WO2025074519A1 - Seat recommendation device, seat recommendation method, and seat recommendation program - Google Patents

Abstract

The disclosed technology makes it possible to recommend seats that achieve both proximity between users and comfort in temperature.　This seat recommendation device inputs user-related data and seat-related data. The user-related data at least specifies predetermined related users related to a user. The seat-related data includes temperature information related to users and seats. The seat recommendation device includes a recommended seat calculation unit that outputs recommendation data indicating recommended seats that achieve both proximity between the users and comfort in temperature.

Description

Seat recommendation device, seat recommendation method, and seat recommendation program

The disclosed technology relates to a seat recommendation device, a seat recommendation method, and a seat recommendation program.

In the office, it is sometimes desirable to position colleagues who work in related jobs close to each other in order to promote communication and increase productivity.

Also, from a similar perspective, optimization of seating arrangements has been studied for pair programming classes, taking into account the academic ability of students and the proximity of friends, and it is possible to calculate seating arrangements in the office in a similar way (see Non-Patent Document 1).

On the other hand, because each worker has a different preferred illuminance, an illuminance sensor is installed at each seat and seating arrangements are calculated to match the pre-registered illuminance preferences of each worker (see Non-Patent Document 2). From a similar perspective, it is also possible to grasp or estimate the spatial temperature distribution from sensors in the case of office air conditioning, and calculate seating arrangements that match the preferred temperature in a similar manner.

Suzuki Satoshi, Multiple Pair Programming Exercises Optimizing Pair Organization and Seat Layout, Information Processing Society of Japan Research Report, Computers and Education Research Report 2014 (7), 1-8, 2014-11-29, Information Processing Society of Japan Kazuhiro Miwa et al., Study on seating arrangement method based on workers' preferred illuminance in intelligent lighting, Information Science and Technology Forum, 2015

However, even if a seating arrangement is calculated so that colleagues who should be encouraged to interact are placed close to each other, as in Non-Patent Document 1, there may be cases where there is a large discrepancy between the temperature at the seat and the worker's preferred temperature. Conversely, even if a seating arrangement is calculated based on the worker's preferred temperature, as in Non-Patent Document 2, there may be cases where colleagues who should be encouraged to interact are placed far apart.

In addition, conventional technology is based on the assumption that users will sit according to the calculated seating arrangement. However, when considering applications such as recommending seats to workers, in reality, only a limited number of workers will sit as recommended, so the intended improvement will not be achieved and seating arrangements may end up being reversed. Specifically, there may be cases where a worker moves as recommended, but a colleague they want to work with does not move, and ends up moving farther away, or where they try to move to a seat as recommended, but the seat remains taken.

The disclosed technology has been developed in consideration of the above points, and aims to provide a seat recommendation device, a seat recommendation method, and a seat recommendation program that are capable of recommending seats that balance proximity between users and thermal comfort.

The first aspect of the present disclosure is a seat recommendation device that receives user-related data and seat-related data as input, the user-related data defines at least a predetermined related user related to the user, the seat-related data defines temperature information related to the user and the seat, and includes a recommended seat calculation unit that outputs recommendation data indicating a recommended seat that achieves both proximity between users and thermal comfort.

A second aspect of the present disclosure is a seat recommendation method in which user-related data and seat-related data are input, the user-related data defines at least a predetermined related user related to the user, the seat-related data defines temperature information related to the user and the seat, and a computer executes a process to output recommendation data indicating a recommended seat that achieves both proximity between users and thermal comfort.

The disclosed technology makes it possible to recommend seats that balance proximity between users and thermal comfort.

FIG. 1 is a block diagram showing the configuration of a seat recommendation device according to the present embodiment. FIG. 2 is a block diagram showing a hardware configuration of the seat recommendation device. FIG. 3 is a block diagram showing the functional configuration of the recommended seat calculation unit. FIG. 4 shows an example of relationship data between workers. FIG. 5 shows an example of data on desired temperatures of workers. FIG. 6 shows an example of the current location data of an office worker. FIG. 7 is an example of seat master data. FIG. 8 is an example of spatial temperature distribution data. FIG. 9 shows an example of recommendation candidate data. FIG. 10 shows an example of distance calculation result data between related parties. FIG. 11 is an example of calculated recommendation data. FIG. 12 is a flowchart showing the flow of the seat recommendation process performed by the seat recommendation device. FIG. 13 is a flowchart showing details of the recommended seat calculation process of the recommended seat calculation unit. FIG. 14 shows an example of a display result of recommendation data.

