. 1 is an explanatory diagram showing an overview of an information processing method according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of an information processing system according to an embodiment. FIG. 3 is a diagram illustrating a configuration example of a terminal device according to an embodiment. FIG. 4 is a diagram illustrating a configuration example of an information providing apparatus according to an embodiment. FIG. 5 is a diagram showing an example of a user information database. FIG. 6 is a diagram showing an example of a history information database. FIG. 7 is a diagram showing an example of a model information database. FIG. 8 is a flowchart showing the processing procedure according to the embodiment. FIG. 9 is a diagram showing an example of the hardware configuration.

DESCRIPTION OF THE PREFERRED EMBODIMENTS An information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. In addition, in the following embodiments, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. Overview of information processing method]
First, with reference to FIG. 1, an overview of an information processing method performed by an information processing apparatus according to an embodiment will be described. FIG. 1 is an explanatory diagram showing an overview of an information processing method according to an embodiment. In FIG. 1, an example will be described in which a user shares a model, performs evolutionary calculations, and updates the model.

As shown in FIG. 1, the information processing system 1 includes a terminal device 10 and an information providing device 100. The terminal device 10 and the information providing device 100 are connected to each other via a network N (see FIG. 2) so that they can communicate with each other by wire or wirelessly. In this embodiment, the terminal device 10 cooperates with the information providing device 100.

The terminal device 10 is a smart device such as a smartphone or a tablet used by a user U (user), and can communicate with any server device via a wireless communication network such as 4G (Generation) or LTE (Long Term Evolution). This is a mobile terminal device that can perform Further, the terminal device 10 has a screen such as a liquid crystal display, which has a touch panel function, and displays data such as content through a tap operation, a slide operation, a scroll operation, etc. from the user U using a finger or a stylus. Accepts various operations on. Note that an operation performed on an area of the screen where content is displayed may be an operation on the content. Further, the terminal device 10 may be not only a smart device but also an information processing device such as a desktop PC (Personal Computer) or a notebook PC.

The information providing device 100 cooperates with the terminal device 10 of each user U, and provides API (Application Programming Interface) services for various applications (hereinafter referred to as applications), etc., to the terminal device 10 of each user U, and various It is an information processing device that provides data, and is realized by a server device, a cloud system, etc.

Further, the information providing device 100 may be an information processing device that provides some kind of web service online to the terminal device 10 of each user U. For example, the information providing device 100 provides web services such as Internet connection, search service, SNS (Social Networking Service), electronic commerce, electronic payment, online games, online banking, online trading, accommodation/ticket reservation, video/music distribution, Services such as news, maps, route searches, route guidance, route information, operation information, weather forecasts, etc. may be provided. In reality, the information providing apparatus 100 may cooperate with various servers that provide the above-mentioned Web services, mediate the Web services, or may be in charge of processing the Web services.

Note that the information providing device 100 can acquire user information regarding the user U. For example, the information providing device 100 acquires information regarding attributes of the user U, such as the user's U's gender, age, and area of residence. Then, the information providing device 100 stores and manages information regarding attributes of the user U along with identification information indicating the user U (user ID, etc.).

Further, the information providing device 100 acquires various kinds of history information (log data) indicating the behavior of the user U from the terminal device 10 of the user U or from various servers based on the user ID or the like. For example, the information providing device 100 acquires a location history, which is a history of the user U's location, date and time, from the terminal device 10. The information providing device 100 also acquires a search history, which is a history of search queries input by the user U, from a search server (search engine). The information providing device 100 also acquires a viewing history, which is a history of content viewed by the user U, from the content server. Further, the information providing device 100 acquires a purchase history (payment history) that is a history of product purchases and payment processing by the user U from the electronic commerce server and the payment processing server. Further, the information providing device 100 may acquire the listing history and the sales history, which are the listing history of the user U on the marketplace, from the electronic commerce server or the payment server. The information providing device 100 also acquires a posting history, which is a history of postings by the user U, from a posting server or SNS server that provides a word-of-mouth posting service.

As shown in FIG. 1, the information providing device 100 (server side) distributes models with different patterns to each of the terminal devices 10 (terminal side) of each user U (step S1).

For example, the model distributed from the information providing device 100 to the terminal device 10 of each user U is not a global model (overall model) on the server side, but a local model (local model) on the terminal side, which focuses on a certain interest. This is a model that is estimated from device logs.

In the present embodiment, the information providing device 100 creates 10 optimization models (10 patterns) of recommendation information (recommendation), and applies the 10 patterns to the terminal devices 10 of all users U participating in the information processing system 1. One of the models is randomly distributed. Note that, in reality, the type and content of the distributed model are arbitrary. For example, the information providing device 100 may distribute an inference model that infers each user's behavior.

The terminal device 10 of each user U receives the model distributed from the information providing device 100 (server side), uses the data acquired by the respective terminal device 10 as learning data, and uses the model on the respective terminal. On-device machine learning is performed (step S2).

In this embodiment, the terminal device 10 of the user U acquires data measured or recorded by the functions of the terminal device 10. For example, the terminal device 10 acquires location information of the terminal device 10, sensor data, attribute information of the user U, history information (operation history, payment history, etc.) as data. The terminal device 10 acquires detailed position information at a first accuracy (for example, 10 meter accuracy, 10 meter mesh) using a positioning method such as GPS (Global Positioning System) or RTK (Real Time Kinematic). Furthermore, the terminal device 10 may acquire sensor data measured by each sensor mounted on or connected to the terminal.

Note that when the terminal device 10 of the user U acquires data such as location information and sensor data, the local model (local model) on the terminal side (terminal device 10) is It may be determined which model is used for machine learning among the global model (overall model) on the server side (information providing device 100). That is, it may be determined whether to update the local model or the global model. Local models and global models have different accuracy. For example, the terminal device 10 of the user U determines which one to learn, the server-side global model or the terminal-side local model, from the acquired data and context.

At this time, if the terminal device 10 of the user U determines that machine learning is to be performed using the global model on the server side (information providing device 100), the terminal device 10 of the user U changes the data to a raw data state or an abstracted state based on a predetermined rule. It is transmitted to the server side (information providing device 100) in the form of abstracted data. Then, the terminal device 10 receives the results of machine learning using the global model using the transmitted data from the server side (information providing device 100). For example, the terminal device 10 receives an inference result using a global model or information based on the inference result (recommendation information, etc.) as a result of machine learning. That is, the terminal device 10 performs online machine learning.

