Proposal system, learning device and inference device

Abstract

To objectively and easily provide useful suggestions to support users in managing their buildings. [Solution] The proposal system comprises a boarding and alighting history information acquisition means for acquiring boarding and alighting history information of users of elevators installed in a building, a boarding and alighting history storage means for storing the boarding and alighting history information acquired by the boarding and alighting history information acquisition means, and a proposal means for making proposals regarding the installation of facilities within the building or proposals regarding services for facilities within the building based on the boarding and alighting history information stored in the boarding and alighting history storage means.

Description

[Technical Field]

[0001] The present disclosure relates to a suggestion system, a learning device, and an inference device. [Background technology]

[0002] As a conventional technique, an elevator operation diagnostic device is described in Patent Document 1. The conventional technique described in Patent Document 1 provides improvement measures based on elevator operation data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-070564 Summary of the Invention [Problem to be solved by the invention]

[0004] The conventional technology described in Patent Document 1 has a problem in that it is difficult to objectively and easily provide useful suggestions for the operation of a building to users such as owners or managers.

[0005] The present disclosure is intended to solve the above-mentioned problems. An object of the present disclosure is to realize objective and easy provision of useful suggestions to support building management by users. [Means for solving the problem]

[0006] The proposal system according to the present disclosure includes a boarding and alighting history information acquisition means for acquiring boarding and alighting history information of users of elevators installed in a building, a boarding and alighting history storage means for storing the boarding and alighting history information acquired by the boarding and alighting history information acquisition means, and a proposal means for making proposals regarding the installation of facilities within the building or proposals regarding services for facilities within the building based on the boarding and alighting history information stored in the boarding and alighting history storage means. The learning device disclosed herein is a learning device for a proposal system that makes proposals regarding the installation of facilities within a building or proposals regarding services for facilities within the building by utilizing boarding and alighting history information of users of elevators installed in the building, and includes a data acquisition unit that acquires learning data including attributes of users of the building and proposals that will improve user satisfaction that match the attributes, and a model generation unit that uses the learning data to generate a trained model for inferring proposals from the boarding and alighting history information that includes attribute information that is information on the attributes of the users. The inference device according to the present disclosure is an inference device for a proposal system that makes proposals regarding the installation of facilities in a building or proposals regarding services for the facilities in the building by utilizing information on the boarding and alighting history of users of elevators installed in the building, the inference device including: a data acquisition unit that acquires the boarding and alighting history information including attribute information that is information on the attributes of the users; The data acquisition unit acquired The boarding and alighting history information and a trained model for inferring suggestions that improve user satisfaction that match the attributes. and an inference unit that outputs a suggestion. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to objectively and easily make useful suggestions to support users in managing their buildings. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram showing the overall configuration of a proposed system according to a first embodiment. [Figure 2] 4 is a table showing an example of boarding and alighting history information stored in an information recording unit according to the first embodiment. [Figure 3] 4 is a table showing an example of density information according to the first embodiment. [Figure 4] 1 is a diagram illustrating an example of a hardware configuration of a main part of a proposed system according to a first embodiment. [Figure 5] FIG. 2 is a diagram illustrating a configuration example for realizing the functions of the proposed device according to the first embodiment. [Figure 6]FIG. 10 is a diagram illustrating another example of a learning device that realizes the functions of the proposal device in the first embodiment. [Figure 7] FIG. 2 is a diagram illustrating another example of an inference device that realizes the functions of the proposal device in the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments will be described with reference to the accompanying drawings. In each drawing, the same or corresponding parts are designated by the same reference numerals. In this disclosure, duplicated descriptions will be appropriately simplified or omitted. Note that this disclosure is not limited to the following embodiments and their modifications. Any components described in the following embodiments and their modifications can be freely combined, modified, or omitted within the scope of the spirit of this disclosure.

[0010] Embodiment 1 FIG. 1 is a diagram showing the overall configuration of the proposed system according to the first embodiment. The proposed system according to this embodiment is applied to a building in which an elevator 100 is installed. The proposed system according to this embodiment includes boarding and alighting history information acquisition means for acquiring boarding and alighting history information of the elevator 100 by users 101 of the elevator 100 installed in the building. The boarding and alighting history information in this disclosure means, for example, information on floors traveled to, such as the boarding time of the elevator 100, the boarding floor and the alighting floor, for each user 101. The boarding and alighting history information acquisition means is configured, for example, by an elevator control panel 102 that manages the operation of the elevator 100.

