Support system, information processing device, learning model generation method, support method, and program

Abstract

To support proposal for a position of environment that is comfortable for individuals when they start work.SOLUTION: A system comprises: a sensor 200 for measuring environmental information indicating an environment for each area where a seat is arranged; and an information processing apparatus 100 for acquiring personal identification information that identifies an individual and evaluation information that indicates an evaluation of the environment by the individual, performing machine learning on the area corresponding to the environmental information according to the evaluation information for each acquired personal identification information to generate a learning model, and inputting the personal identification information and the environmental information measured by the sensor 200 into the learning model to acquire area information that indicates the area from the learning model, and outputting the acquired area information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a support system, an information processing device, a learning model generation method, a support method, and a program. [Background technology]

[0002] A technology has been disclosed in which, when a user reports that the environment is unpleasant, a location category that satisfies the user's pre-registered preferred environmental conditions is searched for and notified (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-214975 Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology described in Patent Document 1, discomfort is a requirement for starting an action, which poses a problem in that it is not possible to suggest a comfortable environment for an individual when they start working.

[0005] An object of the present invention is to provide an assistance system, an information processing device, a learning model generation method, an assistance method, and a program that can assist in proposing an environmental location that will be comfortable for an individual when the individual starts work. [Means for solving the problem]

[0006] The support system of the present invention comprises: an information acquisition unit that acquires individual identification information that identifies an individual and evaluation information that indicates the individual's evaluation of an environment; a sensor that measures environmental information indicating the environment for each area where seats are arranged; a learning model generation unit that performs machine learning on the area corresponding to the environmental information according to the evaluation information for each of the individual identifying information acquired by the information acquisition unit to generate a learning model; an estimation unit that inputs the individual identifying information and environmental information measured by the sensor into the learning model, and acquires area information indicating the area from the learning model; and an output unit that outputs the region information acquired by the estimation unit.

[0007] Further, the information processing device of the present invention comprises: an information acquisition unit that acquires individual identification information that identifies an individual and evaluation information that indicates the individual's evaluation of an environment; a learning model generation unit that performs machine learning on the area corresponding to environmental information indicating the environment measured by a sensor for each area where seats are arranged according to the evaluation information, for each individual identifying information acquired by the information acquisition unit, to generate a learning model; an estimation unit that inputs the individual identifying information and environmental information measured by the sensor into the learning model, and acquires area information indicating the area from the learning model; and an output unit that outputs the region information acquired by the estimation unit.

[0008] Further, the learning model generation method of the present invention includes: A process of acquiring individual identification information that identifies an individual and evaluation information that indicates the individual's evaluation of the environment; generating training data that associates the acquired individual identification information, the evaluation information, environmental information indicating the environment, and area information indicating an area corresponding to the environmental information; Using the generated training data, a process is performed to generate a learning model that outputs the area information according to the individual identifying information and the environmental information.

[0009] Further, the support method of the present invention includes: A process of acquiring individual identification information that identifies an individual and evaluation information that indicates the individual's evaluation of the environment; a process of acquiring area information indicating the area from a learning model by inputting the individual identifying information and the environmental information measured by the sensor into a learning model that has been machine-learned for the area corresponding to environmental information indicating the environment measured by the sensor for each area where seats are arranged according to the evaluation information; and outputting the acquired area information.

[0010] The program of the present invention also includes: A program to be executed by a computer, a step of acquiring individual identification information that identifies an individual and evaluation information that indicates the individual's evaluation of an environment; generating training data that associates the acquired individual identification information, the evaluation information, environmental information indicating the environment, and area information indicating an area corresponding to the environmental information; The generated training data is used to generate a learning model that outputs the area information according to the individual identifying information and the environmental information.

[0011] The program of the present invention also includes: A program to be executed by a computer, a step of acquiring individual identification information that identifies an individual and evaluation information that indicates the individual's evaluation of an environment; a step of acquiring area information indicating the area from a learning model by inputting the individual identifying information and the environmental information measured by the sensor into a learning model that has been machine-learned for the area corresponding to environmental information indicating the environment measured by the sensor for each area where seats are arranged according to the evaluation information; and a procedure for outputting the acquired area information. [Effects of the Invention]

[0012] In the present invention, when an individual starts work, it is possible to assist in proposing a location in an environment that will be comfortable for the individual. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a diagram illustrating a first embodiment of a support system according to the present invention. [Figure 2] FIG. 2 is a diagram showing an example of a work space in which the sensor shown in FIG. 1 is installed. [Figure 3] FIG. 3 is a diagram showing an example of the arrangement of seats included in one area in the work space shown in FIG. 2. [Figure 4] 2 is a diagram illustrating an example of components included in the communication terminal illustrated in FIG. 1. FIG. [Figure 5] FIG. 2 is a diagram illustrating an example of components included in the information processing device illustrated in FIG. [Figure 6] 6 is a diagram illustrating an example of input and output of the learning model illustrated in FIG. 5. [Figure 7] 2 is a sequence diagram illustrating an example of a method for generating a learning model in the support system shown in FIG. 1. FIG. [Figure 8] 5 is a diagram showing an example of an input screen displayed by an output unit for inputting personal identification information by the input unit shown in FIG. 4. FIG. [Figure 9] 5 is a diagram showing an example of an input screen displayed by an output unit for inputting evaluation information by the input unit shown in FIG. 4. FIG. [Figure 10] 5 is a diagram showing another example of the input screen displayed by the output unit for inputting evaluation information by the input unit shown in FIG. 4. FIG. [Figure 11] 2 is a sequence diagram illustrating an example of a support method in the support system shown in FIG. 1. FIG. [Figure 12] FIG. 5 is a diagram showing an example of seat information displayed on the output unit of the communication terminal shown in FIG. 4 in step S18. [Figure 13] FIG. 10 is a diagram illustrating a second embodiment of the support system of the present invention. [Figure 14] FIG. 14 is a diagram illustrating an example of components included in the information processing device illustrated in FIG. [Figure 15] 15 is a diagram illustrating an example of input and output of the learning model illustrated in FIG. 14. [Figure 16]FIG. 14 is a sequence diagram for explaining an example of a method for generating a learning model in the support system shown in FIG. [Figure 17] FIG. 14 is a sequence diagram illustrating an example of a support method in the support system shown in FIG. [Figure 18] FIG. 10 is a diagram illustrating a third embodiment of the support system of the present invention. [Figure 19] FIG. 19 is a diagram illustrating an example of components included in the information processing device illustrated in FIG. 18. [Figure 20] FIG. 20 is a diagram showing an example of priority information stored in the priority database shown in FIG. [Figure 21] FIG. 19 is a sequence diagram for explaining an example of a support method in the support system shown in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. (First embodiment)

