JP2019175109A - Prediction control unit, prediction control system, and prediction control method - Google Patents

Abstract

An object of the present invention is to provide a prediction control device and a prediction control device capable of predicting the home status of a facility with higher accuracy even if the facility cannot acquire the energy information as well as a facility capable of acquiring energy information. A system and a predictive control method are provided. Kind Code: A1 Abstract: Attribute information about a target person to be visited by a visitor is stored, energy information consumed in a facility where the target person can stay at home is measured by a meter, and the energy information is acquired from the meter. Based on this energy information, the home situation of the subject at the time when the energy information is measured is predicted. Further, based on the predicted home situation and attribute information on the subject of the home situation, prediction reference data used for home prediction of another subject associated with the attribute information is created, and energy information is created. When the target cannot be acquired, the home situation of the target person is predicted with reference to the prediction reference data based on the attribute information of the target person. [Selection diagram] Fig. 1

Description

  The present invention relates to a predictive control device, a predictive control system, and a predictive control method.

  In the case of collection, delivery, delivery, etc. of various products (including documents), delivery companies may visit their homes, and in order to check the various conditions of residents (including health conditions, etc.) May visit home.

  Although it is possible for a visitor or the like to make a visit with a appointed date and time with a resident or guardian in advance, a sudden visit may be required. In the latter case, the number of times when the resident is not at home (at the time of absence) is overwhelmingly larger than when the resident is away from home, making contact with the intended resident and making a wasteful effort.

  This leads to a decrease in visit efficiency, and the originally required processing (delivery, status confirmation, etc.) is delayed.

  For this reason, in order to perform processing more efficiently in scenes where sudden visits are unavoidable, a technique has been disclosed in which a home situation is predicted and a visit can be made during a time when there is a high tendency to stay.

JP 2012-181789 A JP 2017-62765 A JP 2003-288442 A

  The above-mentioned Patent Document 1 is a technique for calculating the home probability, and calculates information indicating the home situation using information on the power consumption detected by the automatic meter-reading system. Further, it is disclosed that the home probability is calculated in consideration of the behavioral characteristics of each household.

  Further, Patent Document 2 makes it possible to predict the presence or absence of a person with high accuracy, and obtains building power data at a certain first time to obtain the first time. In addition, it is predicted whether or not the person is in the building at the first time from the correspondence relationship between the power data of the past building and the information indicating whether or not the person is actually in the building.

  As described above, Patent Document 1 and Patent Document 2 describe predicting whether a person is at home using information about power.

  In addition, Patent Document 3 calculates and predicts a home date and time that is likely to be at home based on visit history data.

  In such a prior art, it is difficult to predict being at home in an environment in which information on electric power cannot be acquired particularly in Patent Document 1 and Patent Document 2, and in Patent Document 3, past visit history data is necessary. However, it is not always possible to predict the at-home situation, and even if the prediction can be made, the prediction result has low accuracy.

  The present invention relates to a prediction control apparatus and a prediction device that can predict the home status of a facility with higher accuracy even in a facility that can acquire energy information as well as a facility that can acquire energy information. It is an object to provide a control system and a predictive control method.

  Therefore, the present invention makes it possible to plan a more optimal visit schedule and call schedule.

  In order to achieve the above object, a predictive control device according to claim 1 of the present invention includes attribute information storage means for storing attribute information related to a target person to be visited by a visitor, and a facility where the target person can be at home. Energy information to be consumed is measured by a meter, acquisition means for acquiring the energy information from the meter, and based on the energy information acquired by the acquisition unit, the target person at the time of measuring the energy information The attribute information corresponds to the first at-home situation predicting means for predicting the at-home situation, the at-home situation predicted by the first at-home situation predicting means, and the attribute information on the target person in the at-home situation. Creating means for creating prediction reference data used for home prediction of another attached target person, and when the energy information of the facility cannot be acquired, the target person The home situation, characterized by comprising a second home situation prediction means for predicting with reference to the predictive reference data based on the attribute information of the subject to be stored in the attribute information storage unit.

  Further, the prediction control apparatus according to claim 2 of the present invention further comprises a visit history storage means for storing a visit history of the subject person to the facility with respect to the invention of claim 1, and the visit history is stored in the visit history. Includes a case where the presence or absence of a visit to the facility of the subject is stored and a case where the presence or absence of the visit is not stored.

