WO2018100679A1 - Computer system, teaching data trading method, and program - Google Patents

Abstract

[Problem] The purpose of the present invention is to provide a computer system, a teaching data trading method, and a program that enable teaching data used in machine learning to be traded. [Solution] A computer system for trading teaching data used in machine learning receives from a lister an input of teaching data to be listed, receives from a purchaser a search for teaching data the purchaser wishes to purchase, and receives from the purchaser a purchase of the preferred teaching data. In addition, the computer system receives a search that is based on any among the data type, data volume, data content, or programming language of the teaching data the purchaser wishes to purchase or based on a combination of a plurality of the same. Additionally, the computer system carries out machine learning using the teaching data for which the purchase was received and provides the results of the machine learning to the purchaser. An input of the listing price for the listed teaching data is received from the lister. The compatibility between the sensor device used by the purchaser and the teaching data the purchaser wishes to purchase is presented. A sensor device having excellent compatibility with the purchased teaching data is presented.

Description

Computer system, teacher data transaction method and program

The present invention relates to a computer system, a teacher data trading method, and a program for trading teacher data used for machine learning.

In recent years, the use of artificial intelligence has been promoted in various fields. In such artificial intelligence, machine learning is performed based on teacher data which is correct answer data for learning, and newly acquired information is processed based on the result of machine learning. In machine learning, creating appropriate teacher data can improve the calculation efficiency of the system, but creating such teacher data requires specialized knowledge and takes time and effort. .

As a system for creating such teacher data used for machine learning, post information on SNS (social networking service) is collected, and the collected post information is classified based on a specific text portion, and the result of the classification is obtained. Based on this, a configuration for creating teacher data is disclosed (see Patent Document 1).

JP 2016-162257 A

However, in the configuration of Patent Document 1, when creating teacher data used for machine learning, a system builder needs specialized knowledge to specify a specific text portion for classifying collected post information. Met. Therefore, it is difficult for an actual system user to acquire a sufficient amount of appropriate teacher data due to the small amount of distribution, and the teacher data creator and the user acquire such teacher data. It was difficult to trade.

An object of the present invention is to provide a computer system, a teacher data trading method, and a program capable of trading teacher data used for machine learning.

The present invention provides the following solutions.

The present invention is a computer system for trading teacher data used for machine learning,
An exhibitor that accepts input of teacher data to exhibit from the seller;
A search means for accepting search for teacher data to be purchased from the purchaser,
Purchase means for accepting purchase of favorite teacher data from the purchaser;
A computer system is provided.

According to the present invention, a computer system for trading teacher data used for machine learning accepts input of teacher data to be sent from an exhibitor, accepts a search for teacher data to be purchased from a purchaser, and from the purchaser, Accept purchases of teacher data you like.

The present invention is a computer system category, but in other categories such as a teacher data transaction method and program, the same actions and effects according to the category are exhibited.

According to the present invention, it is possible to provide a computer system, a teacher data transaction method, and a program capable of trading teacher data used for machine learning.

FIG. 1 is a diagram showing an overview of the teacher data transaction system 1. FIG. 2 is an overall configuration diagram of the teacher data transaction system 1. FIG. 3 is a functional block diagram of the computer 10, the exhibitor terminal 100, and the purchaser terminal 200. FIG. 4 is a flowchart showing teacher data exhibition processing executed by the computer 10 and the exhibitor terminal 100. FIG. 5 is a flowchart showing sensor device registration processing executed by the computer 10 and the purchaser terminal 200. FIG. 6 is a flowchart showing teacher data search processing executed by the computer 10 and the purchaser terminal 200. FIG. 7 is a flowchart showing sensor device introduction processing executed by the computer 10 and the purchaser terminal 200. FIG. 8 is a flowchart showing machine learning processing executed by the computer 10 and the purchaser terminal 200. FIG. 9 is a diagram illustrating an example of an exhibition screen. FIG. 10 is a diagram illustrating an example of a teacher data database. FIG. 11 is a diagram illustrating an example of a personal information input screen. FIG. 12 is a diagram illustrating an example of a search screen. FIG. 13 is a diagram illustrating an example of a purchase screen. FIG. 14 is a diagram illustrating an example of the compatibility introduction screen.

Hereinafter, the best mode for carrying out the present invention will be described with reference to the drawings. This is merely an example, and the technical scope of the present invention is not limited to this.

[Outline of Teacher Data Trading System 1]
An outline of a preferred embodiment of the present invention will be described with reference to FIG. FIG. 1 is a diagram for explaining an overview of a teacher data trading system 1 which is a preferred embodiment of the present invention. The teacher data transaction system 1 includes a computer 10, an exhibitor terminal 100, and a purchaser terminal 200, and is a computer system that trades teacher data used for machine learning.