Below, an example of an embodiment of the disclosed technology will be described with reference to the drawings. Note that the same reference symbols are used for identical or equivalent components and parts in each drawing. Also, the dimensional ratios in the drawings have been exaggerated for the convenience of explanation and may differ from the actual ratios.

The configuration of this embodiment will be described below. FIG. 1 is a block diagram showing the configuration of the seat recommendation device of this embodiment. The seat recommendation device 100 includes an office worker-related data storage unit 102, a seat-related data storage unit 104, a startup unit 110, a recommended seat calculation unit 112, a recommended data storage unit 114, and a display unit 116. Note that in the following description, an example of a user will be an office worker, but the present invention is applicable to users in general who are located in spaces other than an office. The office worker-related data is an example of "user-related data" in this disclosure.

FIG. 2 is a block diagram showing the hardware configuration of the seat recommendation device 100. As shown in FIG. 2, the seat recommendation device 100 has a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a storage 14, an input unit 15, a display interface (I/F) 16, and a communication interface (I/F) 17. Each component is connected to each other so as to be able to communicate with each other via a bus 19.

The CPU 11 is a central processing unit that executes various programs and controls each part. That is, the CPU 11 reads the programs from the ROM 12 or storage 14, and executes the programs using the RAM 13 as a working area. The CPU 11 controls each of the above components and performs various calculation processes according to the programs stored in the ROM 12 or storage 14. In this embodiment, a seat recommendation program is stored in the ROM 12 or storage 14.

ROM 12 stores various programs and data. RAM 13 temporarily stores programs or data as a working area. Storage 14 is composed of a storage device such as a HDD (Hard Disk Drive) or SSD (Solid State Drive), and stores various programs including an operating system, and various data.

The input unit 15 includes a pointing device such as a mouse and a keyboard, and is used to perform various input operations.

The display interface 16 is, for example, a liquid crystal display, and displays various information. The display interface 16 may also function as the input unit 15 by adopting a touch panel system.

The communication interface 17 is an interface for communicating with other devices such as terminals. For this communication, for example, a wired communication standard such as Ethernet (registered trademark) or FDDI, or a wireless communication standard such as 4G, 5G, or Wi-Fi (registered trademark) is used.

The functional components of the seat recommendation device 100 will be described below. Each functional component is realized by the CPU 11 reading out a seat recommendation program stored in the ROM 12 or storage 14, expanding it in the RAM 13, and executing it. The worker-related data storage unit 102 stores, as worker-related data, relationship data between workers, current seat data of the workers, and desired temperature data of the workers. The seat-related data storage unit 104 stores, as seat-related data, spatial temperature distribution data, and seat master data. Examples of the storage manner of each data will be described later.

The start-up unit 110 starts the processing of the recommended seat calculation unit 112 at a specified date and time. The recommended seat calculation unit 112 receives various data from the worker-related data storage unit 102 and the seat-related data storage unit 104 as input, and outputs the calculated recommended seat to the recommended data storage unit 114 as recommended data. The display unit 116 makes it possible to display information on the user interface of a specified device. The display unit 116 receives recommendation data from the recommended data storage unit 114 as input, and displays the seat position of the related user, reference information (temperature conditions of each seat), etc., along with the recommended seat of the recommendation data.

Next, we will explain the recommended seat calculation unit 112. The recommended seat calculation unit 112 has a function of calculating recommendation data that balances proximity between users and temperature comfort.

3 is a block diagram showing the functional configuration of the recommended seat calculation unit 112. The recommended seat calculation unit 112 includes a data acquisition unit 210, a combination unit 220, a temperature difference calculation unit 222, a travel distance calculation unit 224, a recommended candidate generation unit 226, a distance calculation unit 228 between related parties, an optimization calculation unit 230, and an output unit 232. The data acquisition unit 210 includes (1) a relationship data acquisition unit 310, (2) a current seat data acquisition unit 312, (3) a desired temperature data acquisition unit 314, (4) a temperature distribution data acquisition unit 316, and (5) a seat master data acquisition unit 318. The data acquisition unit 210 in the recommended seat calculation unit 112 acquires relationship data between workers, current seat data of the workers, and desired temperature data of the workers from the worker-related data storage unit 102 by each of the units (1) to (3). Meanwhile, each of units (4) and (5) acquires spatial temperature distribution data and seat master data from the seat-related data storage unit 104, respectively.