On the other hand, if the terminal device 10 of the user U determines that machine learning is to be performed using the local model on the terminal side (terminal device 10) (in the case of on-device machine learning), the terminal device 10 of the user U performs machine learning using the data and uses the local model. Build. Then, the terminal device 10 inputs the data into the local model, performs inference, and obtains an inference result. That is, the terminal device 10 performs on-device machine learning.

However, when machine learning is performed on a local model on the terminal side (terminal device 10) (in the case of on-device machine learning), the local model develops independently on each user's terminal device 10, so each terminal device It is not possible to harmonize or unify the 10 local models or to judge their superiority or inferiority.

Therefore, in this embodiment, only the local models of each user U are exchanged/shared without passing the respective data between the terminal devices 10 of each user U, and the own data is transmitted on the terminal device 10 of each user U. Input your own model and other people's models and compare and verify which model is better. For example, the accuracy of inferences made by local models of oneself and others is compared and verified using one's own data. In most cases, it is assumed that a self-developed model optimized for one's own data is superior, but due to differences in the performance of terminal devices and sensors, or differences in the type and number of data used for learning, It may happen that someone else's model is better. In this case, the self model is updated to the other person's model. That is, when exchanging/sharing local models between terminal devices, the models are pitted against each other, and the winning model is updated.

The terminal devices 10 of each user U exchange/share the local model on which on-device machine learning was performed on each user's U terminal device 10 (step S3).

To exchange/share local models between the terminal devices 10 of each user U, short-range wireless communication such as Bluetooth (registered trademark) or wireless LAN (Local Area Network), or so-called "passing communication" is used. Good too. As a result, when a user from a certain area visits another area for business/travel, they can exchange/share models with users from the area they visited.

Furthermore, the terminal devices 10 of each user U may exchange/share local models via the same base station, router, access point, home server, LAN in the same campus, or the like. Further, the terminal device 10 of each user U may exchange/share local models using P2P (Peer to Peer) or an overlay network. Alternatively, the terminal device 10 of each user U may exchange/share local models with users who have common attributes and behavior history via the network N (see FIG. 2). In reality, the terminal device 10 of each user U randomly exchanges/shares local models with users in the same region or across the country via the network N (see FIG. 2). You may also do so.

Furthermore, when exchanging local models between the terminal devices 10 of each user U, only a part of the model may be exchanged instead of the entire model. For example, in the case of a language model, it is also possible to exchange only part of the model.

When the terminal devices 10 of each user U exchange local models between the terminal devices 10 of each user U, the terminal device 10 of each user U inputs its own data into its own model and the model of another person on each terminal, Comparatively verify which model is superior (step S4).

In this embodiment, the terminal device 10 of the user U uses its own data to compare and verify the accuracy of inferences made by the local models of itself and others. For example, each user U exchanges/shares models when passing each other with other users, and pits the models against each other using data (question data, correct answer data) stored in the user's terminal device 10.

For example, when user U1 and user U2 pass each other, their respective terminal devices 10 exchange models with each other. The terminal device 10A of the user U1 has a model in which model A is tuned using the log of the user U1. The terminal device 10B of the user U2 has a model in which the model B is tuned using the log of the user U1. The terminal device 10A of the user U1 has a model in which model A is tuned using the log of the user U1.

Then, each user swaps Model A and Model B on their own terminals and compares and verifies them (let them compete). At this time, the terminal device 10A of the user U1 applies model B to the log of the user U1. Further, the terminal device 10B of the user U2 applies model A to the log of the user U2.

Note that if a large number of local models are compared and verified at the same time, the load on the terminal device 10 increases, so it is preferable that the number of local models that are simultaneously compared and verified is about two or three. For example, the terminal device 10 of each user U compares and verifies which of the local models of three terminal devices including the user U has the highest accuracy.

The terminal device 10 of each user U adopts the model determined to be superior as a result of comparison and verification, and updates its own model to the adopted model (step S5).

In the present embodiment, the terminal device 10 of each user U completely updates (repaints) the model when a significant victory or defeat (superiority) is determined as a result of comparison verification. Furthermore, if the terminal device 10 of each user U determines that there is no significant difference as a result of the comparison verification, the model may not be updated or may be assembled. The assembled model survives as a new model (a model that is different from the current models of itself and others).

For example, the terminal device 10 of the user U may construct a new model that shares part of the neural network as a model assembly. That is, when updating the local model, the terminal device 10 may update only a portion of the model instead of the entire model. At this time, the terminal device 10 of the user U may extract good parts from each of the compared and verified models and combine them.

By continuing to repeatedly perform the above process on an unspecified number of terminal devices 10, a highly accurate model is propagated among the terminal devices. Thereby, the model can be optimized/averaged between terminal devices. In addition, in machine learning, it is possible to improve overfitting (overfitting, overlearning) in which learning is performed on training data, but it is not possible to fit unknown data (test data).

It is also possible to investigate model characteristics (dialects) by area, such as prefecture or city, ward, town, or village. For example, it is possible to grasp the situation in which terminal devices of users in metropolitan areas such as Tokyo and Fukuoka tend to be aggregated into models with the same pattern even if they are located far apart. Additionally, it is possible to grasp the situation, such as in which regions the trends in the models being adopted are divided.

You can also pit models against each other to see who is better or worse (model battle), and gain new knowledge based on the results. For example, by holding model battles between residents and between residents and visitors (movers) in each area, you can find out that ``Model 1 is strong in Western Japan and Model 2 is strong in East Japan,'' or ``Model 2 is uniquely strong in Western Japan.'' Results include ``Model 3 is strong in only one area,'' ``Model 4 is strong among women in their 20s regardless of area,'' and ``Model A is strong in Tokyo and Fukuoka, and Model B is strong in Osaka.'' By reviewing these results, new knowledge that cannot be obtained using conventional techniques can be obtained. In other words, by looking back on the results of model battles, you can learn about the unique context of each model and how to approach it. The angle at which differences in model battle results occur indicates that the characteristics of each group are different, so it is useful to just know the angle.

As described above, in this embodiment, when the terminal device 10 of the user U exists in the same context, the terminal device 10 of the user U has a local Exchange/share models, pit your own and others' local models against each other, and overwrite the one with better performance. Since it is executed on the terminal device side, the model with better performance overwrites the data that each other has. As a result, a model with good accuracy conquers other users' terminal devices. Note that if the models are balanced, weights are assembled (shared part of the neural network structure, etc.). That is, in this embodiment, the terminal device 10 of the user U performs evolutionary calculation with position information.