In FIG. 1, the computer 10, the exhibitor terminal 100, and the purchaser terminal 200 are not limited to one and may be plural. Further, the computer 10, the exhibitor terminal 100, and the purchaser terminal 200 are not limited to actual devices, but may be virtual devices. Each process described below may be realized by any one or a combination of the computer 10, the exhibitor terminal 100, and the purchaser terminal 200.

The computer 10 is a computing device connected to the exhibitor terminal 100 and the purchaser terminal 200 so that data communication is possible.

The exhibitor terminal 100 is a terminal device that is connected to the computer 10 so as to be capable of data communication and is owned by an exhibitor who exhibits teacher data. The exhibitor terminal 100 is, for example, an electronic product such as a netbook terminal, a slate terminal, an electronic book terminal, a portable music player, a smart glass, a head-mounted display, etc. in addition to a mobile phone, a portable information terminal, a tablet terminal, a personal computer. Wearable terminals and other items.

The purchaser terminal 200 is a terminal device that is connected to the computer 10 so as to be capable of data communication and is owned by a purchaser who purchases teacher data. The purchaser terminal 200 is, for example, an electrical appliance similar to the exhibitor terminal 100, a wearable terminal, or other items.

First, the exhibitor terminal 100 receives input of teacher data to be exhibited from the exhibitor (step S01). The exhibitor terminal 100 accepts, for example, input of a data name, data type, data volume, data content, programming language, and exhibition price as input of teacher data.

The exhibitor terminal 100 transmits the received teacher data to the computer 10 (step S02).

The computer 10 receives teacher data. The computer 10 stores the received teacher data (step S03).

The purchaser terminal 200 accepts a search for teacher data to be purchased from the purchaser (step S04). The purchaser terminal 200 accepts input of one or a plurality of combinations of data type, data volume, data content, programming language of teacher data to be purchased.

The purchaser terminal 200 transmits the received search data to the computer 10 (step S05).

The computer 10 receives the search data. The computer 10 selects teacher data corresponding to the search data based on the received search data (step S06).

In addition, the computer 10 acquires information related to the sensor device used by the purchaser in advance, determines the compatibility between the information related to the sensor device and the selected teacher data, and sends the determined compatibility to the purchaser terminal 200. By providing, the compatibility between the sensor device used by the purchaser and the teacher data that the purchaser wants to purchase may be introduced.

The computer 10 transmits information on the selected teacher data to the purchaser terminal 200 (step S07).

The purchaser terminal 200 receives information on teacher data. The purchaser terminal 200 receives purchase of favorite teacher data from the purchaser (step S08). The purchaser terminal 200 accepts information necessary for settlement such as the purchaser's name and address and a credit card in advance or this time, and sends information relating to teacher data to be purchased and information necessary for settlement to the computer 10. Transmit (step S09).

The computer 10 receives information regarding teacher data that the purchaser wants to purchase and information necessary for payment, and executes payment processing (step S10).

Note that the computer 10 may provide the purchaser by performing machine learning using the teacher data accepted for purchase, and transmitting the result of the machine learning to the purchaser terminal 200. Further, the computer 10 may charge the purchaser for the amount of machine learning performed.

The above is the outline of the teacher data transaction system 1.

[System Configuration of Teacher Data Trading System 1]
Based on FIG. 2, the system configuration | structure of the teacher data transaction system 1 which is suitable embodiment of this invention is demonstrated. FIG. 2 is a diagram showing a system configuration of the teacher data transaction system 1 which is a preferred embodiment of the present invention. The teacher data transaction system 1 is composed of a computer 10, an exhibitor terminal 100, a purchaser terminal 200, and a public line network (Internet network, third and fourth generation communication network, etc.) 5, and transmits teacher data used for machine learning. A computer system for trading.

In FIG. 2, the number of computers 10, exhibitor terminals 100, and purchaser terminals 200 is not limited to one and can be changed as appropriate. Further, the computer 10, the exhibitor terminal 100, and the purchaser terminal 200 are not limited to actual devices, but may be virtual devices. Moreover, each process mentioned later may be implement | achieved by the computer 10, the exhibitor terminal 100, the purchaser terminal 200, or the combination of several.

The computer 10 is the above-described computing device having the functions described later.

The exhibitor terminal 100 is the above-described terminal device having the functions described later.

The purchaser terminal 200 is the above-described terminal device having the functions described below.

[Description of each function]
Based on FIG. 3, the function of the teacher data transaction system 1 which is a preferred embodiment of the present invention will be described. FIG. 3 is a functional block diagram of the computer 10, the exhibitor terminal 100, and the purchaser terminal 200.