[0015] FIG. 1 is a diagram showing a first embodiment of a support system of the present invention. As shown in FIG. 1, the support system in this embodiment includes an information processing device 100, a sensor 200, and a communication terminal 300. The information processing device 100, the sensor 200, and the communication terminal 300 are communicably connected to each other via a communication network 400. The communication network 400 may be the general Internet or a communication network closed to a specific location such as an in-house network. Furthermore, the information processing device 100, the sensor 200, and the communication terminal 300 may be directly connected to each other.

[0016] The sensor 200 measures environmental information indicating the environment for each area where seats are arranged. The environmental information is at least one of temperature, humidity, illuminance, and sound volume. The sensor 200 transmits the measured environmental information to the information processing device 100. At this time, the sensor 200 transmits sensor identification information for identifying the sensor 200 or area identification information for identifying the area where the sensor 200 measured the environmental information to the information processing device 100 together with the environmental information. The sensor 200 may be attached to each area. An area is an area divided into a space used by many users, such as an office, a coffee shop, or a workspace, or a room in an apartment building.

[0017] FIG. 2 is a diagram illustrating an example of a workspace in which the sensor 200 illustrated in FIG. 1 is installed. A plurality of sensors 200-1 to 200-6 are installed in the workspace 500 illustrated in FIG. 2. The regions 510-1 to 510-6 are regions in which the sensors 200-1 to 200-6 can measure environmental information, respectively. While the regions 510-1 to 510-6 are shown spaced apart from one another in FIG. 2 for the sake of convenience, it is preferable that there be no actual space between them. Furthermore, the shapes and sizes (areas) of the regions 510-1 to 510-6 are not particularly specified. It should be noted that, for regions in the workspace 500 where the user does not perform work, it is not necessary to measure environmental information, and therefore, it is not necessary to provide sensors in such regions. The association between the sensors 200-1 to 200-6 and the regions 510-1 to 510-6 is pre-stored in the information processing device 100.

[0018] Fig. 3 is a diagram showing an example of the arrangement of seats included in area 510-1 in work space 500 shown in Fig. 2. One area 510-1 shown in Fig. 2 includes multiple seats A to F as shown in Fig. 3. Although sensor 200-1 measuring environmental information for area 510-1 measures only one piece of environmental information, it is conceivable that there will be slight differences between the individual seats A to F. For this reason, it is preferable to consider not only the area but also each individual seat in the processing described below.

[0019] Communication terminal 300 is a communication device carried by a user. Communication terminal 300 may be, for example, a mobile terminal such as a smartphone. FIG. 4 is a diagram showing an example of components included in communication terminal 300 shown in FIG. 1. As shown in FIG. 4, communication terminal 300 shown in FIG. 1 has an input unit 310, an output unit 320, and a communication unit 330.

[0020] The input unit 310 inputs information to the communication terminal 300 based on an operation received from an external device. The input unit 310 may be a touch panel, a touch pad, a keyboard, or any other device capable of inputting information to the communication terminal 300 based on a user's operation. In this embodiment, the information input by the input unit 310 is personal identification information that identifies an individual and evaluation information that indicates the individual's evaluation of the environment. The personal identification information may be, for example, identification information that can identify an individual, such as the name of a user using the system or an ID (identification) uniquely assigned to the user. The personal identification information may also be identification information (e.g., a telephone number) or email address uniquely set to a communication terminal such as a mobile terminal used (owned) by the individual. The evaluation information is information indicating an evaluation of the assistance processing system by a user who used the assistance system during the learning phase. Details of the evaluation information will be described later.

[0021] The output unit 320 outputs information processed by the communication terminal 300. The form of information output from the output unit 320 may be a display of characters or images, or may be an audio output, printed, or transmitted to another device.

[0022] The communication unit 330 includes the information processed by the communication terminal 300 in a predetermined signal and transmits the signal to the information processing device 100 via the communication network 400. The communication unit 330 extracts the information to be processed from the signal received from the information processing device 100 via the communication network 400. The communication method used by the communication unit 330 is not particularly specified.

[0023] The information processing device 100 processes information transmitted from the communication terminal 300. FIG. 5 is a diagram showing an example of components included in the information processing device 100 shown in FIG. 1. As shown in FIG. 5, the information processing device 100 shown in FIG. 1 has an information acquisition unit 110, a learning model generation unit 120, a learning model 130, an estimation unit 140, an output unit 150, and a location information acquisition unit 160. Note that FIG. 5 shows only the main components related to this embodiment among the components included in the information processing device 100 shown in FIG. 1. The learning model 130 may be provided outside the information processing device 100.

[0024] The information acquisition unit 110 acquires individual identification information that identifies an individual. The information acquisition unit 110 also acquires evaluation information that indicates an individual's evaluation of the environment. In this embodiment, the information acquisition unit 110 also acquires seat information corresponding to the individual identification information. When this information is transmitted from the communication terminal 300 or another device, the information acquisition unit 110 may acquire it by receiving the transmitted information. When this information is input to an input unit (not shown) provided in the information processing device 100, the information acquisition unit 110 may acquire the input information.