  According to a third aspect of the present invention, in the prediction control device according to the second aspect of the present invention, the first at-home condition prediction means is the visit history storage means together with the energy information of the subject. The at-home situation of the target person is predicted using the stored visit history of the target person to the facility.

  According to a fourth aspect of the present invention, there is provided a predictive control device according to the second aspect, wherein the second at-home condition predicting unit cannot acquire the energy information in the facility and the visit is made. The present invention is characterized in that when the visit history of the subject person's visit to the facility is not stored in the history storage means, the home situation of the subject person is predicted.

  According to a fifth aspect of the present invention, there is provided a predictive control device according to the first or fourth aspect of the present invention, wherein at least one of the first home status predicting means and the second home status predicting means. Based on the attribute information of the target person who predicted the home status, further comprising: generation means for generating prediction reference data capable of predicting the home status of another target person having the attribute information, the second home The situation prediction means predicts the at-home situation of the target person using the prediction reference data generated by the generation means based on the attribute information of the target person for the facility visited by the visitor. And

  According to a sixth aspect of the present invention, there is provided a predictive control system comprising: attribute information storage means for storing attribute information related to a target person to be visited by a visitor; and home prediction means for predicting the home status of the target person. A predictive control device comprising: an energy utilization device that is installed in a facility visited by the visitor and operates using energy; and a measuring unit that measures energy information consumed by the energy utilization device, The at-home prediction means further comprises first at-home condition prediction means for predicting the at-home condition of the subject at the time when the energy information is measured based on the energy information measured by the measurement means, The predictive control device is configured to generate the attribute based on the home status predicted by the first home status prediction means and the attribute information on the target person of the home status. A creation unit that creates prediction reference data used for home prediction of another target person associated with the information, and when the energy information cannot be measured in the facility, the home status of the target person is stored in the attribute information storage unit. The apparatus further comprises second at-home prediction means for predicting with reference to the prediction reference data based on the attribute information of the subject to be stored.

  In addition, the prediction control method according to claim 7 of the present invention stores, in a storage medium, attribute information related to a target person to be visited by a visitor, and energy information consumed in a facility where the target person can stay at home. A step of the predictive control device measuring, based on the measured energy information, a step of the predictive control device predicting the home status of the subject at the time when the energy information was measured, the predicted home status, A step in which a prediction control device creates prediction reference data to be used for home prediction of another target person associated with the attribute information based on the attribute information on the target person in the home situation, and the energy information in the facility When the prediction control device predicts the at-home status of the target person with reference to the prediction reference data based on the attribute information of the target person Consisting of.

  According to the present invention, not only a facility that can acquire energy information, but also a facility that cannot acquire this energy information can predict the home status of the facility with higher accuracy. Play.

1 is a system configuration diagram showing a prediction control system in an embodiment of the present invention. The figure which shows the user information memorize | stored in the user management database with which the prediction control system in embodiment of this invention comprises. The figure which shows the energy usage-amount data memorize | stored in the energy data management database with which the prediction control system in embodiment of this invention comprises. The figure which shows the visit history information memorize | stored in the visit history management database with which the prediction control system in embodiment of this invention comprises. The schematic diagram which modeled the prediction control process performed by the prediction control apparatus in embodiment of this invention. The figure which shows the prediction reference data used for the prediction control process performed by the prediction control apparatus in embodiment of this invention. The flowchart which shows the flow of the prediction control process performed by the prediction control apparatus in embodiment of this invention.

  Hereinafter, an embodiment of a prediction control apparatus, a prediction control system, and a prediction control method according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 is a system configuration diagram showing a predictive control system according to an embodiment of the present invention.

  In FIG. 1, the predictive control system includes a predictive control device 100, an information management server 200, an information communication control device 300, an instrument 400 with a communication function (hereinafter referred to as “instrument 400”), and a home system 500. This in-home system 500 shows the whole system provided in a building, a facility, etc., and the meter 400 is provided corresponding to the in-home system 500 and measures energy information (information on energy). Is shown.

