Information processing system

The system optimizes home appliance settings through clustering and user-specific adjustment, addressing the lack of convenience in existing systems by automatically reducing power consumption.

JP2025161409APending Publication Date: 2025-10-24TOSHIBA LIFESTYLE PROD & SERVICES CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2024064571
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-04-12
Publication Date
2025-10-24

AI Technical Summary

Technical Problem

Existing information processing systems for home appliances lack the ability to improve convenience by optimizing power consumption settings without user intervention.

Method used

An information processing system that includes a server to sort and cluster home appliance setting information, adjust settings based on user-specific information, and dynamically change criteria based on user behavior, using machine learning to optimize power consumption.

Benefits of technology

Enables automatic adjustment of home appliance settings to reduce power consumption without user awareness, enhancing convenience and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025161409000001_ABST
    Figure 2025161409000001_ABST
Patent Text Reader

Abstract

To provide an information processing system enabling improvement of convenience.SOLUTION: An information processing system classifies a plurality of combinations of household electrical appliance setting information acquired from household electrical appliances of a plurality of users into a plurality of aggregations; selects a combination of household electrical appliance setting information from an aggregation corresponding to a predetermined user on the basis of a first standard; in performing setting to a household electrical appliance possessed by the predetermined user on the basis of individual household electrical appliance setting information in the selected combination of household electrical appliance setting information, adjusts a setting content on the basis of unique information on the household electrical appliance possessed by the predetermined user; and when the predetermined user changes the setting content of the household electrical appliance after setting is performed to the household electrical appliance possessed by the predetermined user, determines whether or not to select a combination of household electrical appliance setting information using a second standard instead of the first standard so as to select a different combination of household electrical appliance setting information on the basis of a degree of the change of the setting content of the household electrical appliance by the predetermined user.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] FIELD An embodiment of the present invention relates to an information processing system. [Background technology]

[0002] The settings of home appliances connected to a network are sometimes updated, and improvements in convenience are expected for information processing systems that include such appliances. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2019 / 198129 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the present invention is to provide an information processing system that can improve convenience. [Means for solving the problem]

[0005] The information processing system of the embodiment includes a first processing unit that performs a first process of sorting multiple combinations of home appliance setting information acquired from home appliances of multiple users into multiple collections; a second processing unit that performs a second process of selecting a combination of home appliance setting information from the collection corresponding to a predetermined user based on a predetermined first criterion, and adjusting the setting contents based on unique information of the home appliance owned by the predetermined user when configuring the home appliance owned by the predetermined user based on individual home appliance setting information in the selected combination of home appliance setting information; and a third processing unit that performs a third process of determining whether to select a combination of home appliance setting information based on a second criterion instead of the predetermined first criterion, based on the degree to which the predetermined user changed the setting contents of the home appliance, so that a different combination of home appliance setting information is selected in the second process, if the predetermined user changes the setting contents of the home appliance after configuring the home appliance owned by the predetermined user through the second process. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a diagram showing an example of the overall configuration of an information processing system according to an embodiment. [Figure 2] FIG. 10 is a first diagram for explaining the setting information acquisition process performed by the server of the embodiment. [Figure 3] FIG. 2 is a second diagram for explaining the setting information acquisition process performed by the server of the embodiment. [Figure 4] FIG. 10 is a third diagram for explaining the setting information acquisition process performed by the server of the embodiment. [Figure 5] FIG. 6 is a diagram for explaining an automatic setting change process performed by the server according to the embodiment. [Figure 6] FIG. 6 is a diagram for explaining a setting adjustment process performed by the server according to the embodiment. [Figure 7] FIG. 10 is a diagram illustrating an example of a screen for selecting a home electric appliance that is a target of an automatic setting change process performed by the terminal device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] An information processing system 1 according to an embodiment will be described below with reference to the drawings. In the following description, components having the same or similar functions will be assigned the same reference numerals. Duplicate descriptions of those components may be omitted. In this specification, "based on XX" means "based on at least XX" and may include a case where the component is based on other elements in addition to XX. Furthermore, "based on XX" is not limited to the direct use of XX, but may also include a case where the component is based on XX after calculation or processing. In this specification, "XX or YY" is not limited to either XX or YY, but may include both XX and YY. This also applies when there are three or more selective elements. XX and YY are arbitrary elements (e.g., arbitrary information).