[0025] The learning model generation unit 120 generates training data that associates the individual identifying information and evaluation information acquired by the information acquisition unit 110 with environmental information indicating the environment measured by the sensor 200 and area information indicating the area where the sensor 200 measured the environment. The learning model generation unit 120 uses the training data to perform machine learning on an area corresponding to environmental information according to the evaluation information for each of the individual identifying information acquired by the information acquisition unit 110. In this embodiment, the learning model generation unit 120 performs machine learning on an area corresponding to environmental information according to seat information and evaluation information for each of the individual identifying information acquired by the information acquisition unit 110. Here, the seat information indicates a seat located within the area indicated by the area information and is information acquired by the information acquisition unit 110. At this time, the seat information is used to identify the area or sensor 200 that is the subject of the evaluation information in which the user evaluated the environment. By identifying the area or sensor 200, it is possible to recognize environmental information in that area. In this way, it is possible to recognize what kind of environment (e.g., the temperature) the user evaluated. The learning model generation unit 120 uses the results of machine learning to generate the learning model 130. For example, the learning model generation unit 120 may generate the learning model 130 by performing machine learning using training data in which individual identification information, evaluation information, environmental information, and seat information are associated with each other for each predetermined unit time.

[0026] The learning model 130 is a learning model generated by the learning model generation unit 120. The learning model 130 uses the training data generated by the learning model generation unit 120 to output area information corresponding to individual identifying information and environmental information. The learning model 130 may output area information for days on which the number of unit times that the environmental information derived for the input individual identifying information matches the input environmental information is large. Furthermore, if the learning model 130 is a model that has performed machine learning using training data generated for each unit time as described above, the learning model 130 may output area information ranked in descending order of the number of unit times that the environmental information derived for the input individual identifying information matches the input environmental information. The learning model 130 may have, for example, a neural network structure in which multiple neurons are interconnected. A neuron is an element that performs a predetermined calculation on multiple inputs and outputs a single value as a calculation result. The learning model 130 is stored in a storage unit (not shown). The learning method in the learning model 130 may be a general method for generating a learning model. Fig. 6 is a diagram showing an example of input and output of the learning model 130 shown in Fig. 5. The learning model 130 shown in Fig. 5 is a learning model that outputs domain information when individual identifying information and environmental information are input, as shown in Fig. 6.

[0027] The estimation unit 140 inputs the individual specifying information and the environmental information into the learning model 130, and acquires area information indicating the area from the learning model 130.

[0028] The output unit 150 outputs the area information acquired by the estimation unit 140. The output unit 150 also outputs seat information indicating seats included in the area indicated by the area information acquired by the estimation unit 140. Here, the output unit 150 determines seats included in the area according to values ​​measured by the sensor 200 in the area indicated by the area information acquired by the estimation unit 140, and outputs seat information indicating the determined seats. The output mode of the area information performed by the output unit 150 may be display or audio output, or may be printing or transmission to another device such as the communication terminal 300.

[0029] The location information acquisition unit 160 acquires location information indicating the location of the communication terminal 300. For example, the communication terminal 300 may be equipped with a GPS (Global Positioning System) function, and the location information acquisition unit 160 may acquire location information acquired by the communication terminal 300 using the GPS function. Alternatively, the location information acquisition unit 160 may acquire the location information of the communication terminal 300 based on location information of a wireless base station with which the communication terminal 300 is communicating, and the method of acquiring the location information is not particularly specified.

[0030] The following describes a method for generating a learning model in the support system shown in Fig. 1. Fig. 7 is a sequence diagram for explaining an example of a method for generating the learning model 130 in the support system shown in Fig. 1.

[0031] First, a user sits down in a seat of their choice. The sensor 200 starts measuring environmental information such as temperature, humidity, airflow, illuminance, and sound volume (step S1). Thereafter, the communication terminal 300 accepts an operation from the user, and the input unit 310 inputs personal identification information, evaluation information, and seat information (step S2). The input personal identification information, evaluation information, and seat information are transmitted from the communication unit 330 of the communication terminal 300 to the information processing device 100 (step S3).

[0032] Fig. 8 is a diagram showing an example of an input screen displayed by output unit 320 for inputting personal identification information by input unit 310 shown in Fig. 4. As shown in Fig. 8, output unit 320 displays an input field for inputting a user ID, which is personal identification information, and prompts the user to input the user ID. The user performs a predetermined input operation and inputs the user ID in the input field for inputting the user ID.

[0033] FIG. 9 is a diagram showing an example of an input screen displayed by the output unit 320 for inputting evaluation information from the input unit 310 shown in FIG. 4. As shown in FIG. 9, the output unit 320 displays a screen for inputting a user's evaluation of the environment and prompts the user to input the evaluation information. The user performs a predetermined input operation to input the evaluation information. The evaluation information input screen may, for example, as shown in FIG. 9, display radio buttons that allow the user to select an item for inputting an evaluation of the environment, such as "hot," "cold," "dark," "bright," or "noisy." In this case, if the user evaluates the temperature as high, the user can select the "hot" option. If the user evaluates the illuminance as low, the user can select the "dark" option. If the user evaluates the sound as loud, the user can select the "noisy" option. These input items are fed back as evaluation information. The screen for inputting evaluation information is not limited to the one shown in FIG. 9, and may also be one that allows the user to input (select) the level of each information indicating the environment (temperature, humidity, airflow, illuminance, sound volume, etc.). The evaluation information may also include information indicating the reason for the evaluation and areas for improvement.