The computer 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like as the control unit 11, and can communicate with other devices (cameras and sensors) as the communication unit 12. For example, a device compatible with WiFi (Wireless Fidelity) compliant with IEEE802.11. The computer 10 also includes a data storage unit such as a hard disk, a semiconductor memory, a recording medium, or a memory card as the storage unit 13. The storage unit 13 stores various databases described later.

In the computer 10, when the control unit 11 reads a predetermined program, the exhibition data reception module 20, the purchaser data reception module 21, the search data reception module 22, and the search result data transmission module 23 cooperate with the communication unit 12. The purchase instruction receiving module 24, the settlement module 25, the sensor device data acquisition module 26, the compatibility introduction notification transmission module 27, and the learning result data transmission module 28 are realized. In the computer 10, the control unit 11 reads a predetermined program, thereby realizing a storage module 30, a teacher data selection module 31, a compatibility determination module 32, and a machine learning module 33 in cooperation with the storage unit 13.

Like the computer 10, the exhibitor terminal 100 includes a CPU, RAM, ROM, and the like as the control unit 110, and a device for enabling communication with other devices as the communication unit 120. The exhibitor terminal 100 also includes, as the input / output unit 140, a display unit that outputs and displays data and images controlled by the control unit 110, a touch panel that accepts input, a keyboard, an input unit such as a mouse, and the like.

In the exhibitor terminal 100, when the control unit 110 reads a predetermined program, the exhibition data transmission module 150 is realized in cooperation with the communication unit 120. Further, in the exhibitor terminal 100, the exhibit module 160 is realized in cooperation with the input / output unit 140 by the control unit 110 reading a predetermined program.

As with the exhibitor terminal 100, the purchaser terminal 200 includes a CPU, RAM, ROM, and the like as the control unit 210, a device for enabling communication with other devices as the communication unit 220, and an input / output unit. 240 includes a display unit, an input unit, and the like.

In the purchaser terminal 200, when the control unit 210 reads a predetermined program, in cooperation with the communication unit 220, the purchaser data transmission module 250, the search data transmission module 251, the search result data reception module 252, and the purchase instruction transmission A module 253, a compatibility introduction notification receiving module 254, and a learning result data receiving module 255 are realized. Further, in the purchaser terminal 200, the control unit 210 reads a predetermined program, so that the sensor device input module 260, the purchaser data input module 261, the search module 262, and the purchase module 263 cooperate with the input / output unit 240. The compatibility display module 264 and the learning result display module 265 are realized.

[Teacher data exhibition process]
Based on FIG. 4, the teacher data exhibition process which the teacher data transaction system 1 performs is demonstrated. FIG. 4 is a diagram showing a flowchart of teacher data exhibition processing executed by the computer 10 and the exhibitor terminal 100. The processing executed by the modules of each device described above will be described together with this processing.

The exhibition module 160 receives input of teacher data to be exhibited from the exhibitor (step S20). In step S20, the exhibition module 160 displays a teacher data exhibition screen by launching a dedicated application, and accepts input of various types of teacher data on the exhibition screen. The exhibition module 160 accepts input of data name, data type, data volume, data content, programming language, and exhibition price as various types of teacher data.

The data name is an identifier indicating the name of the teacher data. The data names are, for example, “teacher data 1”, “teacher data 2”,. The data type is an identifier indicating the type of teacher data. The data type includes, for example, an image captured by an imaging device, “image data” indicating an image acquired from the public network 5, etc., temperature, wind power, etc. where a sensor device such as a thermometer or anemometer is installed. Sound data collected by the sound collection device, such as "temperature data" and "wind power data", which are the data obtained as a result of acquiring environmental data, and artificial voice generated by software, etc. 5 is “voice data” indicating the voice and the like acquired from 5. The data volume is an identifier indicating the quantity of the teacher data and the usage amount of the storage area. For example, if the data volume is image data, “1000 images”, if it is temperature data, “temperature 3 months”, if it is sound data, “sound 500 people”, if it is wind data “For 2 years of wind power”. This data volume may represent the size of information as a numerical value. The data content is an identifier indicating the content of the teacher data. For example, when the data content is image data, the content of the subject included in the image data (for example, names such as “adult” and “child”, sex, age group, etc.) and the quantity (for example, “600 images”). ”,“ 400 ”, etc.), and the location of the sensor data (for example,“ Minato-ku Coast 1-chome ”,“ Nichinan City Nichinan 3-chome ”) , Latitude / longitude, GPS coordinates, etc.) and audio data, the contents of the audio data (for example, the race, age, occupation, address, etc.). The programming language is an identifier indicating a formal language describing the teacher data. Examples of the programming language include “R”, “Python”, “Scala”, “Julia”, and the like. The exhibition price is a sales price set by the exhibitor in the teacher data. The exhibition price is, for example, “10000 yen”, “5000 yen”, “30000 yen”, “15000 yen”, or the like.