[0008] In this specification, "acquisition" is not limited to active acquisition by sending a transmission request, but may also include acquisition by passively receiving information transmitted from another device. "Acquisition" may also include acquisition by performing calculations or processing on information obtained from outside to generate and obtain the desired information. In this specification, "use" and "utilization" are used with essentially the same meaning and can be read interchangeably. In this specification, "database" is abbreviated as "DB."

[0009] <Embodiment> (Overall composition) 1 is a diagram illustrating an example of the overall configuration of an information processing system 1 according to an embodiment. The information processing system 1 is a system that performs processing to set a home appliance 100 owned by a user U to reduce power consumption without the user U being aware of it, and adjusts the setting. As shown in FIG. 1, the information processing system 1 includes a plurality of home appliances 100, a server 200, and a home appliance management application program APP of a terminal device 300. The network NW, which will be described later, may be, for example, the Internet, a cellular network, a Wi-Fi network, a low power wide area network (LPWA), a wide area network (WAN), a local area network (LAN), or other public or dedicated lines, depending on the situation.

[0010] The home appliance 100 is an electrical appliance primarily used at home. The home appliance 100 is used by a user U and is placed in the user U's residence. The home appliance 100 is connected to a network NW via a wireless router WR and a modem M installed in the user U's residence. The home appliance 100 can communicate with a server 200 via the network NW. The home appliance 100 may be, but is not limited to, a refrigerator 100A, a refrigerator 100B, an air conditioner 100C, a washing machine 100D, or a video device 100E. The washing machine 100D may also include a washer-dryer, a dryer, or a closet-type clothing processing machine. In the following description, for convenience, an "air conditioner" may be referred to as an "air conditioner."

[0011] The terminal device 300 is a computer used by the user U. The terminal device 300 is, for example, a mobile terminal device such as a smartphone or a tablet terminal device. However, the terminal device 300 is not limited to a mobile terminal device and may be a personal computer or the like. The terminal device 300 includes, for example, a display device 301 (an example of a display unit), an input device 302, and a communication unit 303. The display device 301 has a display screen 301a capable of displaying various information. The input device 302 can accept input from the user U. The input device 302 is, for example, a touch panel provided on top of the display screen 301a of the display device 301. The input device 302 may include a camera, a microphone, and the like provided in the terminal device 300. The communication unit 303 is a communication module capable of wireless communication. The communication unit 303 is connected to the network NW via a wireless router WR and a modem M or directly. The communication unit 303 can communicate with the home appliance 100 or the server 200 via the network NW.

[0012] The server 200 performs a setting information acquisition process, an automatic setting change process, and a setting adjustment process. Next, the processes performed by the server 200 will be described.

[0013] (Setting information acquisition process) First, the setting information acquisition process performed by the server 200 will be described. The setting information acquisition process is a process for acquiring setting information. FIG. 2 is a first diagram for explaining the setting information acquisition process performed by the server 200 according to the embodiment. The server 200 acquires each setting information (an example of home appliance setting information) of each home appliance 100 of each user U via the network NW. The server 200 stores the acquired setting information of each home appliance 100 of each user U as a user DB (DataBase).

[0014] For example, the user DB includes the setting contents for each time of each home electric appliance 100 owned by the user U as a combination of data for each user U. In the example shown in Fig. 2, the user DB includes the setting contents for each time of each home electric appliance 100 for each user identifier.