The recommended seat calculation unit 112 performs processing using various data acquired by the data acquisition unit 210. The acquired worker's current seat data, worker's desired temperature data, spatial temperature distribution data, and seat master data are combined by the combination unit 220. Then, after processing by the temperature difference calculation unit 222, travel distance calculation unit 224, and recommendation candidate generation unit 226, they become input to the related party distance calculation unit 228 and optimization calculation unit 230. On the other hand, relationship data between workers becomes input to the related party distance calculation unit 228, and recommendation result data is output to the recommended data storage unit 114 via the optimization calculation unit 230 and output unit 232. Details of the processing of each unit of the recommended seat calculation unit 112 will be described later in the flow explanation.

Figure 4 is an example of relationship data between workers. For each "worker ID", the "worker ID" of the "related parties of the worker" who is a colleague that the worker with that ID would like to work nearby is stored. Alternatively, the "worker ID" of a colleague that the company recommends working nearby is stored. In other words, the IDs of related parties for each user are stored. Note that related parties associated with workers as shown in Figure 4 are an example of the specified related users of this disclosure. Also, while an example is shown where "related parties of the worker" are stored for each "worker ID", this is not limited to this, and related parties may be associated with some workers.

FIG. 5 is an example of the desired temperature data of an office worker. The preferred temperature at which the office worker feels comfortable is stored for each "office worker ID." The temperature may be obtained by input from the office worker, or the preferred temperature may be estimated based on the average temperature at the seating position where the office worker sits most frequently. The desired temperature data is an example of the "user preferred temperature" of this disclosure.

Figure 6 is an example of data on the current location of an office worker. The location of the office worker is obtained at regular intervals for each "office worker ID" and stored. As in the example, the office can be meshed and the location recorded as a "mesh ID," but the method of recording is not important, and the location can be recorded as two-dimensional coordinate information, for example.

Figure 7 is an example of seat master data. When dividing the inside of an office into meshes and recording them, the X and Y coordinates that represent the position of that mesh, and the number of people that can be accommodated within that mesh are recorded for each "mesh ID" as in the example. For the X and Y coordinates, a specific reference mesh may be set, and relative coordinate information indicating how many meshes away from that mesh on the X and Y axes, respectively, may be recorded. The number of people that can be accommodated is recorded as the number of people that can sit or work within that mesh.

FIG. 8 is an example of spatial temperature distribution data. When recording data by dividing the inside of an office into meshes, the temperature measured, predicted, or estimated in that mesh is recorded as the "reproduced temperature" for each "mesh ID" as in the example. Humidity distribution data is an example of the "spatial temperature distribution in a space including seats" disclosed in this disclosure.

Figure 9 is an example of recommendation candidate data. For each "worker ID" and "mesh ID", the number of people that can be accommodated in that mesh, the temperature difference between the reproduced temperature of that mesh and the preferred temperature of that worker, and the travel distance from that mesh to the mesh where the worker is currently located are recorded. Any scale can be used for the travel distance, such as Euclidean distance or Manhattan distance.

Figure 10 shows an example of distance calculation result data between related parties, which is output from the related parties distance calculation unit 228. All combinations of "office worker ID", "related parties of the office worker" in Figure 4 linked to the "office worker ID", "mesh ID" that is a recommendation candidate for the former, and "mesh ID" that is a recommendation candidate for the latter are recorded. In addition, for each combination, the distance between the former and latter meshes is recorded as the "distance between related parties".

Figure 11 is an example of calculated recommendation data. The recommendation data records the "mesh ID" recommended for each "worker ID."

Next, the operation of the seat recommendation device 100 will be described. FIG. 12 is a flowchart showing the flow of the seat recommendation process by the seat recommendation device 100. The seat recommendation process is performed by the CPU 11 reading out a seat recommendation program from the ROM 12 or storage 14, expanding it into the RAM 13, and executing it.

In step S100, the CPU 11, functioning as the startup unit 110, starts the processing of the recommended seat calculation unit 112.

In step S102, the CPU 11 executes processing as the recommended seat calculation unit 112, and outputs the recommendation data obtained as a result of the processing to the recommendation data storage unit 114.

In step S104, the CPU 11 inputs the recommendation data from the recommendation data storage unit 114 to the display unit 116 and displays it in a predetermined display format.

The recommended seat calculation process in step S102 will now be described. Figure 13 is a flowchart showing the details of the recommended seat calculation process in the recommended seat calculation unit 112.

In step S200, the CPU 11, as the data acquisition unit 210, acquires various data from the worker-related data storage unit 102 and the seat-related data storage unit 104.