The exhibition screen displayed by the exhibition module 160 will be described with reference to FIG. FIG. 9 is a diagram illustrating an example of an exhibition screen. In FIG. 9, the exhibition module 160 includes a name input area 310, a type input area 320, a volume input area 330, a content input area 340, a language input area 350, a price input area 360, a transmission icon 370, and an end icon as an exhibition screen 300. 380 is displayed. The exhibition module 160 accepts input of numbers, characters, symbols, and the like to each area by displaying a virtual keyboard or the like based on a tap operation or a touch operation from the exhibitor to each area.

The name input area 310 is an area for inputting the data name of the teacher data that the exhibitor wants to exhibit. In FIG. 9, the input of “teacher data 1” is accepted. The type input area 320 is an area for inputting the data type of the teacher data. In FIG. 9, the input of “image data” is accepted. The volume input area 330 is an area for inputting the data volume of the teacher data. In FIG. 9, the input of “1000 images” is accepted. The content input area 340 is an area for inputting the data content of the teacher data. In FIG. 9, the input of “600 adults, 400 children” is accepted. The language input area 350 is an area for inputting a programming language of the teacher data. In FIG. 9, the input of “R” is accepted. The price input area 360 is an area for inputting the exhibition price of the teacher data. In FIG. 9, the input of “10000 yen” is accepted. The transmission icon 370 receives input from the exhibitor, and the exhibitor terminal 100 transmits the teacher data input to the computer 10. The end icon 380 receives input from the exhibitor, and the exhibitor terminal 100 ends the exhibit screen.

In addition, the exhibition module 160 may accept input of all the above-described areas, or may accept input of any one or a plurality of combinations.

The exhibition module 160 determines whether or not input of teacher data to be exhibited has been completed (step S21). In step S21, the exhibition module 160 makes a determination based on whether or not the input of the transmission icon 370 described above has been accepted. In step S21, if the exhibition module 160 determines that the transmission has not been completed (NO in step S21), that is, if the input of the transmission icon 370 has not been received, this processing is repeated until the input is received. In addition, when receiving an input of the end icon 380, the exhibition module 160 ends the present process without executing the process described later.

On the other hand, if it is determined in step S21 that the exhibition module 160 has been completed (YES in step S21), that is, if the input of the transmission icon 370 is accepted, the exhibition data transmission module 150 receives the received teacher data and the exhibitor. Exhibit data including an identifier that can uniquely identify the exhibitor, such as the manufacturing number, device number, IP address, MAC address, etc. of the terminal 100 and the name of the owner of the exhibitor terminal 100 is transmitted to the computer 10 ( Step S22).

The exhibition data receiving module 20 receives the exhibition data. The storage module 30 stores the received exhibition data as a teacher data database (step S23).

[Teacher data database]
The teacher data database stored in the storage module 30 will be described with reference to FIG. FIG. 10 is a diagram illustrating an example of a teacher data database. In FIG. 10, the storage module 30 stores the seller name, the teacher data name, the data type, the data volume, the data content, the programming language, and the exhibition price in association with each other based on the exhibition data. . The exhibitor name is the name of the exhibitor in the teacher data. The teacher data name, data type, data volume, data content, programming language, and exhibition price are the same as those described above.

The above is the teacher data listing process.

[Sensor device registration process]
Based on FIG. 5, the sensor apparatus registration process which the teacher data transaction system 1 performs is demonstrated. FIG. 5 is a flowchart of sensor device registration processing executed by the computer 10 and the purchaser terminal 200. The processing executed by the modules of each device described above will be described together with this processing.

The sensor device input module 260 receives an input of a sensor device (for example, a temperature sensor, a wind sensor, a humidity sensor, a sunshine sensor, an imaging device, a sound collecting device, etc.) used by the purchaser (step S30). In step S30, the sensor device input module 260 receives an input of a sensor device identifier that can identify the sensor device such as the name, model, and manufacturing number of the sensor device.

The purchaser data input module 261 accepts input of personal information such as the purchaser's name, age, occupation, address, and place of use (step S31). In step S31, the purchaser data input module 261 may acquire a terminal identifier unique to the terminal such as a manufacturing number, a telephone number, an IP address, and a MAC address of the purchaser terminal 200 as personal information. The purchaser data input module 261 displays a personal information input screen for inputting personal information by launching a dedicated application, and accepts input of personal information on the personal information input screen. The purchaser data input module 261 accepts input of personal information such as name, age, occupation, address, place of use, and purpose of use. When the purchaser possesses a plurality of sensor devices, the purchaser inputs each location where the sensor devices are installed.