  In addition, the in-home system 500 includes indoors and outdoors such as private homes (including single houses (also referred to as “detached”), apartment houses (also referred to as “collectives”), commercial facilities such as stores, and buildings. It shows a system of a facility (hereinafter simply referred to as “building”, “in-home”, “home”, or “visit”) where humans can stay at home, regardless of the type. More specifically, the home system 500 includes a home energy management device 501 and various energy utilization devices 502. The home energy management apparatus 501 is also called HEMS (Home Energy Management System), and is connected to the energy utilization device 502 directly or indirectly, and manages and monitors information obtained from the energy utilization device 502. And can communicate with the home energy management apparatus 501. This home energy management device 501 is not an essential component, but can be provided as necessary.

The energy use device 502 is a device that can be used by residents, managers, and the like in the facility, and indicates all devices that can communicate with the home energy management apparatus 501. This energy utilization device 502 operates using electric energy, which is a force necessary for operating the energy utilization device 502, as well as various network communication devices (PCs, mobile phones, etc.) and display displays. Devices (electrical devices) such as electrical appliances (TVs, air conditioners, refrigerators, telephones, etc.), electrical equipment (solar power generation systems, secondary batteries, electric vehicles, etc.) are applicable. Of course, it is also possible to use energy such as gas and petroleum (gasoline, kerosene) in addition to this electric energy. Details will be described later. For this reason, electric energy, which is a force necessary to operate the energy utilization device 502, is referred to as “main energy (main energy, first energy)”, and is used in addition to this “main energy”. Energy such as oil and petroleum may be referred to as “sub energy (sub energy, second energy)”. In addition, each of “main energy (first energy)” and “sub energy (second energy)” is also collectively referred to as “energy (amount of use, amount of operation, amount of work)”.
Is applicable.

  In addition, the home energy management apparatus 501 can manage the communication status in addition to the amount of energy used (consumed) by the energy utilization device 502. Information on energy used at this time and information on communication status (these information may be collectively referred to as “energy information”) may be displayed on the display. Of course, the energy information necessary for the home energy management apparatus 501 itself can be displayed on the display.

  From the above, the in-home system 500 including the home energy management apparatus 501 and various energy utilization devices 502 is provided in a place where visitors can visit and can collectively manage the energy information. System. In addition, since the visitor visits the resident or manager who lives in the facility where he / she is visited, the resident / manager is referred to as “visitor”, “subject” or “user (energy User)).

  Subsequently, the meter 400 includes a measuring unit that measures (measures) energy usage, a communication unit that performs communication, and the like, and receives energy information from the home energy management apparatus 501 via the communication unit (home). The energy management apparatus 501 actively transmits data, and the home energy management apparatus 501 transmits data in response to a request from the meter 400), that is, when energy information is measured. The metering unit measures the “energy usage”. The communication unit transmits energy information regarding the continued energy usage to the information communication control device 300 at a predetermined timing (immediately or after a predetermined time (for example, 30 minutes) has elapsed). Since this energy information is data used for a home determination condition with the highest priority, which will be described later, it is also referred to as “highly reliable data used for predicting home status”. As described above, the home energy management device 501 is not an essential constituent element. Therefore, when the home energy management device 501 is not provided, the meter 400 receives energy information directly from the energy utilization device 502. Will be.

  The instrument 400 and the information communication control device 300 at this time are connected by either wire or wireless, and in particular, a specific frequency band (via a relay device (such as a concentrator)) installed on a utility pole or the like. For example, mutual communication using 920 MHz band radio waves is possible.

  The meter 400 mainly indicates an electric meter that measures the amount of electric energy used. In addition to the main energy, which is electrical energy, in the case where supplementary energy is used supplementarily for home determination performed by the predictive control device 100 described later, a meter capable of measuring the subsidiary energy for each type of subsidiary energy is provided. It is possible to provide.

  The information communication control device 300 is connected to each meter 400 in a loop topology, and receives information on the amount of energy used from each meter 400, thereby communicating with the prediction control device 100 or the information management server 200. (Information transmission, information transmission / reception). The information communication control device 300 enables the prediction control device 100 or the information management server 200 to communicate with the meter 400 regardless of the communication method (the meter 400 alone, grid configuration).

  Then, the information management server 200 collects energy usage per predetermined time (for example, 15 minutes, 30 minutes, 1 hour) at each facility received from the meter 400 via the information communication control device 300 (aggregation, meter reading). ) To manage. The information management server 200 can also perform a process of calculating a cost for the energy usage.