[0011] Furthermore, the proposed system according to this embodiment may include an authentication unit 103, as shown in Fig. 1. The authentication unit 103 acquires attribute information, which is information on the attributes of a user 101 of the elevator 100. The attributes of the user 101 include, for example, gender and age. As an example, the authentication unit 103, together with the elevator control panel 102, constitutes boarding and alighting history information acquisition means. That is, the boarding and alighting history information acquired by the boarding and alighting history information acquisition means may include attribute information in addition to travel floor information.

[0012] The proposed system according to this embodiment includes an information recording unit 104 as an example of boarding and alighting history storage means for storing the boarding and alighting history information acquired by the boarding and alighting history information acquisition means. The information recording unit 104 may be an element constituting the elevator 100 as shown in FIG. 1, or may be provided outside the elevator 100.

[0013] The proposal system according to the present embodiment includes a proposal device 105 as proposal means for making proposals based on the boarding and alighting history information stored in the boarding and alighting history storage means, which is an example of boarding and alighting history storage means that stores the boarding and alighting history information acquired by the boarding and alighting history information acquisition means. The proposal device 105 is installed, for example, in a monitoring room 106 of a building in which the elevator 100 is installed, and makes proposals to users such as the owner or manager of the building to improve the satisfaction of the users 101. The proposal device 105, which is an example of proposal means according to the present disclosure, makes proposals regarding the installation of facilities within the building or proposals regarding services for the facilities within the building.

[0014] The proposal system according to this embodiment uses elevators 100 that form the movement paths of users 101 in a building to acquire boarding and alighting history information, which is information on the flow of users 101. The proposal system according to this embodiment utilizes this boarding and alighting history information to make proposals regarding the installation of facilities within the building or proposals regarding services for the facilities within the building. A proposal system configured in this manner can objectively and easily make useful proposals to support building management by users such as owners or managers. According to this embodiment, for example, it is possible to create proposals for improving the value of buildings and support the acceleration of smart buildings and smart cities.

[0015] As described above, the boarding and alighting history information may include attribute information of the user 101. By making suggestions using the boarding and alighting history information including attribute information, it is possible to make more objective and effective suggestions.

[0016] 2 is a table showing an example of boarding and alighting history information stored in the information recording unit 104 of the first embodiment. As shown in FIG. 2, as an example, the information recording unit 104 stores the boarding and alighting history information as information in which the travel floor information acquired by the elevator control panel 102 and the attribute information acquired by the authentication unit 103 are linked.

[0017] The authentication unit 103 can acquire the attribute information by analyzing image data captured by a camera capable of capturing images of the inside of the elevator car 100 and the inside of the hall. In this example, the attribute information can be acquired without pre-registering personal information of the user 101. In public facilities such as shopping malls or hospitals visited by an unspecified number of users 101, it is preferable to acquire the attribute information by analyzing image data captured by a camera, as in this example.

[0018] Furthermore, the authentication unit 103 may acquire attribute information as information linked to a personal ID that can be acquired by reading a device such as a mobile terminal carried by the user 101 inside the car or at the platform. In this example, attribute information can be acquired with a high degree of reliability. However, personal information must be registered in advance. Therefore, this example is suitable for use in office buildings, schools, apartment buildings, and the like that are visited by specific individuals.

[0019] In this embodiment, the proposal device 105 may generate density information from boarding and alighting history information and make a proposal based on the density information. FIG. 3 is a table showing an example of density information in embodiment 1. In this embodiment, "density information" means information on the number of people getting on and off for each time period on a specific floor. The example in FIG. 3 shows distribution data on the number of people getting off for each hour on a specific floor. Note that "number of people getting on and alighting" in this disclosure may include any of "number of people getting on," "number of people getting off," or "number of people getting on and alighting." The proposal system according to this embodiment makes proposals based on density information, thereby enabling more objective and effective proposals.

[0020] The coarse-grained information may be targeted at a specific attribute of the user 101. For example, the coarse-grained information may be generated for women in their twenties. By making a proposal based on the coarse-grained information targeted at a specific attribute, it becomes possible to make a more targeted and effective proposal.