[2. Configuration example of information processing system]
Next, the configuration of the information processing system 1 including the information providing apparatus 100 according to the embodiment will be described using FIG. 2. FIG. 2 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. As shown in FIG. 2, the information processing system 1 according to the embodiment includes a terminal device 10 and an information providing device 100. These various devices are connected via a network N so that they can communicate by wire or wirelessly. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

Furthermore, the number of devices included in the information processing system 1 shown in FIG. 2 is not limited to what is illustrated. For example, in FIG. 2, only three terminal devices 10 are shown for simplification of illustration, but this is just an example and is not limited, and the number may be four or more.

The terminal device 10 is an information processing device used by the user U. For example, the terminal device 10 may be a smart device such as a smartphone or a tablet terminal, a feature phone, a PC (Personal Computer), a PDA (Personal Digital Assistant), a game console or AV device with a communication function, a car navigation system, a smart watch, or the like. These include wearable devices such as head-mounted displays, smart glasses, smart speakers, cameras, etc. However, in reality, it is not limited to these examples.

The terminal device 10 also supports wireless communication networks such as LTE (Long Term Evolution), 4G (4th Generation), 5G (5th Generation), Bluetooth (registered trademark), wireless LAN (Local The information providing device 100 can be connected to the network N via short-distance wireless communication such as an area network) and can communicate with the information providing device 100.

The information providing device 100 is, for example, a PC, a server device, a mainframe, a workstation, or the like. Note that the information providing device 100 may be realized by cloud computing.

[3. Configuration example of terminal device]
Next, the configuration of the terminal device 10 will be explained using FIG. 3. FIG. 3 is a diagram showing a configuration example of the terminal device 10. As shown in FIG. As shown in FIG. 3, the terminal device 10 includes a communication section 11, a display section 12, an input section 13, a positioning section 14, a sensor section 20, a control section 30 (controller), and a storage section 40. Be prepared.

(Communication Department 11)
The communication unit 11 is connected to a network N (see FIG. 2) by wire or wirelessly, and transmits and receives information to and from the information providing device 100 via the network N. For example, the communication unit 11 is realized by a NIC (Network Interface Card), an antenna, or the like.

(Display section 12)
The display unit 12 is a display device that displays various information such as position information. For example, the display unit 12 is a liquid crystal display (LCD) or an organic electro-luminescent display (EL display). Further, the display unit 12 is a touch panel type display, but is not limited to this.

(Input section 13)
The input unit 13 is an input device that receives various operations from the user U. For example, the input unit 13 includes buttons for inputting characters, numbers, and the like. Note that the input unit 13 may be an input/output port (I/O port), a USB (Universal Serial Bus) port, or the like. Further, when the display section 12 is a touch panel display, a part of the display section 12 functions as the input section 13. Further, the input unit 13 may be a microphone or the like that receives voice input from the user U. The microphone may be wireless.

(Positioning unit 14)
The positioning unit 14 receives a signal (radio wave) sent from a GPS (Global Positioning System) satellite, and based on the received signal, determines position information (for example, latitude and longitude). That is, the positioning unit 14 positions the terminal device 10 . Note that GPS is just one example of GNSS (Global Navigation Satellite System).

Further, the positioning unit 14 can measure the position using various methods other than GPS. For example, the positioning unit 14 may use various communication functions of the terminal device 10 to measure the position as an auxiliary positioning means for position correction and the like, as described below.

(Wi-Fi positioning)
For example, the positioning unit 14 positions the terminal device 10 using the Wi-Fi (registered trademark) communication function of the terminal device 10 or the communication network provided by each communication company. Specifically, the positioning unit 14 performs Wi-Fi communication, etc., and determines the position of the terminal device 10 by measuring the distance to nearby base stations and access points.

(Beacon positioning)
Further, the positioning unit 14 may use the Bluetooth (registered trademark) function of the terminal device 10 to measure the position. For example, the positioning unit 14 measures the position of the terminal device 10 by connecting to a beacon transmitter connected by a Bluetooth (registered trademark) function.

(geomagnetic positioning)
Furthermore, the positioning unit 14 positions the terminal device 10 based on the geomagnetic pattern of the structure measured in advance and the geomagnetic sensor included in the terminal device 10 .

(RFID positioning)
Further, for example, if the terminal device 10 has an RFID (Radio Frequency Identification) tag function equivalent to a contactless IC card used at station ticket gates, stores, etc., or has a function to read an RFID tag. In this case, the location where the terminal device 10 used the terminal device 10 is recorded together with the information that the payment was made. The positioning unit 14 may measure the position of the terminal device 10 by acquiring such information. Further, the position may be determined by an optical sensor, an infrared sensor, or the like provided in the terminal device 10.

The positioning unit 14 may position the terminal device 10 using one or a combination of the above-mentioned positioning means, if necessary.

(sensor section 20)
The sensor unit 20 includes various sensors mounted on or connected to the terminal device 10. Note that the connection may be a wired connection or a wireless connection. For example, the sensors may be a detection device other than the terminal device 10, such as a wearable device or a wireless device. In the example shown in FIG. 3, the sensor unit 20 includes an acceleration sensor 21, a gyro sensor 22, an atmospheric pressure sensor 23, an air temperature sensor 24, a sound sensor 25, an optical sensor 26, a magnetic sensor 27, and an image sensor ( camera) 28.

Note that each of the sensors 21 to 28 described above is merely an example and is not limited to the above. That is, the sensor section 20 may be configured to include a portion of each of the sensors 21 to 28, or may include other sensors such as a humidity sensor in addition to or instead of each of the sensors 21 to 28. .

The acceleration sensor 21 is, for example, a three-axis acceleration sensor, and detects the physical movement of the terminal device 10, such as the moving direction, speed, and acceleration of the terminal device 10. The gyro sensor 22 detects physical movements of the terminal device 10 such as tilt in three axes directions based on the angular velocity of the terminal device 10 and the like. The atmospheric pressure sensor 23 detects the atmospheric pressure around the terminal device 10, for example.

Since the terminal device 10 is equipped with the above-mentioned acceleration sensor 21, gyro sensor 22, atmospheric pressure sensor 23, etc., it is possible to implement technologies such as pedestrian autonomous navigation (PDR) using these sensors 21 to 23, etc. It becomes possible to measure the position of the terminal device 10 using the . This makes it possible to obtain indoor position information that is difficult to obtain using positioning systems such as GPS.