The personal information that the purchaser data input module 261 accepts input will be described with reference to FIG. FIG. 11 is a diagram illustrating an example of a personal information input screen. The purchaser data input module 261 includes, as the personal information input screen 400, a name input area 410, an age input area 420, an occupation input area 430, an address input area 440, a use place input area 450, a use purpose input area 460, and a transmission icon 470. The end icon 480 is displayed. The purchaser data input module 261 accepts inputs of mathematics, characters, symbols, and the like to each area by displaying a virtual keyboard or the like based on a tap operation or a touch operation from the purchaser to each area.

The name input area 410 is an area for inputting a purchaser's name. In FIG. 11, the input of “Taro Tanaka” is accepted. The age input area 420 is an area for inputting the age of the purchaser. In FIG. 11, the input of “50 years old” is accepted. The occupation input area 430 is an area for inputting the occupation of the purchaser. In FIG. 11, the input of “farmer” is accepted. The address input area 440 is an area for inputting a purchaser's address. In FIG. 11, the input of “Nichinan City Nichinan, Maniwa 2-chome” is accepted. The use place input area 450 is an area where the purchaser inputs a place where the sensor device is used. In FIG. 11, an input of “Nichinan City Maniwa 3-chome, Miyazaki Prefecture” is accepted. The usage purpose input area 460 is an area where the purchaser inputs the purpose of using the teacher data. In FIG. 11, the input of “agriculture” is accepted. The transmission icon 470 receives input from the purchaser, and the purchaser terminal 200 transmits personal information input to the computer 10. The end icon 480 receives input from the purchaser, and the purchaser terminal 200 ends the personal information input screen.

Note that the purchaser data input module 261 may accept input of all the areas described above, or may accept input of any one or a plurality of combinations. Further, the purchaser data is not limited to the above-described example, and other data input may be accepted.

The purchaser data input module 261 determines whether or not the input of personal information has been completed (step S32). In step S32, the purchaser data input module 261 makes a determination based on whether or not the input of the transmission icon 470 described above has been accepted. If the purchaser data input module 261 determines in step S32 that the purchase has not been completed (NO in step S32), that is, if the input of the transmission icon 470 is not received, this process is repeated until the input is received. When the purchaser data input module 261 receives an input of the end icon 480, the purchaser data input module 261 ends this processing without executing the processing described later.

On the other hand, if the purchaser data input module 261 determines in step S32 that the purchase has been completed (YES in step S32), that is, if the input of the transmission icon 470 has been received, the purchaser data transmission module 250 performs the process of step S30. The purchaser data including the sensor device used by the purchaser accepted by the purchaser and the personal information of the purchaser accepted by the process of step S31 is transmitted to the computer 10 (step S33).

The purchaser data receiving module 21 receives purchaser data. The storage module 30 stores the received purchaser data (step S34). In step S <b> 34, the storage module 30 may store at least a purchaser's name, a sensor device owned by the purchaser, and a use location of the sensor device in association with each other.

The above is the sensor device registration process.

[Teacher data search processing]
Based on FIG. 6, the teacher data search process which the teacher data transaction system 1 performs is demonstrated. FIG. 6 is a diagram illustrating a flowchart of teacher data search processing executed by the computer 10 and the purchaser terminal 200. The processing executed by the modules of each device described above will be described together with this processing.

The search module 262 accepts a search for teacher data to be purchased from the purchaser (step S40). In step S40, the search module 262 displays a teacher data search screen by launching a dedicated application, and accepts input of search data related to teacher data to be purchased on the search screen. For example, the search module 262 accepts input of any one or a combination of a data name, a data type, a data volume, data content, a programming language, and an exhibition price as a search content.

Based on FIG. 12, the search screen displayed by the search module 262 will be described. FIG. 12 is a diagram illustrating an example of a search screen. In FIG. 12, the search module 262 includes a name input area 510, a type input area 520, a volume input area 530, a content input area 540, a language input area 550, a price input area 560, a transmission icon 570, and an end icon as a search screen 500. 580 is displayed. The search module 262 accepts input of numbers, characters, symbols, and the like to each area by displaying a virtual keyboard or the like based on a tap operation or a touch operation from the exhibitor to each area.

The name input area 510 is an area for inputting a data name of teacher data that the purchaser wants to search. In FIG. 12, the input is not accepted. The type input area 520 is an area for inputting the data type of the teacher data. In FIG. 12, the input of “wind power data” is accepted. The volume input area 530 is an area for inputting the data volume of the teacher data. In FIG. 12, the input is not accepted. The content input area 540 is an area for inputting the data content of the teacher data. In FIG. 12, the input is not accepted. The language input area 550 is an area for inputting a programming language of the teacher data. In FIG. 12, the input is not accepted. The price input area 560 is an area for inputting the exhibition price of the teacher data. In FIG. 12, the input is not accepted. The transmission icon 570 receives input from the purchaser, and the purchaser terminal 200 transmits the search data input to the computer 10. The end icon 580 accepts input from the purchaser, and the purchaser terminal 200 ends the search screen.