[0021] The density information is information regarding the number of people staying on each floor in a building during each time period. It is considered that the density information is influenced by existing facilities in the building, such as tenants such as stores or offices. Therefore, for example, the business hours of a tenant may be proposed as a proposal for services of existing facilities in the building. For example, a specific threshold may be set as a standard for the number of passengers boarding or disembarking during each time period on a floor where a target tenant is located, and appropriate business hours may be proposed based on the threshold. For example, for a tenant whose target user 101 attributes are determined, density information targeting the specific target attributes may be generated from boarding and disembarking history information including attribute information, and the tenant's business hours may be proposed based on the density information. According to this example, more appropriate business hours can be proposed.

[0022] For example, if a tenant targeting women in their twenties is located on the fourth floor of a building, density information for the fourth floor is obtained for women in their twenties. Then, for example, a threshold is set to 20 people, and the time periods when the number of passengers getting off on the fourth floor is 20 or more are proposed as business hours. If the obtained density information is the example shown in FIG. 3, for example, the time periods from 7:00 AM to 8:00 PM are proposed as business hours. In this example, it is possible to support the system in setting the business hours to the time periods when there are many users 101 with the target attributes on the floor where the target tenant is located. This can help increase the profits of the tenant. It also has the effect of supporting users 101 to use the tenant efficiently and deploying staff according to the number of users 101 in each time period.

[0023] For example, suppose that information is obtained from the density information that users 101 with a specific attribute are "dense" on a specific floor. In this case, a proposal may be made to the building owner regarding the installation of a facility that matches the preferences of users 101 with this specific attribute. By utilizing the attribute information and density information of the target users, the proposal device 105 can propose an appropriate floor for installing a facility. This makes it possible, for example, to open a store or install equipment in a location where many users 101 with the target attribute gather. In this example, the effect of supporting high profitability of the store or efficient facility use by users 101 can be obtained.

[0024] The boarding and alighting history information acquisition means in the present disclosure may, for example, acquire boarding and alighting history information for another building already installed in the vicinity of the building that is the target of the proposed system. This "another building" may be a building with a different purpose or structure than the building that is the target of the proposed system. This "another building" may, for example, be a public facility such as a station located outside the target building. Alternatively, the boarding and alighting history information acquisition means may, for example, acquire boarding and alighting history information for another building of the same type as the building that is the target of the proposed system. This "another building of the same type" may be a building with a similar purpose and structure near the building that is the target of the proposed system, or it may be a building located at a distance.

[0025] The boarding and alighting history storage means may store boarding and alighting history information for other existing buildings in the vicinity of the building that is the target of the proposal system, or for other buildings of the same type.The proposal means may generate and propose building specification information that will increase the flow of people based on this boarding and alighting history information.This "building specification information" is generated as information that links, for example, attribute information of the user 101, information on facilities within the building, and architectural specifications.This example enables effective proposals based on past performance at the planning stage of constructing a new building.

[0026] Furthermore, when a building that is the target of the proposal system is renovated, the boarding and alighting history information acquisition means may acquire boarding and alighting history information before the renovation, for example. The boarding and alighting history storage means may store boarding and alighting history information before the renovation. The proposal means may then make proposals regarding the installation of facilities within the building or proposals regarding services for the facilities within the building based on the boarding and alighting history information before the renovation. By utilizing past boarding and alighting history information before the renovation, it becomes possible to make proposals with even greater accuracy.

[0027] Even when the entire building is not renovated, the building specifications may be changed, for example, when a tenant withdraws, a new tenant opens, or a new facility is installed. The boarding and alighting history storage means may store boarding and alighting history information before and after the change in the building specifications. The proposal means may, for example, compare the boarding and alighting history information stored in the boarding and alighting history storage means with the boarding and alighting history information before and after the change in the building specifications, and make a proposal based on the change in the boarding and alighting history information. By accumulating performance information while actually operating the building and making proposals using the accumulated performance information, it becomes possible to make even more accurate proposals.

[0028] FIG. 4 is a diagram illustrating an example of the hardware configuration of the main components of the proposed system according to the first embodiment. The functions of the elevator control panel 102, authentication unit 103, information recording unit 104, and proposed device 105, which are the main components of the proposed system, can be realized by processing circuits. The processing circuits include, for example, a ROM 200a (Read Only Memory), a RAM 200b (Random Access Memory), an EEPROM 200c (Electrically Erasable Programmable Read-Only Memory), and a CPU 200d (Central Processing Unit). The ROM 200a stores programs executed on the proposed system. The RAM 200b stores working information, such as temporary storage of communication packet data. The EEPROM 200c stores information such as playback command data and command response data. The CPU 200d executes the programs stored in the ROM 200a. A portion or all of the processing circuits may be configured using dedicated hardware. A part or all of the processing circuitry may be configured by software or firmware.