In step S202, the CPU 11, as the integration unit 212, combines the worker's current seat data, the worker's desired temperature data, the spatial temperature distribution data, and the seat master data.

In step S204, the CPU 11, as the temperature difference calculation unit 222, calculates the temperature difference between the reproduced temperature of the mesh and the preferred temperature of the worker for the combination of the worker and the mesh.

In step S206, the CPU 11, as the movement distance calculation unit 224, calculates the movement distance from the mesh of the combination to the mesh in which the worker is currently located.

In step S208, the CPU 11, as the recommendation candidate generation unit 226, extracts records for combinations in which the calculated temperature difference or travel distance falls below a preset threshold, and generates recommendation candidate data.

In step S210, the CPU 11, as the related party distance calculation unit 228, combines the recommended candidate data with the relationship data between the workers and generates related party distance calculation result data.

In step S212, the CPU 11, as the optimization calculation unit 230, performs optimization calculations for combinations based on the recommendation candidate data and the distance calculation result data between related parties, and obtains recommendation data that indicates recommended seats. In the optimization calculations in this step, optimization is performed using an objective function, and the details of the mode will be described later.

In step S214, the CPU 11, acting as the output unit 232, outputs the calculated recommendation data to the recommendation data storage unit 114 for storage.

The objective function and constraint equations used in the optimization calculation in step S212 are explained below. The objective function and constraints are used to balance the proximity between users and thermal comfort for the recommended data. In the optimization calculation, a combinatorial optimization calculation for recommended seats is performed using an objective function that represents the good seating arrangement for users, and a constraint on the capacity that is set for each unit that grasps the seating situation, such as a mesh. As an objective function that represents the goodness of the seating arrangement, for example, the proximity between users is used as an index. By using the probability that indicates which seat a user is sitting in in the objective function related to the proximity between users and the constraint related to the capacity of each mesh, it is possible to treat the proximity between colleagues and the number of people seated as expected values and obtain a seating arrangement that takes into account users who do not sit as recommended.

In the optimization calculation, the objective function of the following formula (1-1) is used. The objective function minimizes the sum of the expected travel distance per related person calculated for each user. Note that the objective function is not limited to the expected travel distance, and any objective function that expresses the proximity between related people may be used, and an objective function that maximizes the expected travel distance may be set depending on the expression method.

... (1-1)

Each symbol in the formula will be explained. i: user number, j: mesh number, k: colleague user number, l: colleague mesh number. The user numbers of i and k are numbers of "worker ID". The mesh number is a number of "mesh ID". In addition, X _i,j : a variable of recommendation implementation or not (X _i,j = {0, 1}), C _i : a set of user numbers of colleagues that user i wants to work with (C _i ≠ φ), P _ij : the probability that user i is in mesh j, and d _i,j : the travel distance between mesh j and l. In addition, P _ij is expressed by the auxiliary formula (1-2) below, and represents the probability divided into cases depending on the presence or absence of recommendation implementation. P _ij is an example of "the probability indicating which seat the user is sitting in" in the present disclosure.

... (1-2)

Constraints are explained below in the first to fourth constraints shown in the formulas (2-1) to (2-4). The constraint shown in the formula (2-1) below indicates that the expected number of people in each mesh must be within the capacity of that mesh (first constraint). Note that N _j is the capacity of mesh j.

... (2-1)

The constraint shown in the following formula (2-2) indicates that the mean absolute error between the desired temperature and the reproduced temperature at the recommended destination is within a predetermined range (second constraint). Note that |e _i,j | is the absolute value of the deviation between the desired temperature of user i and the reproduced temperature of mesh j. α is the threshold of the mean absolute error of temperature, and may be a value different from the threshold related to the temperature difference described in step S208 above.

... (2-2)

The constraint shown in the following formula (2-3) indicates that the average movement distance from the user's current position to the recommended destination is within a certain range (third constraint). θ is the movement distance threshold. j' is the current mesh number.

... (2-3)
The constraint shown in the following formula (2-4) is a constraint that the number of recommended destinations per user is one. In the variable (X _i,j ) indicating whether or not a recommendation is implemented, a unique mesh j is assigned to each user i.