For example, a pedometer using the acceleration sensor 21 can calculate the number of steps, walking speed, and distance walked. Furthermore, by using the gyro sensor 22, it is possible to know the direction of travel of the user U, the direction of the line of sight, and the inclination of the user's body. Further, from the atmospheric pressure detected by the atmospheric pressure sensor 23, it is also possible to know the altitude and the number of floors where the terminal device 10 of the user U is located.

The temperature sensor 24 detects, for example, the temperature around the terminal device 10. The sound sensor 25 detects, for example, sounds around the terminal device 10. The optical sensor 26 detects the illuminance around the terminal device 10 . The magnetic sensor 27 detects, for example, the earth's magnetism around the terminal device 10. The image sensor 28 captures an image of the surroundings of the terminal device 10.

The above-mentioned atmospheric pressure sensor 23, temperature sensor 24, sound sensor 25, optical sensor 26, and image sensor 28 each detect atmospheric pressure, temperature, sound, and illuminance, and capture images of the surroundings, so that the terminal device 10 It is possible to detect the surrounding environment and situation. Furthermore, it is possible to improve the accuracy of the location information of the terminal device 10 based on the environment and situation around the terminal device 10.

(Control unit 30)
The control unit 30 includes, for example, a microcomputer having a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM, an input/output port, etc., and various circuits. Further, the control unit 30 may be configured with hardware such as an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The control section 30 includes a transmitting section 31 , a receiving section 32 , a processing section 33 , an acquiring section 34 , a learning section 35 , an exchanging section 36 , a determining section 37 , and an updating section 38 .

(Transmission unit 31)
The transmitting unit 31 receives, for example, various information input by the user U using the input unit 13, various information detected by the sensors 21 to 28 mounted on or connected to the terminal device 10, and information measured by the positioning unit 14. The location information of the terminal device 10 and the like can be transmitted to the information providing device 100 via the communication unit 11. Further, when the transmitting unit 31 determines to send the data to the information providing device 100 (server side), the transmitting unit 31 transmits the data to the information providing device 100 (server side) via the communication unit 11. Note that the transmitting unit 31 may transmit the data in the form of raw data to the information providing device 100 (server side) based on predetermined rules such as data content and context, or may transmit the data in the form of an abstract data. It may also be sent to the information providing apparatus 100 (server side) in the form of data.

Further, when the local model (local model) of the terminal device 10 is updated, the transmitting unit 31 transmits information regarding the updated model (updated model) and the update date and time to the information providing device 100 via the communication unit 11. (server side). At this time, the transmitter 31 may also notify the information providing device 100 (server side) of information regarding the location (region, etc.) at the time the model was updated.

(Receiving unit 32)
The receiving unit 32 can receive various information provided from the information providing device 100 and requests for various information from the information providing device 100 via the communication unit 11 . In this embodiment, the receiving unit 32 receives a model distributed from the information providing device 100 (server side) via the communication unit 11. This distributed model becomes a local model of the terminal device 10. Further, the receiving unit 32 receives, via the communication unit 11, the results of machine learning on the global model (hull model) using data from the information providing device 100 (server side).

(Processing unit 33)
The processing unit 33 controls the entire terminal device 10, including the display unit 12 and the like. For example, the processing unit 33 can output various types of information transmitted by the transmitting unit 31 and various types of information received by the receiving unit 32 from the information providing device 100 to the display unit 12 for display. Note that the processing unit 33 may include an acquisition unit 34, a learning unit 35, an exchange unit 36, a determination unit 37, and an update unit 38 described below.

(Acquisition unit 34)
The acquisition unit 34 acquires data used for learning via the positioning unit 14, the sensor unit 20, or the input unit 13. Specifically, the acquisition unit 34 acquires location information of the terminal device 10, sensor data, attribute information of the user U, history information (operation history, payment history, etc.) as data used for learning. For example, the acquisition unit 34 acquires position information at a first accuracy (for example, 10 meter accuracy, 10 meter mesh) using a positioning method such as GPS (Global Positioning System) or RTK (Real Time Kinematic). Further, the acquisition unit 34 acquires sensor data measured by each sensor mounted on or connected to the terminal.

(Learning Department 35)
The learning unit 35 performs machine learning using a local model using data. That is, the learning unit 35 performs on-device machine learning. For example, when the learning unit 35 determines not to send the data to the information providing device 100 (server side), the learning unit 35 performs machine learning using the local model using the data.

Furthermore, the learning unit 35 determines information to be presented to the user U (presentation information) based on the inference result of the local model using the data. For example, the learning unit 35 determines recommendation information such as advertisements and coupons of stores around the current location of the user U as information to be presented to the user U (presentation information). At this time, the transmitting unit 31 may request recommendation information such as advertisements and coupons of stores around the current location of the user U via the communication unit 11. Further, when receiving a plurality of pieces of provided information (recommendation information, etc.) from the information providing device 100 (server side), the learning unit 35 determines whether the information providing device 100 The information to be presented to the user U (presentation information) is determined by narrowing down the plural pieces of provided information (recommendation information, etc.) received from the user U.

(Replacement part 36)
The exchange unit 36 exchanges models with another person's terminal device 10 and obtains the other person's model held by the other person's terminal device 10. At this time, when exchanging models with each other, the exchanging unit 36 may exchange not all of the models but a part of the models.

Further, the exchange unit 36 may exchange models with each other when passing each other with another person's terminal device 10. Alternatively, the exchange unit 36 may exchange models with another person's terminal device 10 via a network without going through the server side. Furthermore, the exchange unit 36 may exchange models with each other when other terminal devices 10 having different models are in the same context. Note that being in the same context means, for example, being in the same place at the same time (train station, commercial facility, school, office building, etc.), or when the user U and other users U are doing the same thing ( This includes when taking a walk, running, traveling by car, traveling by train, etc.). Some errors in time and location are allowed.

Furthermore, the current model held by one's own terminal device 10 and the other person's model held by another person's terminal device 10 are models distributed from the server side for the same purpose, but with different patterns. be. Moreover, in reality, the exchange unit 36 may be read as a sharing unit that shares a mutual model with the terminal device 10 of another person.

(Determination unit 37)
The determining unit 37 uses data to compare and examine the accuracy of inference between the current model and another person's model, and determines their superiority. Note that the determination unit 37 may be read as a comparison unit that compares and examines the inference accuracy of the own model and that of other models.