[0034] FIG. 10 is a diagram illustrating an example of an input screen displayed by the output unit 320 for inputting evaluation information from the input unit 310 shown in FIG. 4. The evaluation information input screen, as shown in FIG. 10, displays slide buttons for selecting levels for temperature ranging from "cold" through "comfortable" to "hot," levels for humidity ranging from "low" through "comfortable" to "high," and levels for illuminance ranging from "dark" through "comfortable" to "bright." In this case, the user can select these levels by operating the slide buttons according to their evaluation of temperature, humidity, and illuminance. Although not shown in FIG. 10, the input screen displayed by the output unit 320 may also display a display for evaluating the airflow and sound volume described above. In this case, slide buttons for selecting levels for airflow ranging from "weak" through "comfortable" to "strong." Furthermore, slide buttons for selecting levels for sound volume ranging from "quiet" through "comfortable" to "noisy" are displayed. These selected levels are fed back as evaluation information.

[0035] The seat information is information indicating the position where the user carrying the communication terminal 300 was seated when the user evaluated the environment. The seat information may be information input to and transmitted from the communication terminal 300, or may be position information indicating the position of the communication terminal 300 acquired by the position information acquisition unit 160.

[0036] Furthermore, sensor 200 transmits the measured environmental information to information processing device 100 (step S4). Then, information acquiring unit 110 acquires the individual identifying information, evaluation information, and seat information transmitted from communication terminal 300 in step S3, and the environmental information transmitted from sensor 200 in step S4. At this time, information acquiring unit 110 may acquire the seat information based on the position information acquired by position information acquiring unit 160.

[0037] Next, the learning model generation unit 120 generates training data that associates the personal identifying information, evaluation information, seat information, and environmental information acquired by the information acquisition unit 110 (step S5). Then, the learning model generation unit 120 uses the generated training data to generate a learning model 130 that outputs area information corresponding to the personal identifying information and environmental information (step S6). Specifically, the learning model generation unit 120 selects an area of ​​the sensor 200 that measures the environment indicated by the environmental information corresponding to the personal identifying information, evaluation information, and environmental information acquired by the information acquisition unit 110, and generates the learning model 130 that outputs area information indicating the selected area as area information to be proposed to the user of the personal identifying information. Note that the personal identifying information and evaluation information acquired by the information acquisition unit 110 are not limited to those transmitted from the communication terminal 300, but may also be those directly input to the information processing device 100 or transmitted from another communication device.

[0038] The following describes a support method in the support system shown in Fig. 1. Fig. 11 is a sequence diagram for explaining an example of the support method in the support system shown in Fig. 1. This is a process that is performed before a user carrying communication terminal 300 starts work in the work space.

[0039] When the communication terminal 300 receives an external operation and the input unit 310 inputs personal identifying information (step S11), the communication unit 330 of the communication terminal 300 transmits the input personal identifying information to the information processing device 100 (step S12). Note that if the personal identifying information is terminal identification information that is uniquely set in advance in the communication terminal 300 to identify the communication terminal 300 possessed by the user, when the communication terminal 300 detects that the user has entered a target workspace, the terminal identification information may be transmitted from the communication terminal 300 to the information processing device 100. Note that, needless to say, when the terminal identification information is used as the personal identifying information, input of the personal identifying information is not required.

[0040] Furthermore, the sensor 200 measures environmental information (step S13) and transmits the measured environmental information to the information processing device 100 (step S14). The timing at which the sensor 200 transmits the environmental information is not particularly specified. Since multiple sensors 200 are provided in one workspace, each of the multiple sensors 200 also transmits identification information previously assigned to each sensor 200 to the information processing device 100. This allows the information processing device 100 to recognize which sensor 200 measured the transmitted environmental information.

[0041] Next, the information acquisition unit 110 acquires the individual identifying information transmitted from the communication unit 330 of the communication terminal 300 and the environmental information transmitted from the sensor 200. The estimation unit 140 inputs the acquired individual identifying information and environmental information to the learning model 130 (step S15). The estimation unit 140 then acquires area information output from the learning model 130 (step S16). The output unit 150 transmits seating information indicating seats included in the area indicated by the area information acquired by the estimation unit 140 to the communication terminal 300 (step S17). The output unit 320 of the communication terminal 300 displays the seating information transmitted from the output unit 150 (step S18). Note that if the environmental information transmitted from the sensor 200 changes after the seating information is presented, the learning model generation unit 120 may generate the learning model 130 based on the changed environmental information, and the estimation unit 140 may acquire the area information using the generated learning model 130. In this case, the seating information newly acquired by the estimation unit 140 is presented.

[0042] FIG. 12 is a diagram illustrating an example of the display of seat information on the output unit 320 of the communication terminal 300 shown in FIG. 4 in step S18. As shown in FIG. 12, the communication terminal 300 displays seat information indicating seats recommended to the user who input information to the communication terminal 300 in step S11. This seat information indicates the location of the recommended seats. As shown in FIG. 12, the display shows which seats in the work space are recommended. This display may be performed by adding a predetermined mark to the recommended seats, or by highlighting the recommended seats more than other seats, as shown in FIG. 12. For example, the output unit 320 of the communication terminal 300 may display the lines surrounding the recommended seats thicker than the lines surrounding the other areas, in a different color, or by flashing. This display may also display a mark such as an arrow or cursor that specifies the recommended seat. This display may also be a number or other display indicating a specific seat. As shown in FIG. 12, the output unit 320 of the communication terminal 300 may display multiple seats with a recommendation level. In this case, the learning model 130 outputs multiple pieces of area information based on the probability of occurrence for the input individual identifying information and environmental information, and the output unit 320 displays seat information indicating seats included in the areas indicated by the output multiple pieces of area information according to the probability. The output unit 320 may also display environmental information such as temperature, humidity, airflow, illuminance, and sound volume for each seat. In this case, the output unit 320 may also display the temperature distribution measured by the sensor 200.