Note that the search module 262 may accept input of all the above-described areas, or may accept input of any one or a plurality of combinations. Moreover, you may receive the input of data other than the example mentioned above.

The search module 262 determines whether or not input of search data has been completed (step S41). In step S41, the search module 262 makes a determination based on whether or not the input of the transmission icon 570 described above has been received. In step S41, when the search module 262 determines that the transmission has not been completed (NO in step S41), that is, when the input of the transmission icon 570 is not received, the processing is repeated until the input is received. When the search module 262 receives an input of the end icon 580, the search module 262 ends the process without executing the process described later.

On the other hand, if the search module 262 determines in step S41 that the search is completed (YES in step S41), that is, if the input of the transmission icon 570 is received, the search data transmission module 251 sends the received search data to the computer 10. (Step S42). In step S <b> 42, the search data transmission module 251 transmits the personal information (name, etc.) of the purchaser holding the purchaser terminal 200 and the sensor device identifier of the purchaser terminal 200 together with the search data.

The search data receiving module 22 receives search data. Based on the search data, the teacher data selection module 31 selects the teacher data corresponding to one or a combination of a data name, data type, data volume, data content, programming language, exhibition price included in the search data, A selection is made based on the teacher data database (step S43). In step S43, the teacher data selection module 31 selects one or a plurality of teacher data corresponding to the received search data. The teacher data selection module 31 simply selects one or a plurality of data based on the search data and the teacher data database when the data type of the search data does not matter where the image data or audio data is used. Select teacher data. In addition, when the data type of the search data is sensor data, the teacher data selection module 31 is based on the purpose and place of use included in the purchaser data, and the data content and data type stored in the teacher data database. To select one or a plurality of teacher data. This is because, for example, when sensor data at a place away from the place of use is used, there is a possibility that the data will not necessarily be appropriate teacher data because of a difference in climate and weather.

The compatibility determination module 32 determines compatibility with the sensor device owned by the purchaser based on the selected teacher data and the purchaser data of the purchaser stored in advance, and extracts teacher data with good compatibility (step) S44). In step S44, compatibility refers to whether or not the sensor device held by the purchaser corresponds to the teacher data that the purchaser wants to purchase, whether or not the operating environment is satisfied, and whether or not it matches the purpose and location of use. Etc. The compatibility determination module 32 determines, for example, three-level evaluations such as very good compatibility, good compatibility, and poor compatibility. When compatibility is very good, it is judged as “、”, when compatibility is good, “◯”, when compatibility is bad, it is judged as “x” or the like.

Note that the compatibility evaluation is not limited to the above-described example, but may be determined using other symbols, character strings, or the like in the order of compatibility. Moreover, you may judge by another structure.

The search result data transmission module 23 transmits the extracted teacher data compatible with the extracted sensor device to the purchaser terminal 200 as search result data (step S45). In step S45, the search result data includes the teacher data and the compatibility between the teacher data and the sensor device.

The search result data receiving module 252 receives search result data. The purchase module 263 displays a purchase screen based on the received search result data (step S46). By the process of step S46, the purchaser terminal 200 displays the teacher data that is compatible with the sensor device held by the purchaser, so that the sensor device used by the purchaser and the teacher data that the purchaser wants to purchase are displayed. Compatibility can be introduced to the purchaser.

The purchase screen displayed by the purchase module 263 will be described with reference to FIG. FIG. 13 is a diagram illustrating an example of a purchase screen. In FIG. 13, the purchase module 263 includes, as a purchase screen 600, a name display area 610, a type display area 620, a volume display area 630, a content display area 640, a language display area 650, a price display area 660, a compatibility display area 670, purchase. An icon 680 and an end icon 690 are displayed.

The name display area 610 is an area for displaying the data name of the teacher data. In FIG. 13, “teacher data 4” is displayed. The type display area 620 is an area for displaying the data type of the teacher data. In FIG. 13, “wind power data” is displayed. The volume display area 630 is an area for displaying the data volume of teacher data. In FIG. 13, “2 years of wind power” is displayed. The content display area 640 is an area for displaying the data content of the teacher data. In FIG. 13, “Nichinan City Nichinan Obi 3 chome” is displayed. The language display area 650 is an area for displaying a programming language of teacher data. In FIG. 13, “Julia” is displayed. The price display area 660 is an area for displaying the exhibition price of the teacher data. In FIG. 13, “15000 yen” is displayed. The compatibility display area 670 is an area for displaying compatibility with the sensor device used by the purchaser. In FIG. 13, “◎” is displayed. The purchase icon 680 receives input from the purchaser, and the purchaser terminal 200 executes billing processing. The end icon 690 accepts input from the purchaser, and the purchaser terminal 200 ends the purchase screen.