Further, the determination unit 37 performs a model battle in which the current model is pitted against another person's model, and stores (records) the result of the model battle in the storage unit 120 or the like. For example, the determination unit 37 conducts a model battle in which the current model and another person's model compete in each area. Further, the determination unit 37 analyzes the results of the model battle to obtain a unique context and perspective for each model.

(Update section 38)
As a result of the comparison, the updating unit 38 updates its own model to the model with higher inference accuracy between the current model and the other model. Note that when updating its own model, the updating unit 38 may update a part of the model instead of the entire model. Further, when updating its own model, the updating unit 38 may assemble the model using the current model and another person's model.

(Storage unit 40)
The storage unit 40 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 an HDD (Hard Disk Drive), an SSD (Solid State Drive), or an optical disk. Ru. The storage unit 40 stores various programs, various data, and the like. In this embodiment, the storage unit 40 stores acquired learning data, a model distributed from the server side (information providing device), another person's model acquired from another person's terminal device 10, and the like.

[4. Configuration example of information providing device]
Next, the configuration of the information providing apparatus 100 according to the embodiment will be described using FIG. 4. FIG. 4 is a diagram illustrating a configuration example of the information providing apparatus 100 according to the embodiment. As shown in FIG. 4, the information providing device 100 includes a communication section 110, a storage section 120, and a control section 130.

(Communication Department 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). Further, the communication unit 110 is connected to the network N (see FIG. 2) by wire or wirelessly.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as an HDD, an SSD, or an optical disk. As shown in FIG. 4, the storage unit 120 includes a user information database 121, a history information database 122, and a model information database 123.

(User information database 121)
The user information database 121 stores user information regarding the user U. For example, the user information database 121 stores various information such as user U's attributes. FIG. 5 is a diagram showing an example of the user information database 121. In the example shown in FIG. 5, the user information database 121 has items such as "user ID (identifier),""age,""gender,""home,""worklocation," and "interest."

“User ID” indicates identification information for identifying user U. Note that the "user ID" may be user U's contact information (telephone number, email address, etc.), or may be identification information for identifying user U's terminal device 10.

Moreover, "age" indicates the age of the user U identified by the user ID. Note that the "age" may be information indicating the specific age of the user U (for example, 35 years old, etc.), or may be information indicating the age of the user U (for example, 30s, etc.) . Alternatively, the "age" may be information indicating the date of birth of the user U, or may be information indicating the generation of the user U (for example, born in the 1980s). Furthermore, “gender” indicates the gender of the user U identified by the user ID.

Moreover, "home" indicates the location information of the home of the user U identified by the user ID. In the example shown in FIG. 5, "home" is illustrated as an abstract code such as "LC11", but it may also be latitude and longitude information. Furthermore, for example, "home" may be a region name or address.

Moreover, "work place" indicates the location information of the work place (school in the case of a student) of the user U identified by the user ID. In the example shown in FIG. 5, the "work location" is illustrated as an abstract code such as "LC12", but it may also be latitude/longitude information or the like. Further, for example, the "work location" may be a region name or address.

Moreover, "interest" indicates the interest of the user U identified by the user ID. That is, "interest" indicates an object in which the user U identified by the user ID has a high interest. For example, "interest" may be a search query (keyword) that the user U inputs into a search engine. In the example shown in FIG. 5, one "interest" is shown for each user U, but there may be a plurality of "interests".

For example, in the example shown in FIG. 5, the age of the user U identified by the user ID "U1" is "20s", and the gender is "male". Further, for example, the user U identified by the user ID "U1" indicates that his home is "LC11". Further, for example, the user U identified by the user ID "U1" indicates that the work location is "LC12". Further, for example, the user U identified by the user ID "U1" indicates that he is interested in "sports."

Here, in the example shown in FIG. 5, abstract values such as "U1", "LC11", and "LC12" are used for illustration, but "U1", "LC11", and "LC12" have specific values. It is assumed that information such as character strings and numerical values is stored. Below, abstract values may be illustrated in diagrams related to other information as well.

Note that the user information database 121 is not limited to the above, and may store various information depending on the purpose. For example, the user information database 121 may store various information regarding the terminal device 10 of the user U. In addition, the user information database 121 includes information such as demographic (demographic attributes), psychographic (psychological attributes), geographic (geographical attributes), behavioral (behavioral attributes), etc. of user U. Information regarding attributes may also be stored. For example, the user information database 121 includes name, family composition, place of birth (locality), occupation, position, income, qualifications, type of residence (single-family house, condominium, etc.), presence or absence of a car, commuting/commuting time, commuting/commuting, etc. Memorizes information such as routes, commuter pass sections (stations, lines, etc.), frequently used stations (other than the stations closest to your home or work), lessons (location, time zone, etc.), hobbies, interests, lifestyle, etc. You can.

(History information database 122)
The history information database 122 stores various information related to history information (log data) indicating the actions of the user U. FIG. 6 is a diagram showing an example of the history information database 122. In the example shown in FIG. 6, the history information database 122 has items such as "user ID", "location history", "search history", "browsing history", "purchase history", and "posting history".

“User ID” indicates identification information for identifying user U. Further, “position history” indicates a position history that is a history of the user U's position and movement. Further, “search history” indicates a search history that is a history of search queries input by the user U. In addition, “browsing history” indicates a browsing history that is a history of contents that the user U has viewed. Further, “purchase history” indicates a purchase history that is a history of purchases by user U. Moreover, "posting history" indicates a posting history that is a history of postings by user U. Note that the "posting history" may include questions regarding user U's belongings.

For example, in the example shown in FIG. 6, user U identified by user ID "U1" moves as per "location history #1", searches as per "search history #1", and searches as per "view history #1". This indicates that the content was viewed according to "history #1", a predetermined product, etc. was purchased at a predetermined store etc. according to "purchase history #1", and the content was posted according to "posting history".

Here, in the example shown in FIG. 6, abstracts such as "U1", "location history #1", "search history #1", "browsing history #1", "purchase history #1" and "posting history #1" are used. Although the figures are shown using typical values, "U1", "location history #1", "search history #1", "browsing history #1", "purchase history #1" and "posting history #1" are , information such as specific character strings and numerical values shall be stored.