[0043] After the processing of step S18 is performed and the user uses the displayed seat, further evaluation information may be input, and the learning model generation unit 120 may re-learn the learning model 130 to strengthen the learning model 130. Note that the environmental information may include all or some of the temperature, humidity, airflow, illuminance, and sound volume. Furthermore, the temperature, humidity, airflow, illuminance, and sound volume may each be weighted, and the learning model 130 may output seat information based on the weighted environmental information.

[0044] As described above, in this embodiment, the learning model generation unit 120 generates training data that associates personal identifying information, environmental information indicating the environment, evaluation information indicating the user's personal evaluation of the environment, and seat information indicating the corresponding area, and generates a learning model 130 that outputs area information corresponding to the personal identifying information and environmental information using the generated training data. Furthermore, the estimation unit 140 inputs the personal identifying information and environmental information into the learning model 130, thereby acquiring area information indicating the area from the learning model 130 and outputting seat information indicating the seat included in the area indicated by the acquired area information. This makes it possible to support the suggestion of an environmental location that will be comfortable for the individual user when they start work. (Second embodiment)

[0045] Fig. 13 is a diagram showing a second embodiment of the support system of the present invention. As shown in Fig. 13, the support system in this embodiment has an information processing device 101, a sensor 200, and a communication terminal 300. The information processing device 101, the sensor 200, and the communication terminal 300 are connected to each other so as to be able to communicate with each other via a communication network 400. The sensor 200, the communication terminal 300, and the communication network 400 are the same as the sensor 200, the communication terminal 300, and the communication network 400 in the first embodiment, respectively.

[0046] FIG. 14 is a diagram illustrating an example of components included in the information processing device 101 illustrated in FIG. 13. As illustrated in FIG. 14, the information processing device 101 illustrated in FIG. 13 includes an information acquisition unit 110, a learning model generation unit 121, a learning model 131, an estimation unit 141, an output unit 150, and a past information database 171. Note that FIG. 14 illustrates only the main components related to this embodiment among the components included in the information processing device 101 illustrated in FIG. 13. The information acquisition unit 110 and the output unit 150 are the same as the information acquisition unit 110 and the output unit 150, respectively, in the first embodiment. The learning model 131 and the past information database 171 may be provided outside the information processing device 101.

[0047] The past information database 171 stores past statistical information. Specifically, the past information database 171 stores date and time information indicating the date and time when past environmental information was acquired and the weather information at that time in association with the environmental information. The date and time information may include not only the year, month, date, and time, but also the day of the week. The weather information may include not only the weather, but also the temperature and humidity.

[0048] The learning model generation unit 121 uses past statistical information stored in the past information database 171 to perform machine learning on the area indicated by the area information corresponding to the predicted transition of the environmental information according to the seat information and the evaluation information for each piece of personal identification information acquired by the information acquisition unit 110, and generates a learning model 131. The learning model generation unit 121 generates a learning model 131 that outputs area information that predicts the transition of the environment as a predicted value, based on the past statistical information stored in the past information database 171.

[0049] The learning model 131 is a learning model generated by the learning model generation unit 121. The learning model 131 uses the training data generated by the learning model generation unit 121 to output area information corresponding to individual identifying information, environmental information, date and time information, and weather information. The learning model 131 may have, for example, a neural network structure in which multiple neurons are interconnected. A neuron is an element that performs a predetermined calculation on multiple inputs and outputs a single value as the calculation result. The learning model 131 is stored in a storage unit (not shown). The learning method in the learning model 131 may be a general method for generating a learning model. FIG. 15 is a diagram showing an example of input / output of the learning model 131 shown in FIG. 14. As shown in FIG. 15, the learning model 131 shown in FIG. 14 is a learning model that outputs area information corresponding to a predicted transition of the environmental information when individual identifying information, environmental information, date and time information, and weather information are input.

[0050] The estimation unit 141 inputs the personal identifying information, environmental information, current date and time information, and weather information acquired by the information acquisition unit 110 into the learning model 131, and thereby acquires area information corresponding to a predicted transition of the environmental information from the learning model 131. The estimation unit 141 may also acquire area information from the learning model 131 according to the length of a period during which a predetermined evaluation was made as the evaluation indicated by the evaluation information. For example, the estimation unit 141 may acquire from the learning model 131 an area in which the user to whom the personal identifying information is assigned is predicted to maintain an environment that the user evaluates as comfortable for a long period of time.

[0051] The following describes a method for generating a learning model in the support system shown in Fig. 13. Fig. 16 is a sequence diagram for explaining an example of a method for generating the learning model 131 in the support system shown in Fig. 13.

[0052] First, a user sits down at any seat. The sensor 200 starts measuring environmental information such as temperature, humidity, airflow, illuminance, and sound volume (step S21). Thereafter, the communication terminal 300 accepts an operation from the user, and the input unit 310 inputs personal identification information, evaluation information, and seat information (step S22). The input personal identification information, evaluation information, and seat information are transmitted from the communication unit 330 of the communication terminal 300 to the information processing device 101 (step S23). The input screen for inputting each piece of information to the communication terminal 300 may be the same as that in the first embodiment.

[0053] Furthermore, the sensor 200 transmits the measured environmental information to the information processing device 101 (step S24). Then, the information acquiring unit 110 acquires the individual identifying information, the evaluation information, and the seat information transmitted from the communication terminal 300 in step S23, and the environmental information transmitted from the sensor 200 in step S24.