Note that the purchase module 263 may display all of the above-described areas, or may display any one or a plurality of combinations. Moreover, you may display data other than the example mentioned above. When a plurality of teacher data exist, the plurality of teacher data may be displayed as one screen, or one teacher data may be displayed on each screen as a plurality of screens.

The purchase module 263 determines whether or not an input for purchasing the teacher data has been received (step S47). In step S47, the purchase module 263 determines based on whether or not the input of the purchase icon 680 described above has been received. In step S47, if the purchase module 263 determines that it has not been accepted (step S47: NO), that is, if the input of the purchase icon 680 has not been accepted, this process is repeated until the input is accepted. If the purchase module 263 receives an input of the end icon 690, the purchase module 263 ends this process without executing the process described later.

On the other hand, when the purchase module 263 determines in step S47 that the purchase has been received (YES in step S47), the purchase instruction transmission module 253 transmits a purchase instruction to purchase the teacher data to the computer 10 (step S48). In step S48, the purchase module 263 accepts input of settlement data, which is data necessary for settlement such as a credit card number and an account number of a financial institution, and transmits a purchase instruction together with the accepted settlement data. Note that the purchase module 263 may receive input of payment data in advance and transmit the payment data together with a purchase instruction.

The purchase instruction receiving module 24 receives a purchase instruction. The payment module 25 executes a payment process based on the purchase instruction (step S49). In step S49, the payment module 25 performs data communication with the computer of the financial institution or credit card company based on the payment data.

The storage module 30 stores the teacher data for which payment has been made and the purchaser data of the purchaser in association with each other (step S50). In step S50, the storage module 30 stores the teacher data, the purchaser's name and the sensor device owned by the teacher data in association with each other. The computer 10 associates the teacher data with the purchaser to make the teacher data purchased by the purchaser usable.

The above is the teacher data search process.

[Sensor equipment introduction process]
Based on FIG. 7, a sensor device introduction process executed by the teacher data transaction system 1 will be described. FIG. 7 is a diagram illustrating a flowchart of sensor device introduction processing executed by the computer 10 and the purchaser terminal 200. The processing executed by the modules of each device described above will be described together with this processing.

The sensor device data acquisition module 26 acquires sensor device data, which is data related to the sensor device, from a computer such as a manufacturer or distributor of the sensor device (not shown), an external database, or the like (step S60). In step S60, the sensor device data acquisition module 26 acquires sensor device data related to the teacher data for which payment was performed in step S49 described above. The sensor device data acquisition module 26 acquires related sensor device data based on the data type of the teacher data.

The compatibility determination module 32 determines compatibility based on the acquired sensor device data and teacher data (step S61). In step S61, compatibility refers to whether the teacher data purchased by the purchaser corresponds to the sensor device indicated by the acquired sensor device data, satisfies the operating environment, and matches the purpose of use and the place of use. Whether or not it is done. The compatibility determination module 32 determines, for example, three-level evaluations such as very good compatibility, good compatibility, and poor compatibility. When compatibility is very good, it is judged as “、”, when compatibility is good, “◯”, when compatibility is bad, it is judged as “x” or the like.

Note that the compatibility evaluation is not limited to the above-described example, but may be determined using other symbols, character strings, or the like in the order of compatibility. Moreover, you may judge by another structure.

The compatibility introduction notification transmission module 27 transmits the sensor device data determined to have good compatibility as a compatibility introduction notification to the purchaser terminal 200 that has purchased the teacher data (step S62). In step S <b> 62, the compatibility introduction notification transmission module 27 identifies the purchaser terminal 200 based on the purchaser data associated with the teacher data, and transmits the compatibility introduction notification to the identified purchaser terminal 200. .

The compatibility introduction notification receiving module 254 receives the compatibility introduction notification. The compatibility display module 264 displays a compatibility introduction screen based on the received compatibility introduction notification (step S63).

The compatibility introduction screen displayed by the compatibility display module 264 will be described with reference to FIG. FIG. 14 is a diagram illustrating an example of the compatibility introduction screen. In FIG. 14, the compatibility display module 264 displays an introduction sentence display area 710, a name display area 720, a compatibility display area 730, and an end icon 740 as the compatibility introduction screen 700.

The introductory text display area 710 is an area for displaying a notification that this screen is a screen for introducing a sensor device that is compatible with teacher data. In FIG. 14, “Other sensor devices having compatibility with the teacher data purchased this time are as follows” is displayed. The name display area 720 is an area for displaying the name of the sensor device. In FIG. 14, “sensor device A”, “sensor device B”, and “sensor device C” are displayed. The compatibility display area 730 is an area for displaying the compatibility between the teacher data and the sensor device. In FIG. 14, “◎”, “◎”, and “◯” are displayed. The end icon 740 accepts input from the purchaser, and the purchaser terminal 200 ends the compatibility introduction screen.