Note that the history information database 122 is not limited to the above, and may store various information depending on the purpose. For example, the history information database 122 may store the user U's usage history of a predetermined service. Further, the history information database 122 may store the user U's visit history to a physical store, visit history to a facility, or the like. Further, the history information database 122 may store the payment history of user U's payment using the terminal device 10 (electronic payment).

(Model information database 123)
The model information database 123 stores various information regarding history information (log data) indicating the behavior of the user U. FIG. 7 is a diagram showing an example of the model information database 123. In the example shown in FIG. 7, the model information database 123 has items such as "user ID", "terminal device", "distribution model", "update model", and "update date and time".

“User ID” indicates identification information for identifying user U. Further, “terminal device” indicates identification information for identifying the terminal device 10 of the user U. Note that the "terminal device" may include information indicating the model (smartphone, tablet, OS name, etc.) of the terminal device 10 of the user U.

Further, "distribution model" indicates a model distributed from the information providing device 100 (server side). That is, the "distribution model" indicates the first local model. Moreover, "updated model" indicates a model updated in the terminal device 10 (terminal side). That is, the "updated model" indicates the latest local model. Moreover, the "update date and time" indicates the date and time when the model was updated on the terminal device 10 (terminal side). That is, the "update date and time" indicates the date and time when the updated model was overwritten.

For example, in the example shown in FIG. 7, "terminal device #1" owned by user U identified by user ID "U1" is first distributed with "model A", and then "updated date and time #1" is distributed. ” indicates that the own model has been updated to “updated model #1”.

Here, in the example shown in FIG. 7, abstract values such as "U1", "terminal device #1", "model A", "updated model #1", and "updated date and time #1" are used for illustration. , "U1", "Terminal device #1", "Model A", "Updated model #1", and "Updated date and time #1" store information such as specific character strings and numerical values. .

Note that the model information database 123 is not limited to the above, and may store various information depending on the purpose. For example, the model information database 123 may store information regarding the location (region, etc.) at the time the model was updated. Note that information regarding location (region, etc.) may be determined by region (area) such as prefecture or city, as there is a possibility that user U's location or actions may be identified/estimated if the information is detailed. information (area name, address, etc.) or information for each area mesh (area mesh code, etc.). Further, the model information database 123 may store update history and the like regarding all past updated models from the first distributed model to the latest updated model. Further, the model information database 123 may store data (raw data or abstracted data) collected from the terminal device 10 of each user U along with the model.

(Control unit 130)
Returning to FIG. 4, the explanation will be continued. The control unit 130 is a controller, and uses, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field Programmable Gate Array) to control the information providing apparatus 100. This is achieved by executing various programs (corresponding to an example of an information processing program) stored in an internal storage device using a storage area such as a RAM as a work area. In the example shown in FIG. 4, the control unit 130 includes a collection unit 131, an estimation unit 132, and a provision unit 133.

(Collection unit 131)
The collection unit 131 collects raw data or abstracted data from the terminal device 10 of each user U via the communication unit 110. In addition, when the model is updated on the terminal device 10 of each user U, the collection unit 131 collects the updated model (updated model) from the terminal device 10 of each user U via the communication unit 110. Collect information about date and time. At this time, the transmitter 31 may also collect information regarding the location (region, etc.) at the time the model was updated.

Additionally, the collection unit 131 may acquire user information regarding each user U via the communication unit 110. For example, the collection unit 131 acquires identification information indicating the user U (user ID, etc.), location information of the user U, attribute information of the user U, etc. from the terminal device 10 of the user U. Further, the collection unit 131 may acquire identification information indicating the user U, attribute information of the user U, etc. at the time of the user U's user registration. The collection unit 131 then registers the user information in the user information database 121 of the storage unit 120.

Additionally, the collection unit 131 may acquire various types of history information (log data) indicating the actions of each user U via the communication unit 110. For example, the collection unit 131 acquires various types of history information indicating the behavior of the user U from the terminal device 10 of the user U or from various servers based on the user ID and the like. The collection unit 131 then registers various types of history information in the history information database 122 of the storage unit 120.

(Estimation unit 132)
The estimation unit 132 performs learning and inference based on raw data or abstracted data. For example, the estimation unit 132 performs machine learning based on raw data or abstracted data to construct a global model (whole model). For example, the estimation unit 132 performs machine learning using raw data or abstracted data and the approximate current or future position and behavior of the user U as learning data. Alternatively, the estimation unit 132 performs machine learning using raw data or abstracted data and recommendation information provided to the user U as learning data.

Furthermore, the estimation unit 132 inputs raw data or abstracted data into the global model, performs inference, and obtains an inference result. For example, the estimating unit 132 estimates the approximate current or future location and behavior of the user U, or estimates the recommended information to be provided to the user U, based on raw data or abstracted data.

(Providing unit 133)
The providing unit 133 provides the terminal device 10 of the user U, which is the source of the data, with the provided information based on the inference result according to the raw data or the abstracted data via the communication unit 110. For example, the providing unit 133 provides recommendation information to the terminal device 10 of the user U based on the inference result by the global model.

Further, the providing unit 133 distributes models with different patterns to each of the terminal devices 10 of each user U (terminal side) via the communication unit 110. For example, the model distributed to the terminal device 10 of each user U is not a global model (overall model) on the server side, but a local model (local model) on the terminal side, and certain interests are estimated from on-device logs. This is a model that

For example, the estimation unit 132 creates ten optimization models (ten patterns) of recommendation information (recommendation). The providing unit 133 randomly distributes one of the ten models to the terminal devices 10 of all users U participating in the information processing system 1 via the communication unit 110.

[5. Processing procedure]
Next, a processing procedure by the terminal device 10 according to the embodiment will be described using FIG. 8. FIG. 8 is a flowchart showing the processing procedure according to the embodiment. Note that the processing procedure shown below is repeatedly executed by the control unit 30 of the terminal device 10.

As shown in FIG. 8, the receiving unit 32 of the terminal device 10 receives the model distributed from the information providing device 100 (server side) via the communication unit 11 (step S101). At this time, the receiving unit 32 receives one of the models with different patterns distributed from the information providing device 100 (server side) to each of the terminal devices 10 of each user U (terminal side).

Subsequently, the acquisition unit 34 of the terminal device 10 acquires data used for learning via the positioning unit 14, the sensor unit 20, or the input unit 13 (step S102). For example, the acquisition unit 34 acquires location information of the terminal device 10, sensor data, attribute information of the user U, history information (operation history, payment history, etc.) as data used for learning.