... (2-4)

The above is an explanation of each formula used in the optimization calculation. For example, (the second constraint) is a constraint on thermal comfort, (the third constraint) is a constraint on the travel distance from the user's current location, and (the fourth constraint) is a constraint that the recommended destination for each user is unique. By calculating a combination of recommended seats that minimizes the objective function related to the proximity between colleagues under these constraints, it is possible to obtain a combination of seating arrangements that increases the proximity between colleagues while maintaining the thermal comfort of the workers at a certain level. Calculation methods include, but are not limited to, the branch-and-cut method, simulated annealing, tabu search, genetic algorithm, particle swarm optimization, greedy search, and quantum annealing. Note that, although an example has been described in which the proximity between users is treated as an objective function and the thermal comfort is treated as a constraint, the present invention is not limited to this. For example, the proximity between users may be treated as a constraint and the thermal comfort as an objective function, or both the proximity between users and the thermal comfort may be treated as objective functions.

FIG. 14 is an example of the display result of recommendation data. The recommendation data shown in the example is assumed to be displayed on a smartphone or tablet terminal. As the display information, for example, (d1) the position of the recommended seat is displayed on the layout image of the office. As additional information, (d2) the current position of the user in the office and (d3) the position of related parties (seat positions of related users) may be displayed. As reference information, (d4) the user's preferred temperature, (d5) search/setting of related users, etc. may be displayed. In the example of (d4), an interface is provided that allows a request to change the temperature of the space the user is in. As reference information, the temperature situation of each seat may be expressed in a heat map on the layout image. The positions of related parties are an example of "seat positions of related users". This is an example of reference information.

As described above, the seat recommendation device 100 of this embodiment makes it possible to recommend seats that balance proximity between users and thermal comfort.

In the above embodiment, the seat recommendation process executed by the CPU by reading the software (program) may be executed by various processors other than the CPU. Examples of processors in this case include a PLD (Programmable Logic Device) whose circuit configuration can be changed after manufacture, such as an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), and a dedicated electric circuit, such as an ASIC (Application Specific Integrated Circuit), which is a processor having a circuit configuration designed specifically to execute a specific process. The seat recommendation process may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA, etc.). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor devices.

In the above embodiment, the seat recommendation program is pre-stored (installed) in the storage 14, but the present invention is not limited to this. The program may be provided in a form stored in a non-transitory storage medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), or a USB (Universal Serial Bus) memory. The program may also be downloaded from an external device via a network.

The following notes are further provided with respect to the above embodiment.

(Additional Note 1)
Memory,
at least one processor coupled to the memory;
Including,
The processor,
User-related data and seat-related data are input;
The user-related data defines at least a predetermined related user related to the user, and the seat-related data defines temperature information related to the user and the seat,
Output recommendation data indicating recommended seats that satisfy both proximity between users and thermal comfort.
The seat recommendation device is configured as follows.

(Additional Note 2)
A non-transitory storage medium storing a program executable by a computer to execute a seat recommendation process,
User-related data and seat-related data are input;
The user-related data defines at least a predetermined related user related to the user, and the seat-related data defines temperature information related to the user and the seat,
Output recommendation data indicating recommended seats that satisfy both proximity between users and thermal comfort.
Non-transitory storage media.

Claims (7)

User-related data and seat-related data are input;
The user-related data defines at least a predetermined related user related to the user, and the seat-related data defines temperature information related to the user and the seat,
a recommended seat calculation unit that outputs recommendation data indicating a recommended seat that satisfies both proximity between users and thermal comfort;
A seat recommendation device comprising: The seat recommendation device according to claim 1, wherein the recommended seat calculation unit calculates the recommended seat using the user's preferred temperature and the spatial temperature distribution of the space including the seat as the seat-related data. The seat recommendation device according to claim 1, wherein the recommended seat calculation unit calculates the recommended seats by performing a combinatorial optimization calculation of the recommended seats using an objective function that represents the goodness of seating arrangement among users and constraints related to the capacity of the seating arrangement that are determined for each unit that grasps the seating situation. The seat recommendation device according to claim 3, wherein the recommended seat calculation unit applies at least one of the proximity between the users and the thermal comfort in the objective function, and calculates the recommended seat using a probability representing which seat the user is seated in. Further comprising a display unit capable of displaying information on a user interface of a predetermined terminal,
The seat recommendation device according to claim 1 , wherein the display unit displays at least one of reference information including a seat position of the related user and a temperature status of each seat together with the recommended seat. User-related data and seat-related data are input;
The user-related data defines at least a predetermined related user related to the user, and the seat-related data defines temperature information related to the user and the seat,
Output recommendation data indicating recommended seats that satisfy both proximity between users and thermal comfort.
A seat recommendation method in which processing is performed by a computer. A seat recommendation program for causing a computer to function as each part of the seat recommendation device according to any one of claims 1 to 5.