The compatibility display module 264 displays various information necessary for the purchase of the sensor device such as the name of the company selling the sensor device, the name of the sales office, the URL of the sales website, and the sales price in addition to the above-described areas. May be.

The compatibility display module 264 determines whether or not an input to end the compatibility introduction screen has been received (step S64). In step S64, the compatibility display module 264 makes a determination based on whether or not the input of the above-described end icon 740 has been received. If the compatibility display module 264 determines in step S64 that the compatibility icon is not received (NO in step S64), that is, if the input of the end icon 740 is not received, the present processing is repeated until the input is received.

On the other hand, if it is determined in step S64 that the compatibility display module 264 has received (YES in step S64), that is, if it is determined that the input of the end icon 740 has been received, this processing ends.

The above is the sensor device introduction process.

[Machine learning processing]
Based on FIG. 8, the machine learning process which the teacher data transaction system 1 performs is demonstrated. FIG. 8 is a diagram illustrating a flowchart of machine learning processing executed by the computer 10 and the purchaser terminal 200. The processing executed by the modules of each device described above will be described together with this processing.

The machine learning module 33 uses the teacher data purchased by the purchaser to perform machine learning (step S70). In step S70, the machine learning module 33 performs machine learning on the sensor data acquired by the sensor device based on the teacher data.

The settlement module 25 charges the purchaser for the amount of machine learning by the process of step S70 described above (step S71). In step S71, the payment module 25 executes billing processing based on the payment data used in the payment processing executed in the processing in step S49 described above.

The learning result data transmission module 28 transmits learning result data, which is a result of performing machine learning, to the purchaser terminal 200 (step S72). In step S <b> 72, the computer 10 provides the purchaser with the result of performing the machine learning by transmitting the learning result data to the purchaser terminal 200.

The learning result data receiving module 255 receives learning result data. The learning result display module 265 displays the result of the machine learning based on the learning result data (step S73).

The above is the machine learning process.

The means and functions described above are realized by a computer (including a CPU, an information processing apparatus, and various terminals) reading and executing a predetermined program. The program is provided, for example, in a form (SaaS: Software as a Service) provided from a computer via a network. The program is provided in a form recorded on a computer-readable recording medium such as a flexible disk, CD (CD-ROM, etc.), DVD (DVD-ROM, DVD-RAM, etc.). In this case, the computer reads the program from the recording medium, transfers it to the internal storage device or the external storage device, stores it, and executes it. The program may be recorded in advance in a storage device (recording medium) such as a magnetic disk, an optical disk, or a magneto-optical disk, and provided from the storage device to a computer via a communication line.

As mentioned above, although embodiment of this invention was described, this invention is not limited to these embodiment mentioned above. The effects described in the embodiments of the present invention are only the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. is not.

1 Teacher data transaction system, 10 computers, 100 exhibitor terminals, 200 purchaser terminals

Claims (12)

A computer system for trading teacher data used for machine learning,
An exhibitor that accepts input of teacher data to exhibit from the seller;
A search means for accepting search for teacher data to be purchased from the purchaser,
Purchase means for accepting purchase of favorite teacher data from the purchaser;
A computer system comprising: The search means accepts a search according to the data type of teacher data to be purchased.
The computer system according to claim 1. The search means accepts a search by a data volume of teacher data to be purchased.
The computer system according to claim 1. The search means accepts a search based on the data content of teacher data to be purchased.
The computer system according to claim 1. The search means accepts a search in a programming language for teacher data to be purchased.
The computer system according to claim 1. Opportunity learning means for performing the machine learning using the teacher data received for purchase;
Providing means for providing the purchaser with a result of performing the machine learning;
The computer system according to claim 1, comprising: Pay-as-you-go billing means for paying pay-as-you-go charges for the amount of machine learning performed by the machine learning means;
The computer system according to claim 6, comprising: An exhibition price means for receiving an input of an exhibition price of the teacher data to be exhibited from the seller;
The computer system according to claim 1, comprising: Compatibility introduction means for introducing compatibility between the sensor device used by the purchaser and the teacher data that the purchaser wants to purchase;
The computer system according to claim 1, comprising: Device introduction means for introducing a sensor device that is compatible with the purchased teacher data;
The computer system according to claim 1, comprising: A teacher data trading method for trading teacher data used for machine learning,
A step of accepting input of teacher data to be sent from the seller;
Receiving a search from the purchaser for the teacher data to be purchased,
Receiving a purchase of favorite teacher data from the purchaser;
A teacher data transaction method comprising: In a computer system that trades teacher data used for machine learning,
Receiving input of teacher data to be sent from the seller,
Accepting a search for the teacher data you want to purchase from the buyer,
Receiving a purchase of favorite teacher data from the purchaser;
A program for running

Images