Subsequently, the learning unit 35 of the terminal device 10 performs machine learning with a local model using the data (step S103). That is, the learning unit 35 performs on-device machine learning.

Subsequently, the exchange unit 36 of the terminal device 10 exchanges models with the other person's terminal device 10, and acquires the other person's model held by the other person's terminal device 10 (step S104). At this time, when exchanging models with each other, the exchanging unit 36 may exchange not all of the models but a part of the models.

Next, the determination unit 37 of the terminal device 10 uses the data to compare and examine the inference accuracy of the current model and another person's model, and determines their superiority (step S105).

Subsequently, the determination unit 37 of the terminal device 10 determines whether or not another person's model is superior as a result of the comparative study (step S106).

Subsequently, if the other person's model is superior as a result of the comparative study (step S106: Yes), the updating unit 38 of the terminal device 10 updates its own model to the other person's model (step S107). .

Furthermore, if the current model is superior as a result of the comparative study (step S106: No), the updating unit 38 of the terminal device 10 continues the current model (step S108).

Note that the updating unit 38 of the terminal device 10 may extract good parts of the current model and another person's model as a result of comparative study and assemble the model.

Further, when the local model (local model) of the terminal device 10 is updated, the transmitting unit 31 of the terminal device 10 transmits information regarding the updated model (updated model) and the update date and time via the communication unit 11. The information providing device 100 (server side) may be notified. At this time, the transmitter 31 may also notify the information providing device 100 (server side) of information regarding the location (region, etc.) at the time the model was updated.

[6. Modified example]
The terminal device 10 and the information providing device 100 described above may be implemented in various different forms other than the above embodiments. Therefore, a modification of the embodiment will be described below.

In the above embodiment, part or all of the processing executed by the information providing device 100 may actually be executed by the terminal device 10. For example, the process may be completed stand-alone (by the terminal device 10 alone). In this case, it is assumed that the terminal device 10 has the functions of the information providing device 100 in the above embodiment. Furthermore, in the embodiment described above, since the terminal device 10 cooperates with the information providing device 100, it appears to the user U that the terminal device 10 also executes the processing of the information providing device 100. That is, from another perspective, it can be said that the terminal device 10 includes the information providing device 100.

In the above embodiment, the information providing device 100 (server side) employs federated learning, and the shared model (core model) may be provided. Then, the terminal device 10 creates a pattern by performing on-device machine learning using the raw data (and sensor data) and result information as learning data based on the shared model, and uses the pattern to create a pattern using the raw data (and sensor data) and result information as learning data. The inference may be performed using sensor data) as input data. Further, the terminal device 10 may notify the information providing device 100 (server side) of the updated difference parameters of the model using a federated learning mechanism. Thereby, the information providing device 100 (server side) can know the update of the model on the terminal device 10 side.

Furthermore, in the above embodiment, when exchanging/updating a part of the model, the terminal device 10 may exchange/update the model with higher accuracy. Furthermore, the terminal device 10 may divide the model into partial models including a plurality of intermediate layers. At this time, the terminal device 10 may divide one model into a plurality of partial models for each function. For example, the terminal device 10 divides the current model into a plurality of partial models for each function, and when passing each other with another company's terminal device 10, exchanges each partial model with the other company's terminal device 10 based on each other's model. Alternatively, after exchanging models with the terminal device 10 of another company, the terminal device 10 divides the current model and the other party's model into a plurality of partial models for each function, and creates a plurality of partial models with each partial model replaced. A model is generated, and the model with the highest accuracy among the multiple generated models is adopted as the updated model.

Furthermore, in the above embodiment, the terminal device 10 may be a smartphone or the like that has a highly functional camera function using on-device AI (Artificial Intelligence). Further, the terminal device 10 may be a robot, a self-driving car, a drone, etc. equipped with on-device AI.

[7. effect〕
As described above, the information processing device (terminal device 10) according to the present application includes a receiving unit 32 that receives a model distributed from the server side (information providing device 100), and an obtaining unit 34 that obtains data used for learning. , a learning unit 35 that performs on-device machine learning of a model using data, and a learning unit 35 that exchanges each other's models with another person's information processing device, and the other person's model that has undergone machine learning on the other person's information processing device. an exchange unit 36 that acquires the current model and another person's model using data, and a determination unit 37 that uses data to determine the superiority or inferiority of the current model and another person's model; It includes an updating unit 38 that updates the current model to a model with higher inference accuracy between the current model and another person's model.

Further, when exchanging models with each other, the exchanging unit 36 exchanges not all of the models but a part of the models.

Furthermore, when updating its own model, the updating unit 38 updates a part of the model instead of the entire model.

Furthermore, when updating its own model, the updating unit 38 assembles the model using the current model and another person's model.

Furthermore, the exchange unit 36 exchanges models with each other when passing each other's information processing apparatus.

Furthermore, the exchange unit 36 exchanges models with other information processing devices via the network without going through the server side.

Further, the exchange unit 36 exchanges models with each other when other information processing apparatuses having different models are in the same context.

Further, the current model and the other person's model are models distributed from the server side for the same purpose, but have different patterns.

The determination unit 37 conducts a model battle in which the current model is pitted against another person's model, and analyzes the results of the model battle to obtain a unique context and perspective for each model.

By using any one or a combination of the above-described processes, the information processing apparatus according to the present application can share a model on the user side, perform evolutionary calculations, and update the model.

[8. Hardware configuration]
Further, the terminal device 10 and the information providing device 100 according to the embodiments described above are realized by, for example, a computer 1000 having a configuration as shown in FIG. The information providing apparatus 100 will be described below as an example. FIG. 9 is a diagram showing an example of the hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output I/F (Interface) 1060, an input I/F 1070, and a network I/F 1080 are connected to a bus. 1090.

The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and performs various processes. The arithmetic device 1030 is realized by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like.

The primary storage device 1040 is a memory device such as a RAM (Random Access Memory) that temporarily stores data used by the calculation device 1030 for various calculations. Further, the secondary storage device 1050 is a storage device in which data used by the calculation device 1030 for various calculations and various databases are registered, and includes a ROM (Read Only Memory), an HDD (Hard Disk Drive), and an SSD (Solid Disk Drive). This is realized using flash memory, etc. The secondary storage device 1050 may be a built-in storage or an external storage. Further, the secondary storage device 1050 may be a removable storage medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) memory card. Further, the secondary storage device 1050 may be a cloud storage (online storage), a NAS (Network Attached Storage), a file server, or the like.