[0054] Next, the learning model generation unit 121 generates training data that associates the personal identification information, rating information, seat information, and environmental information acquired by the information acquisition unit 110 with date and time information and weather information (step S25). The date and time information and weather information indicate the current date and time (including the day of the week), and the acquisition method thereof is not particularly limited. The learning model generation unit 121 then uses the generated training data to generate a learning model 131 that outputs area information corresponding to the personal identification information, environmental information, date and time information, and weather information (step S26). Specifically, the learning model generation unit 121 selects an area of ​​the sensor 200 that measures the environment indicated by the environmental information corresponding to the personal identification information, rating information, and environmental information acquired by the information acquisition unit 110, and generates the learning model 131 that outputs, as area information to be proposed to the user of the personal identification information, area information that is associated with area information indicating the selected area and whose date and time information and weather information are similar to those stored in the past information database 171. Here, similar date and time information refers to areas that are similar in time zone, season, and day of the week. The individual identifying information and evaluation information acquired by the information acquiring unit 110 are not limited to those transmitted from the communication terminal 300, but may be those directly input to the information processing device 101 or those transmitted from another communication device. At this time, the past information database 171 stores the environmental information, date and time information, and weather information transmitted from the sensor 200 in association with each other.

[0055] The following describes a support method in the support system shown in Fig. 13. Fig. 17 is a sequence diagram for explaining an example of the support method in the support system shown in Fig. 13. This is a process that is performed before a user carrying communication terminal 300 starts work in the work space.

[0056] When the communication terminal 300 accepts an external operation and the input unit 310 inputs personal identifying information (step S31), the communication unit 330 of the communication terminal 300 transmits the input personal identifying information to the information processing device 101 (step S32). Note that if the personal identifying information is terminal identification information that is uniquely set in advance in the communication terminal 300 to identify the communication terminal 300 possessed by the user, when the communication terminal 300 detects that the user has entered a target workspace, the terminal identification information may be transmitted from the communication terminal 300 to the information processing device 101. Note that, needless to say, when the terminal identification information is used as the personal identifying information, input of the personal identifying information is not required.

[0057] Furthermore, the sensor 200 measures environmental information (step S33) and transmits the measured environmental information to the information processing device 101 (step S34). The timing at which the sensor 200 transmits the environmental information is not particularly specified. Since multiple sensors 200 are provided in one workspace, each of the multiple sensors 200 also transmits identification information previously assigned to each sensor 200 to the information processing device 100. This allows the information processing device 100 to recognize which sensor 200 measured the transmitted environmental information.

[0058] Next, the information acquisition unit 110 acquires the personal identification information transmitted from the communication unit 330 of the communication terminal 300 and the environmental information transmitted from the sensor 200. The estimation unit 141 inputs the acquired personal identification information and environmental information, along with the current date and time information and weather information, into the learning model 131 (step S35). The method for acquiring the current date and time information and weather information is not particularly specified. The date and time information may be acquired from a clock or the like having a calendar function. The weather information may be acquired from an information provider site that provides weather information. The estimation unit 141 then acquires area information output from the learning model 131 (step S36). The output unit 150 transmits seat information indicating seats included in the area indicated by the area information acquired by the estimation unit 141 to the communication terminal 300 (step S37). The output unit 320 of the communication terminal 300 displays the seat information transmitted from the output unit 150 (step S38). Note that if the environmental information or weather information transmitted from the sensor 200 changes after the seat information is presented, the learning model generation unit 121 may generate a learning model 131 based on the changed environmental information or weather information, and the estimation unit 141 may acquire area information using the generated learning model 131. In this case, the newly acquired area information is presented by the estimation unit 141. Note that the display mode of the seat information on the output unit 320 may be the same as that in the first embodiment.

[0059] As described above, in this embodiment, the learning model generation unit 121 generates training data that associates personal identification information, environmental information indicating the environment, evaluation information indicating the user's personal evaluation of the environment, seat information indicating seats included in the corresponding area, date and time information, and weather information at that time. The generated training data is used to generate a learning model 131 that outputs area information corresponding to the personal identification information, environmental information, date and time information, and weather information. The estimation unit 141 inputs the personal identification information, environmental information, date and time information, and weather information into the learning model 131, thereby acquiring area information indicating the area from the learning model 131 and outputting seat information indicating seats included in the area indicated by the acquired area information. This can assist in suggesting a location in an environment that will be comfortable for the individual user when they start work. Compared to the first embodiment, using date and time information and weather information can assist in suggesting a more suitable location. Note that instead of using both date and time information and weather information, only one of them may be used. Alternatively, the date and time information and weather information may be weighted, and the learning model 131 may output area information based on the weighted date and time information and weather information. (Third embodiment)

[0060] Fig. 18 is a diagram showing a third embodiment of the support system of the present invention. As shown in Fig. 18, the support system in this embodiment has an information processing device 102, a sensor 200, and a communication terminal 300. The information processing device 102, the sensor 200, and the communication terminal 300 are communicably connected to each other via a communication network 400. The sensor 200, the communication terminal 300, and the communication network 400 are the same as the sensor 200, the communication terminal 300, and the communication network 400 in the first embodiment, respectively.

[0061] FIG. 19 is a diagram illustrating an example of components included in the information processing device 102 illustrated in FIG. 18. As illustrated in FIG. 19, the information processing device 102 illustrated in FIG. 18 includes an information acquisition unit 110, a learning model generation unit 120, a learning model 130, an estimation unit 140, an output unit 152, and a priority database 182. Note that FIG. 19 illustrates only the main components related to this embodiment among the components included in the information processing device 102 illustrated in FIG. 18. Furthermore, the information acquisition unit 110, the learning model generation unit 120, the learning model 130, and the estimation unit 140 are the same as the information acquisition unit 110, the learning model generation unit 120, the learning model 130, and the estimation unit 140, respectively, in the first embodiment. Furthermore, the priority database 182 may be provided outside the information processing device 102.