[0015] More specifically, as shown in Fig. 2, the user DB of user U with user identifier A000001 contains information that the user owns home appliance A and home appliance B, but does not own home appliances X1 to X3. The user DB of user U with user identifier A000001 also contains hourly setting details for home appliance A and home appliance B owned by user U. Note that user U does not own home appliances X1 to X3. Therefore, the hourly setting details for each of home appliances X1 to X3 are left blank.

[0016] 3 is a second diagram illustrating the setting information acquisition process performed by the server 200 according to the embodiment. Next, the server 200 performs dimension reduction on the data with N dimensions contained in the user DB, thereby changing the data to data with N-α dimensions. Note that the method used by the server 200 to perform dimension reduction may be any method that can obtain the desired results.

[0017] 4 is a third diagram illustrating the setting information acquisition process performed by the server 200 according to the embodiment. Next, the server 200 performs clustering on the data with N-α dimensions, for example, using a DBSCAN (Density-based spatial clustering of applications with noise) algorithm.

[0018] The server 200 performs clustering to group users (in the example shown in FIG. 4, the users are grouped into group A and group B). The server 200 sorts the group to which the user U belongs (group A in the example shown in FIG. 4) by the amount of power consumption. The server 200 extracts the identifier of the user with the smallest amount of power consumption in the group to which the user U belongs. The server 200 then acquires the setting information of each home electric appliance 100 associated with the extracted user identifier. This completes the setting information acquisition process performed by the server 200.

[0019] (Automatic setting change processing) Next, the automatic setting change process performed by the server 200 will be described. The automatic setting change process is a process in which the setting information acquired by the setting information acquisition process is applied to the home appliance 100 without the user U being aware of it. FIG. 5 is a diagram for explaining the automatic setting change process performed by the server 200 of the embodiment. The server 200 generates setting information Y for the home appliance 100 of the user U from setting information X for the home appliance 100 of a user other than the user U, using a trained model such as a neural network as shown in FIG. 5.

[0020] For example, if the home appliance 100 corresponding to the acquired setting information X is the same as the home appliance 100 of the user U, the server 200 applies the value of the setting information X to the setting information Y as is.

[0021] Furthermore, for example, when the home appliance 100 corresponding to the acquired setting information X is different from the home appliance 100 of the user U, the server 200 converts the value of the setting information X into a value applicable to the home appliance 100 of the user U using a function or a learned model learned in advance, and sets the converted value as setting information Y. Note that in the case of prior learning, inputs are the setting information X of the home appliance 100 of the other user, model information of the home appliance 100 of the other user, and model information of the home appliance 100 of the user U. Furthermore, output is the setting information Y of the home appliance 100 of the user U.

[0022] Furthermore, for example, the server 200 may periodically review the setting information Y in a direction to save power based on the lifestyle pattern of the user U. In this case, the server 200 may use a different function or learning model. Furthermore, for example, the server 200 may generate a learning model for each home appliance 100.

[0023] Here, the training data for generating the trained model will be described. Server 200 prepares a large amount of training data, for example, in which the inputs are setting information for home appliance A, setting information for home appliance B, the model of home appliance A, the model of home appliance B, the model of home appliance A', and the model of home appliance B', and the output is setting information for home appliance A' and setting information for home appliance B' (setting values ​​that are expected to consume similar amounts of power through calculation or testing). The training data input is input to a learning model, and weighting coefficients in the learning model are adjusted using a technique such as backpropagation so that the output of the training data is output from the learning model. A learning model in which weighting coefficients are adjusted using training data in this way is a trained model. This trained model can convert setting information for home appliance A and home appliance B owned by another user into setting information for home appliance A' and home appliance B' owned by user U.

[0024] The training data input may include information (date, month, season, etc.) corresponding to the time when the setting information of home appliance A and home appliance B was acquired, and information (date, month, season, etc.) corresponding to the time when the settings of home appliance A' and home appliance B' are expected to be made. This makes it possible to output more appropriate data if the time when the data of other users input to the trained model was acquired differs from the time when user U currently uses the home appliances.