The output I/F 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various information such as a display, a projector, and a printer. (Digital Visual Interface) and HDMI (registered trademark) (High Definition Multimedia Interface). Further, the input I/F 1070 is an interface for receiving information from various input devices 1020 such as a mouse, keyboard, keypad, button, scanner, etc., and is realized by, for example, a USB or the like.

Further, the output I/F 1060 and the input I/F 1070 may be wirelessly connected to the output device 1010 and the input device 1020, respectively. That is, output device 1010 and input device 1020 may be wireless devices.

Moreover, the output device 1010 and the input device 1020 may be integrated like a touch panel. In this case, the output I/F 1060 and the input I/F 1070 may also be integrated as an input/output I/F.

Note that the input device 1020 is, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), or a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like.

Network I/F 1080 receives data from other devices via network N and sends it to computing device 1030, and also sends data generated by computing device 1030 to other devices via network N.

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

For example, when the computer 1000 functions as the information providing device 100, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the primary storage device 1040. Further, the arithmetic device 1030 of the computer 1000 may load a program obtained from another device via the network I/F 1080 onto the primary storage device 1040, and execute the loaded program. Further, the arithmetic device 1030 of the computer 1000 may cooperate with other devices via the network I/F 1080, and may call and use program functions, data, etc. from other programs of other devices.

[9. others〕
Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. Furthermore, the above-mentioned components include those that can be easily assumed by those skilled in the art, those that are substantially the same, and those that are in a so-called equivalent range. Furthermore, the aforementioned components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the constituent elements can be made without departing from the gist of the embodiments described above.

Further, 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 this 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.

Further, 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, the information providing apparatus 100 described above may be realized by a plurality of server computers, and depending on the function, it may be realized by calling an external platform etc. using an API (Application Programming Interface), network computing, etc. can be changed flexibly.

Furthermore, the above-described embodiments and modifications can be combined as appropriate within a range that does not conflict with the processing contents.

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.

1 Information processing system 10 Terminal device 11 Communication unit 14 Positioning unit 20 Sensor unit 30 Control unit 31 Transmission unit 32 Receiving unit 33 Processing unit 34 Acquisition unit 35 Learning unit 36 Exchange unit 37 Judgment unit 38 Update unit 100 Information providing device 110 Communication unit 120 Storage unit 121 User information database 122 History information database 123 Model information database 130 Control unit 131 Collection unit 132 Estimation unit 133 Providing unit

Claims (11)

An information processing device used as a terminal device carried by a user,
a receiving unit that receives the model distributed from the server side;
an acquisition unit that acquires data measured or recorded by the functions of the terminal device as data used for learning;
When the data is acquired, based on predetermined rules such as data content or context, it is determined which model should be used for machine learning, the local model on the terminal side or the global model on the server side, and the terminal side a learning unit that performs on-device machine learning of the model using the data when it is determined that machine learning is to be performed on the local model;
In order to match and unify the models while determining the superiority and inferiority of the local models of each terminal device, models were exchanged with other people's information processing devices, and machine learning was performed on the other people's information processing devices. an exchange section that obtains other people's models;
a determination unit that pits the models against each other when exchanging local models between terminal devices, and uses the data to compare and examine the accuracy of inference between the current model and the other person's model to determine their superiority;
and an updating unit that updates the own model to a model that has won the battle by updating its own model to a model with higher inference accuracy between the current model and the other person's model as a result of the comparative study. Characteristic information processing device. The information processing apparatus according to claim 1, wherein the exchange unit exchanges not all of the models but a part of the models when exchanging models with each other. The information processing device according to claim 1 or 2, wherein the updating unit updates a part of the model instead of the entire model when updating its own model. The updating unit assembles a model using the current model and the other person's model when updating its own model. Information processing device. The information processing device according to any one of claims 1 to 4, wherein the exchange unit exchanges models with the other information processing device when passing each other. According to any one of claims 1 to 5, the exchange unit exchanges models with the other person's information processing device via a network without going through the server side. information processing equipment. The information according to any one of claims 1 to 6, wherein the exchange unit exchanges each other's models when the other information processing devices having different models are in the same context. Processing equipment. Any one of claims 1 to 7, wherein the current model and the other person's model are models distributed from the server side and have the same purpose, but have different patterns. The information processing device described in . The determining unit performs a model battle in which the current model and the other person's model are pitted against each other, and analyzes the results of the model battle to obtain a unique context and perspective for each model. The information processing device according to any one of 1 to 8. An information processing method executed by an information processing device used as a terminal device carried by a user, the method comprising:
a receiving step of receiving the model distributed from the server side;
an acquisition step of acquiring data measured or recorded by the functions of the terminal device as data used for learning;
When the data is acquired, based on predetermined rules such as data content or context, it is determined which model to perform machine learning, the local model on the terminal side or the global model on the server side, and the terminal side a learning step of performing on-device machine learning of the model using the data when it is determined that machine learning is to be performed on the local model;
In order to match and unify the models while determining the superiority and inferiority of the local models of each terminal device, models were exchanged with other people's information processing equipment, and machine learning was performed on the other people's information processing equipment. an exchange step of acquiring another person's model;
a determination step of pitting the models against each other when exchanging local models between terminal devices, and comparing and examining the inference accuracy of the current model and the other person's model using the data to determine their superiority;
As a result of the comparative study, updating the own model to a model with higher inference accuracy between the current model and the other person's model , thereby updating the model to the model that won the battle. Characteristic information processing method. a reception procedure for receiving a model distributed from the server side;
an acquisition procedure for acquiring data measured or recorded by a function of a terminal device as data used for learning;
When the data is acquired, based on predetermined rules such as data content or context, it is determined which model to perform machine learning, the local model on the terminal side or the global model on the server side, and the terminal side a learning procedure of performing on-device machine learning of the model using the data when it is determined that machine learning is to be performed on the local model;
In order to match and unify the models while determining the superiority and inferiority of the local models of each terminal device, we exchange models with other terminal devices and perform machine learning on the other terminal device . Exchange procedure to obtain the model of
a determination procedure of pitting the models against each other when exchanging local models between terminal devices, and using the data to compare and examine the inference accuracy of the current model and the other person's model to determine their superiority;
As a result of the comparative study, the user updates his/her own model to a model with higher inference accuracy between the current model and the other person's model , thereby updating the model to the model that won the battle. An information processing program that is executed by a computer used as a portable terminal device .

Images