[0062] The priority database 182 stores personal identification information and priorities in association with each other in advance. FIG. 20 is a diagram illustrating an example of priority information stored in the priority database 182 illustrated in FIG. 19. As illustrated in FIG. 20, the priority database 182 illustrated in FIG. 19 stores priority information in which personal identification information and priorities are associated with each other. The personal identification information is the same as that described above and is identification information previously assigned to a user to identify the user. The priority is information indicating which user should be prioritized when a proposed seat overlaps between multiple users. This priority may be preset or calculated from predetermined parameters. In the example illustrated in FIG. 20, the priority is preset to a level of priority such as "low," "medium," or "high." As another example, the user may input the work time required by each user at the start of a task, and the priority may be set so as to prioritize users who spend longer working hours. Furthermore, the priority may be set based on the user's level of proficiency in the task, the type of task, age, etc.

[0063] When seat information indicating seats included in the area indicated by the area information acquired by the estimation unit 140 overlaps among multiple users, the output unit 152 selects one of the multiple users based on the priority information stored in the priority database 182. The output unit 152 outputs a seat included in the area indicated by the area information acquired by the estimation unit 140 as the seat of the selected user. For example, when the association shown in FIG. 20 is stored in the priority database 182 and seat information indicating seats included in the area indicated by the area information acquired by the estimation unit 140 for a user whose personal identifying information is "A0001" and a user whose personal identifying information is "A0002" are the same, the output unit 152 selects the user whose personal identifying information is "A0002" with the highest priority, and transmits the seat information to the communication terminal carried by the user whose personal identifying information is "A0002".

[0064] The following describes a support method in the support system shown in Fig. 18. Fig. 21 is a sequence diagram for explaining an example of the support method in the support system shown in Fig. 18. This is a process that is performed before a user carrying communication terminal 300 starts work in the work space.

[0065] When the communication terminal 300 accepts an external operation and the input unit 310 inputs personal identifying information (step S41), the communication unit 330 of the communication terminal 300 transmits the input personal identifying information to the information processing device 102 (step S42). Note that if the personal identifying information is terminal identification information that is uniquely set in advance in the communication terminal 300 to identify the communication terminal 300 possessed by the user, when the communication terminal 300 detects that the user has entered a target workspace, the terminal identification information may be transmitted from the communication terminal 300 to the information processing device 102. Note that, needless to say, when the terminal identification information is used as the personal identifying information, input of the personal identifying information is not required.

[0066] Furthermore, the sensor 200 measures environmental information (step S43) and transmits the measured environmental information to the information processing device 102 (step S44). The timing at which the sensor 200 transmits the environmental information is not particularly specified. Since multiple sensors 200 are provided in one workspace, each of the multiple sensors 200 also transmits identification information previously assigned to each sensor 200 to the information processing device 100. This allows the information processing device 100 to recognize which sensor 200 measured the transmitted environmental information.

[0067] Next, the information acquisition unit 110 acquires the individual identifying information transmitted from the communication unit 330 of the communication terminal 300 and the environmental information transmitted from the sensor 200. The estimation unit 140 inputs the acquired individual identifying information and environmental information to the learning model 130 (step S45). Then, the estimation unit 140 acquires area information output from the learning model 130 (step S46). The output unit 152 determines whether seat information indicating seats included in the area indicated by the area information acquired by the estimation unit 140 overlaps with each other for multiple users. If seat information indicating seats included in the area indicated by the area information acquired by the estimation unit 140 overlaps with each other for multiple users, the output unit 152 selects one of the multiple users based on the priority information stored in the priority database 182 (step S47). The output unit 152 transmits the seat information indicating seats included in the area indicated by the area information acquired by the estimation unit 140 to the communication terminal 300 of the selected user (step S48). If the seat information indicating the seats included in the area indicated by the area information acquired by the estimation unit 140 does not overlap among multiple users, the output unit 152 transmits the seat information indicating the seats included in the area indicated by the area information acquired by the estimation unit 140 to the communication terminal 300 of that user. The output unit 320 of the communication terminal 300 displays the seat information transmitted from the output unit 152 (step S49). Note that if the environmental information transmitted from the sensor 200 changes after the seat information is presented, the learning model generation unit 120 may generate a learning model 130 based on the changed environmental information, and the estimation unit 140 may acquire the area information using the generated learning model 130. In this case, the seat information newly acquired by the estimation unit 140 is presented. Note that the display format of the seat information on the output unit 320 may be the same as that in the first embodiment.

[0068] As described above, in this embodiment, the learning model generation unit 120 generates training data that associates personal identification information, environmental information indicating the environment, evaluation information indicating the user's individual evaluation of the environment, and seat information indicating the seat within the corresponding area. The generated training data is used to generate a learning model 130 that outputs area information corresponding to the personal identification information and the environmental information. Furthermore, the estimation unit 140 inputs the personal identification information and environmental information into the learning model 130, acquires area information indicating seats from the learning model 130, and outputs seat information indicating seats within the area indicated by the acquired area information. This can help suggest a comfortable environment for an individual user when they start work. Furthermore, if seat information indicating seats within the area indicated by the area information acquired by the estimation unit 140 overlaps between multiple users, the output unit 152 selects a user to whom the seat information is provided based on priority. This allows seat information to be provided to the most appropriate user.

[0069] Although the above description has been given by allocating each function (process) to each component, this allocation is not limited to the above. Furthermore, the configuration of the components is also not limited to the above-described embodiments, which are merely examples. Furthermore, each embodiment may be combined.