[0025] The server 200 sets the setting information output by the trained model in the home appliance 100 owned by the user U. The above is the automatic setting change process performed by the server 200.

[0026] (Settings adjustment process) Next, the setting adjustment process performed by the server 200 will be described. The setting adjustment process is a process for adjusting (changing) the settings that have been changed by the automatic setting change process. Fig. 6 is a diagram for explaining the setting adjustment process performed by the server 200 of the embodiment. Fig. 6 is a diagram showing an example of the processing flow of the server 200. Here, the setting adjustment process performed by the server 200 will be described with reference to Fig. 6.

[0027] The server 200 performs the setting information acquisition process and the automatic setting change process described above (step S1). The server 200 determines whether or not the user has made a setting change request for a predetermined function (step S2). If the server 200 determines that the user has not made a setting change request for the predetermined function (NO in step S2), the server 200 terminates the process. If the server 200 determines that the user has made a setting change request for the predetermined function (YES in step S2), the server 200 determines whether or not the requested change amount for the setting value for the predetermined function is equal to or greater than a predetermined threshold (step S3). Note that instead of the setting value, setting contents such as large, medium, and small may be used. In this case, a value between large and medium, a value between medium and small, and a value between large and small may each be the predetermined threshold. Note that instead of the setting value, setting contents such as strong, medium, and weak may be used. In this case, a value between strong and medium, a value between medium and weak, and a value between strong and weak may each be the predetermined threshold.

[0028] When the degree to which the predetermined user has changed the setting contents of the home appliance is less than a predetermined threshold, server 200 (an example of a fifth processing unit) executes a process (an example of a fifth processing unit) of selecting a combination of home appliance setting information using the second criterion instead of the predetermined first criterion by the second processing. For example, when server 200 determines that the amount of change requests for setting values ​​for a predetermined function is less than a predetermined threshold (NO in step S3), server 200 executes a setting information acquisition process (step S4) that emphasizes similarity with the setting value corresponding to the setting change request.

[0029] For example, the server 200 selects the setting information of a user whose setting values ​​are closest to those corresponding to the setting change request (that is, whose lifestyle is most similar) from among the setting information of a plurality of users who consume little power.

[0030] Specifically, for example, suppose that the server 200 changes the refrigerator compartment temperature setting from medium to low through the automatic setting change process, but the user U later changes it back to medium. Here, the power consumption and refrigerator compartment temperature setting information of the top three users in group A to which user U belongs, when sorted in ascending order of power consumption, are as follows: User A: (Power consumption: 10 kW, Refrigerator temperature setting: Low, Freezer temperature setting: Medium, Sterilization: ON) User B: (Power consumption: 12 kW, Refrigerator temperature setting: Medium, Freezer temperature setting: Medium, Sterilization: ON) User C: (Power consumption: 15 kW, Refrigerator temperature setting: High, Freezer temperature setting: High, Sterilization: OFF) In this case, user A, who consumes the least amount of power, would normally be selected, but if the setting information acquisition process is performed with emphasis on the similarity with the setting value corresponding to the setting change request, user B will be selected.

[0031] As another specific example, suppose that the server 200 changes the air conditioner temperature setting at 4 p.m. from 22° C. to 25° C. through the automatic setting change process. Here, the power consumption and air conditioner temperature at 4 p.m. of the top three users in group A to which user U belongs, when sorted in ascending order of power consumption, are as follows: User A: (Power consumption: 10 kWh, air conditioner temperature at 4 p.m.: 22°C) User B: (Power consumption: 12 kWh, air conditioner temperature at 4 p.m.: 24.5°C) User C: (Power consumption: 15 kWh, air conditioner temperature at 4 p.m.: 23°C) In this case, user A would normally be selected, but if the setting information acquisition process is performed so as to emphasize the similarity with the setting value corresponding to the setting change request, user B will be selected.