[0029] In the proposed system according to this embodiment, each device, such as the elevator control panel 102, the authentication unit 103, the information recording unit 104, and the proposed device 105, reads a program recorded on a recording medium and operates according to the program, thereby executing each function. The recording medium on which the program is recorded may be, for example, built into the processing circuit of each device, or may be connected to each device, or may be one from which information is read by a reading device such as a drive of each device. The program may be a software package including multiple pieces of software that run on each of the multiple devices that make up the proposed system.

[0030] Fig. 5 is a diagram showing an example of a configuration for realizing the functions of the proposal device 105 in embodiment 1. The functions of the proposal device 105, which is a main component of the proposal system according to embodiment 1, can be realized by a learning device and an inference device that use known algorithms such as supervised learning or reinforcement learning. Fig. 5 shows an example of a learning device and an inference device when supervised learning is used.

[0031] 5, a learning device that realizes the functions of proposal device 105 includes, for example, a data acquisition unit 107 that acquires learning data including, as input data, attributes of user 101 and proposals that improve the satisfaction of user 101 that match the attributes, and a model generation unit 108 that uses this learning data consisting of a combination of both data to generate a trained model for inferring proposals from boarding and alighting history information including attribute information. The trained model generated by model generation unit 108 is stored in storage unit 109.

[0032] In addition, the inference device that realizes the functions of the proposal device 105 includes, for example, a data acquisition unit 110 that acquires boarding and alighting history information including attribute information of the user 101, and an inference unit 111 that outputs a proposal from the boarding and alighting history information acquired by the data acquisition unit 110 and a learned model stored in the memory unit 109.

[0033] For example, the proposal device 105 generates coarse and fine information targeting specific attributes from boarding and alighting history information including attribute information, and makes proposals using a trained model stored in the memory unit 109 to improve the satisfaction of the dense attributes and users 101 who match these attributes.

[0034] 6 is a diagram showing another example of a learning device that realizes the functions of the proposal device 105 in Embodiment 1. FIG. 7 is a diagram showing another example of an inference device that realizes the functions of the proposal device in Embodiment 1.

[0035] Reinforcement learning is used in the example of Fig. 6. In the example of Fig. 6, a data acquisition unit 107 constituting the learning device acquires learning data including, as input data, information on changes in boarding and alighting history information before and after adoption of a proposal by the proposal device 105 and information on the adopted proposal. A model generation unit 108 calculates a reward using the change in the density information as a reward criterion, generates a trained model, and updates the trained model stored in a storage unit 109.

[0036] 7, a data acquisition unit 110 constituting the inference device acquires building information such as the location and specifications of the building that is the target of the proposed system as input data. Then, an inference unit 111 outputs a proposal by citing, for example, boarding and alighting history information of another building of the same type as the building that is the target of the proposed system.

[0037] Various aspects of the present disclosure are summarized below as appendices.

[0038] (Appendix 1) an elevator boarding / alighting history information acquisition means for acquiring information on the boarding / alighting history of users of elevators installed in the building; boarding / alighting history storage means for storing the boarding / alighting history information acquired by the boarding / alighting history information acquisition means; a proposal means for making a proposal regarding installation of a facility within the building or a proposal regarding a service for the facility within the building based on the boarding and alighting history information stored in the boarding and alighting history storage means; A proposal system equipped with (Appendix 2) The proposed system described in Appendix 1, characterized in that the boarding and alighting history information includes attribute information that is information on the attributes of the user. (Appendix 3) The proposal system described in Appendix 2, characterized in that the proposal means makes proposals based on information on the number of passengers boarding and alighting per time period targeting specific attributes on specific floors. (Appendix 4) The proposal system according to claim 3, wherein the proposal means proposes business hours for tenants. (Appendix 5) The proposal system described in any one of Supplementary Note 1 to Supplementary Note 4, characterized in that the proposal means generates and proposes information on building specifications that will increase pedestrian flow based on the boarding and alighting history information of other buildings already installed in the vicinity of the building or other buildings of the same type. (Appendix 6) The proposal system according to any one of appendices 1 to 5, wherein the proposal means makes proposals regarding the installation of facilities within the building or proposals regarding services for facilities within the building based on the boarding and alighting history information for the building before renovation. (Appendix 7) The proposal system according to any one of Supplementary Note 1 to Supplementary Note 6, wherein the proposal means makes proposals regarding the installation of facilities within the building or proposals regarding services for facilities within the building based on changes in the boarding and alighting history information before and after a change in the specifications of the building. (Appendix 8) A learning device for a proposal system that makes proposals regarding the installation of facilities in a building or proposals regarding services for the facilities in the building by utilizing elevator user boarding and alighting history information, a data acquisition unit that acquires learning data including attributes of users of the building and proposals that improve user satisfaction that match the attributes; a model generation unit that generates a trained model for inferring suggestions from the boarding and alighting history information including attribute information that is information on the attributes of the user, using the training data; A learning device equipped with (Appendix 9) An inference device for a proposal system that makes proposals regarding installation of facilities in a building or proposals regarding services for the facilities in the building by utilizing elevator user boarding and alighting history information, a data acquisition unit that acquires the boarding and alighting history information including attribute information that is information on the attributes of the user; an inference unit that outputs a proposal based on the boarding and alighting history information including the attribute information; An inference device comprising: [Explanation of symbols]