[0070] The processing performed by each of the information processing devices 100, 101, and 102 may be performed by a logic circuit manufactured for each purpose. Alternatively, a computer program (hereinafter referred to as a program) describing processing procedures may be recorded on a recording medium readable by each of the information processing devices 100, 101, and 102, and the program recorded on the recording medium may be read and executed by each of the information processing devices 100, 101, and 102. The recording medium readable by each of the information processing devices 100, 101, and 102 may include removable recording media such as a magneto-optical disk, a digital versatile disc (DVD), a compact disc (CD), a Blu-ray (registered trademark) disc, and a universal serial bus (USB) memory, as well as memories such as read only memory (ROM) and random access memory (RAM), a hard disc drive (HDD), and a solid state drive (SSD) built into each of the information processing devices 100, 101, and 102. The program recorded on this recording medium is read by the CPU provided in each of the information processing devices 100, 101, and 102, and the same processing as described above is performed under the control of the CPU. Here, the CPU operates as a computer that executes the program read from the recording medium on which the program is recorded. [Explanation of symbols]

[0071] 100, 101, 102 Information processing equipment 110 Information Acquisition Department 120,121 Learning model generation unit 130,131 Learning Model 140,141 Estimation part 150,152,320 Output section 160 Location information acquisition unit 171 Past Information Database 182 Priority Database 200, 200-1 to 200-6 sensors 300 Communication terminal 310 Input section 330 Communications Department 400 Communication Network 500 workspace 510-1~510-6 area

Claims

1. an information acquisition unit that acquires individual identification information that identifies an individual, evaluation information that indicates the individual's evaluation of the environment, and seat information that indicates a seat corresponding to the individual identification information; a sensor that measures environmental information indicating the environment for each area in which the seats are arranged; a learning model generation unit that performs machine learning on the area corresponding to the environmental information according to the seat information and the evaluation information for each of the individual identifying information acquired by the information acquisition unit to generate a learning model; an estimation unit that acquires area information indicating the area from the learning model by inputting the individual identifying information and environmental information measured by the sensor into the learning model; an output unit that outputs seat information indicating seats included in the area indicated by the area information acquired by the estimation unit, the learning model generation unit predicts a transition of the environmental information based on the environmental information, date and time information, and weather information previously measured by the sensor, and performs machine learning on the area corresponding to the predicted transition of the environmental information according to the seat information and the evaluation information for each of the individual identifying information acquired by the information acquisition unit using the environmental information, the date and time information, and the weather information to generate a learning model; The estimation unit inputs the personal identification information, environmental information measured by the sensor, current date and time information, and weather information into the learning model, and obtains the area information from the learning model based on the length of the period during which a specified evaluation was made as the evaluation indicated by the evaluation information.

2. 2. The support system according to claim 1, wherein, when the seat information acquired by the estimation unit overlaps with that of multiple individuals, the output unit selects one user from the multiple individuals based on a priority set for each of the individuals, and outputs seat information indicating a seat included in the area indicated by the area information acquired by the estimation unit as the seat information of the selected individual.

3. A location information acquisition unit that acquires location information indicating the location of a communication terminal carried by the individual, The assistance system according to claim 1 , wherein the information acquisition unit acquires the seat information based on the position information acquired by the position information acquisition unit.

4. The assistance system according to claim 1 , wherein the information acquisition unit acquires the individual specifying information from a communication terminal carried by the individual.

5. The assistance system according to claim 1 , wherein the environmental information is at least one of temperature, humidity, airflow, illuminance, and sound volume.

6. an information acquisition unit that acquires individual identification information that identifies an individual, evaluation information that indicates the individual's evaluation of the environment, and seat information that indicates a seat corresponding to the individual identification information; a learning model generation unit that performs machine learning on the area corresponding to the environmental information indicating the environment measured by a sensor for each area in which the seats are arranged, according to the seat information and the evaluation information, for each individual identifying information acquired by the information acquisition unit, to generate a learning model; an estimation unit that acquires area information indicating the area from the learning model by inputting the individual identifying information and environmental information measured by the sensor into the learning model; an output unit that outputs seat information indicating seats included in the area indicated by the area information acquired by the estimation unit, the learning model generation unit predicts a transition of the environmental information based on the environmental information, date and time information, and weather information previously measured by the sensor, and performs machine learning on the area corresponding to the predicted transition of the environmental information according to the seat information and the evaluation information for each of the individual identifying information acquired by the information acquisition unit using the environmental information, the date and time information, and the weather information to generate a learning model; The estimation unit inputs the personal identification information, environmental information measured by the sensor, current date and time information, and weather information into the learning model, and obtains the area information from the learning model according to the length of the period during which a specified evaluation was made as the evaluation indicated by the evaluation information.

7. A support method performed by an information processing device, comprising: A process of acquiring individual identification information that identifies an individual, evaluation information that indicates the individual's evaluation of the environment, and seat information that indicates a seat corresponding to the individual identification information; a process of predicting a transition of the environmental information based on environmental information indicating the environment, date and time information, and weather information previously measured by a sensor for each area where the seats are arranged, and using the environmental information, date and time information, and weather information, inputting the individual identifying information, the environmental information measured by the sensor, the current date and time information, and weather information into a learning model generated by performing machine learning for each of the acquired individual identifying information on the area corresponding to the predicted transition of the environmental information indicating the environment measured by the sensor according to the seat information and the evaluation information, and acquiring area information indicating the area from the learning model according to the length of a period during which a predetermined evaluation was made as the evaluation indicated by the evaluation information; and outputting seat information indicating seats included in the area indicated by the acquired area information.

8. On the computer, a step of acquiring individual identification information for identifying an individual, evaluation information indicating the individual's evaluation of the environment, and seat information indicating a seat corresponding to the individual identification information; a step of predicting a transition of the environmental information based on environmental information, date and time information, and weather information that indicate the environment measured by a sensor in the past for each area where the seats are arranged, and inputting the individual identifying information, the environmental information measured by the sensor, the current date and time information, and weather information into a learning model generated by performing machine learning for each of the acquired individual identifying information on the area corresponding to the predicted transition of the environmental information that indicates the environment measured by the sensor according to the seat information and the evaluation information, thereby acquiring area information that indicates the area from the learning model according to the length of a period during which a predetermined evaluation was made as the evaluation indicated by the evaluation information; and outputting seat information indicating seats included in the area indicated by the acquired area information.

Images