[0032] Furthermore, if the server 200 determines that the amount of requested change in the setting value for a given function is equal to or greater than a given threshold (YES in step S3), it determines whether the user changed the setting value of the given function back within a certain period of time (an example of within the certain period of time) after the setting change request (step S5). In the example of changing the set temperature of an air conditioner described below, the "certain period of time" is set to two hours as an example, but it may be adjusted appropriately as long as it is possible to distinguish whether the setting change request is due to a temporary reason (e.g., after returning home from a cold weather, the temperature may be set higher than usual to heat the air conditioner quickly). The "certain period of time" may also vary depending on the type of home appliance. In the case of an air conditioner, the "certain period of time" may be set to, for example, one-fourth or less of the time of day excluding sleeping time, preferably between one and three hours.

[0033] If the server 200 (an example of a fourth processing unit) determines that the user has not changed the setting value of a specified function within a certain time period after the setting change request (NO in step S5), it performs an automatic setting change process that emphasizes the similarity with the setting value of the specified function (step S6).

[0034] For example, the server 200 may consider that the settings made by the automatic setting change process are far removed from the user's lifestyle, and may modify the home appliance control plan so that the user's settings take top priority in areas where the user has made significant setting changes, and so that the values ​​are as close as possible to the user's requested setting changes.

[0035] Specifically, for example, suppose that the server 200 performs an automatic setting change process, changing the refrigerator compartment temperature setting from medium to low, but that the user U later changes it to high. Also, suppose that the specified time (e.g., 3 hours) setting is not restored. Here, the AI ​​model may learn to set the refrigerator temperature setting to high, and adjust the weight and bias. Alternatively, the refrigerator compartment temperature setting may simply be set to high.

[0036] Furthermore, if the air conditioner's set temperature at 4 p.m. is changed from 22°C to 28°C and has not been lowered below 28°C even after two hours have passed, the learning model is adjusted so that the air conditioner's set temperature at 4 p.m. is closer to 28°C than 22°C (i.e., the bias and weights are adjusted through learning). This can be achieved by changing all 4 p.m. temperatures in the training data used in supervised learning during the initial learning to 28°C and retraining the AI ​​model. Note that the air conditioner's set temperature at 4 p.m. may also be forcibly set to 28°C or a value closer to 28°C than 22°C.

[0037] Furthermore, if the server 200 determines that the user has changed the setting value of a predetermined function back after the setting change request (YES in step S5), the server 200 performs a normal automatic setting change process (step S7).

[0038] The home appliance 100 to be subjected to the automatic setting change process may be selectable by the user. FIG. 7 is a diagram illustrating an example of a screen for selecting the home appliance 100 to be subjected to the automatic setting change process performed by the terminal device 300 according to the embodiment. For example, as shown in FIG. 7, a list of the home appliances 100 of the user U is displayed on the terminal device 300, and the user U performs an operation to select the home appliance 100 to be subjected to the automatic setting change process. The terminal device 300 transmits information about the selected home appliance 100 to the server 200. This allows the server 200 to perform the automatic setting change process only on the home appliances 100 selected by the user U. For appliances such as refrigerator B (wine cellar), the preservation quality of wine may be more important than saving energy. Therefore, the appliance can be excluded from the update targets. Even if the power consumption of a certain home appliance owned by the user U increases as a result of the update, it is sufficient as long as the total power consumption of all home appliances is reduced.