[0039] 100 elevator, 101 user, 102 elevator control panel, 103 authentication unit, 104 information recording unit, 105 proposed device, 106 monitoring room, 107 data acquisition unit, 108 model generation unit, 109 memory unit, 110 data acquisition unit, 111 inference unit, 200a ROM, 200b RAM, 200c EEPROM, 200d CPU

Claims

1. an elevator boarding / alighting history information acquisition means for acquiring information on the boarding / alighting history of users of elevators installed in the building; boarding / alighting history storage means for storing the boarding / alighting history information acquired by the boarding / alighting history information acquisition means; a proposal means for making a proposal regarding the installation of a facility within the building or a proposal regarding a service for the facility within the building based on the boarding and alighting history information stored in the boarding and alighting history storage means; A proposal system equipped with

2. The proposal system according to claim 1 , wherein the boarding and alighting history information includes attribute information that is information about the attributes of the user.

3. The suggestion system according to claim 2, wherein the suggestion means makes a suggestion based on information on the number of passengers getting on and off for each time period on a specific floor and targeting the specific attribute.

4. The proposal system according to claim 3 , wherein the proposal means proposes business hours for tenants.

5. The proposal system described in claim 1 or claim 2, characterized in that the proposal means generates and proposes information on building specifications that will increase pedestrian flow based on the boarding and alighting history information of other buildings already installed in the vicinity of the building or other buildings of the same type.

6. The proposal system according to claim 1 or claim 2, wherein the proposal means makes proposals regarding the installation of facilities within the building or proposals regarding services for facilities within the building based on the boarding and disembarking history information for the building before renovation.

7. The proposal system according to claim 1 or claim 2, wherein the proposal means makes proposals regarding the installation of facilities within the building or proposals regarding services for facilities within the building based on changes in the boarding and disembarking history information before and after changes to the specifications of the building.

8. The proposal system described in Claim 2, characterized in that the proposal means makes proposals that will improve the satisfaction of users who match the attributes.

9. The proposal system described in Claim 1, characterized in that the proposal means makes proposals based on density information, which is information on the number of passengers boarding and alighting at a specific floor per time period.

10. The proposed system described in claim 1 or claim 2, characterized in that the boarding and alighting history information includes floor information, which is information on boarding time, boarding floor and alighting floor.

11. A learning device for a proposal system that makes proposals regarding the installation of facilities in a building or proposals regarding services for the facilities in the building by utilizing elevator user boarding and alighting history information, a data acquisition unit that acquires learning data including attributes of users of the building and proposals that improve user satisfaction that match the attributes; a model generation unit that generates a trained model for inferring suggestions from the boarding and alighting history information including attribute information that is information on the attributes of the user, using the training data; A learning device equipped with

12. An inference device for a proposal system that makes proposals regarding installation of facilities in a building or proposals regarding services for the facilities in the building by utilizing elevator user boarding and alighting history information, a data acquisition unit that acquires the boarding and alighting history information including attribute information that is information on the attributes of the user; an inference unit that outputs a proposal based on the boarding and alighting history information acquired by the data acquisition unit and a trained model for inferring a proposal that will improve satisfaction of users who match the attributes; An inference device comprising:

Images