[0039] (advantage) The information processing system 1 according to an embodiment of the present disclosure has been described above. In the information processing system 1, the server 200 (an example of a first processing unit) performs a first process of sorting a plurality of combinations of home appliance setting information acquired from home appliances of a plurality of users into a plurality of collections. The server 200 (an example of a second processing unit) selects a combination of home appliance setting information from the collection corresponding to a predetermined user based on a predetermined first criterion, and performs a second process of adjusting the setting contents based on the specific information of the home appliance owned by the predetermined user when configuring the home appliance owned by the predetermined user based on each of the home appliance setting information in the selected combination of home appliance setting information. The server 200 (an example of a third processing unit) performs a third process of determining whether to select a combination of home appliance setting information based on a second criterion instead of the predetermined first criterion, based on the degree to which the predetermined user changed the setting contents of the home appliance, so that a different combination of home appliance setting information is selected in the second process. This information processing system 1 enables the user U to set and adjust the settings to reduce the amount of power consumption of the home appliance 100 owned by the user U without the user U being aware of the setting. In other words, this information processing system 1 can improve convenience.

[0040] Note that, in another embodiment of the present disclosure, some of the functions of the first processing unit, the second processing unit, the third processing unit, the fourth processing unit, and the fifth processing unit possessed by the server 200 according to the embodiment of the present disclosure may be possessed by the home appliance 100 or the terminal device 300. Furthermore, in another embodiment of the present disclosure, if the information processing system 1 includes a dedicated control device (such as a home gateway) for a smart home separate from the home appliance 100, the server 200, and the terminal device 300, some of the functions of the first processing unit, the second processing unit, the third processing unit, the fourth processing unit, and the fifth processing unit possessed by the server 200 according to the embodiment of the present disclosure may be possessed by the dedicated control device.

[0041] Several embodiments have been described above. However, the embodiments are not limited to the above examples. For example, the above-described embodiments can be realized by appropriately combining them.

[0042] Each functional unit included in home appliance 100, server 200, and terminal device 300 is realized by one or more hardware processors, such as a CPU (Central Processing Unit), executing a program. However, some or all of these functional units may be realized by hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array), or may be realized by a combination of software and hardware.

[0043] The storage unit is realized by a combination of RAM (Random Access Memory), ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable ROM), HDD (Hard Disk Drive), SSD (Solid State Drive), and the like.

[0044] According to at least one of the embodiments described above, the information processing system 1 can change the setting to a lower power consumption without the user being aware of it, and can further change the setting. With such a configuration, convenience can be improved.

[0045] Although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as the inventions described in the claims and their equivalents. [Explanation of symbols]

[0046] 1...information processing system, 100...home appliance, 200...server, 300...terminal device

Claims

1. a first processing unit that executes a first process of sorting a plurality of combinations of home appliance setting information acquired from home appliances of a plurality of users into a plurality of collections; a second processing unit that selects a combination of home appliance setting information from a collection corresponding to a predetermined user based on a predetermined first criterion, and when configuring a home appliance owned by the predetermined user based on individual home appliance setting information in the selected combination of home appliance setting information, executes a second processing that adjusts setting content based on unique information of the home appliance owned by the predetermined user; a third processing unit that executes a third processing to determine whether to select a combination of home appliance setting information based on a second criterion instead of the predetermined first criterion, based on a degree to which the predetermined user has changed the setting content of the home appliance, so that a different combination of home appliance setting information is selected in the second processing, when the predetermined user has changed the setting content of the home appliance after the second processing has been performed on the home appliance owned by the predetermined user; An information processing system comprising:

2. a fourth processing unit that, when adjusting the setting content by the second processing, executes a fourth processing to adjust the setting content by the second processing so as to more closely approximate the setting content of the home appliance after the change by the specified user, if the setting content of the home appliance is not restored to a state before the change within a specified time after the change by the specified user; The information processing system according to claim 1 .

3. a fifth processing unit that executes a fifth process of selecting a combination of home appliance setting information based on the second criterion instead of the first criterion by the second process when the degree to which the predetermined user has changed the setting content of the home appliance is less than a predetermined threshold; Equipped with The second criterion is a criterion for selecting a combination of home appliance setting information having setting contents that are more similar to setting contents changed by the predetermined user than the first criterion.

3. The information processing system according to claim 1.

Citation Information

Patent Citations

  • Control system, air conditioner and server

    WO2019198129A1