  The information management server 200 is connected to at least storage media such as a user management database 201 (customer DB) and an energy data management database 202 (collection data DB), and a visit history management database 203 (visit history DB) described later. ) Storage media can also be connected. In the user management database 201, information (hereinafter referred to as “user information”) (for example, identification information, name, address, family structure, energy contract contents, etc.) related to a visitor (user) who uses energy is stored. In addition, the energy data management database 202 stores energy usage data received from the meter 400 in association with each user in time series.

  An example of user information (customer information) stored in the user management database 201 at this time is shown in FIG. 2, and an example of energy usage data stored in the energy data management database 202 is shown in FIG. 3, which will be described later.

  When the information management server 200 receives a transmission request for information related to the energy usage amount to the user from the prediction control device 100 described later in a state where the energy usage amount is managed in each facility, the user ID of the user is changed to the user management database. If the energy usage amount for the user is managed by the energy data management database 202, the energy usage amount is returned to the predictive control device 100.

  If the user ID is not registered in the user management database 201, the information management server 200 responds to the prediction control apparatus 100 to that effect. Further, if the user ID is registered in the user management database 201 but the energy usage for the user is not managed in the energy data management database 202, the information management server 200 manages the user with respect to the prediction control device 100. User attribute information registered in the database 201 is transmitted.

  The prediction control apparatus 100 is an apparatus that can predict the home status by performing the prediction control process for all users registered in the user management database 201. Specifically, the predictive control device 100 determines whether or not at home (“100%” or “0%”) for each predetermined date and time, or calculates the home probability (calculates the absence probability). The home status can be predicted (hereinafter, simply referred to as “at-home determination” or “at-home prediction”). That is, the home status is represented by the presence / absence of home and / or the home probability, and the prediction control apparatus 100 generates a “home status list” that is a home prediction result in which the home status is tabulated for each user.

  The prediction control apparatus 100 is connected to at least a visit history management database 203 (visit history DB), and can also be connected to a user management database 201 (customer DB) and an energy data management database 202 (collected data DB). . The visit history management database 203 manages the date and time of visit for each user identification information (user ID) for identifying the user, and the result (at home, absent) of the visit, and details are shown in FIG.

  The predictive control device 100 can perform predictive control processing using the energy usage data and user attribute information received from the information management server 200, and can also provide a user with a past visit history and information for the user in the visit history management database 203. If the power history is registered, it is possible to perform the predictive control process using these history information.

  Further, in the predictive control process using the user attribute information, the predictive control device 100 preliminarily predicts reference reference data including home situations with respect to combinations of items of the user attribute information based on the home prediction results in the predictive control process. It is possible to perform processing to create (aggregate). The prediction control apparatus 100 can predict the home status of a user having the user attribute information using the prediction reference data and the user attribute information acquired from the information management server 200.

  An example of energy usage data at this time is shown in FIG. 3, FIG. 4 shows a past visit history, and FIG. 6 shows predicted reference data.

  The prediction control apparatus 100 can be connected to a terminal such as a PC or a mobile device directly or indirectly via a network, and can receive a home prediction request (input) from the terminal. Is possible. The terminal at this time is also referred to as “at-home prediction request source”, and can refer to the “at-home situation list” that is a home prediction result (output) related to the prediction control processing performed by the prediction control apparatus 100. Of course, it is also possible to output the home prediction result to another device different from the “home prediction requester” and a predetermined medium (paper medium, storage medium, etc.).

  Predictive control processing performed by the predictive control device 100 enables home prediction with high accuracy by preferentially using a home determination condition with high accuracy of home prediction, and provides home determination conditions according to each user. By using, it is possible to make home predictions for specified users or all users.

  Specifically, as the home determination condition with the highest priority (priority: high) (also referred to as “first priority home determination condition”), “energy consumption per predetermined time” and “home determination energy use" (Use amount obtained by adding (+ α) an error amount statistically calculated in advance to a minimum value within a period such as the same month) ”to perform home prediction.

  In home prediction using this home determination condition (priority: high), if “energy consumption per predetermined time” is larger than “home determination energy usage”, it is possible to stay home at that predetermined time On the other hand, if it is equal to or less than the “at-home determination energy consumption”, it is determined that there is a low possibility of being home at the predetermined time (that is, a high possibility of being absent). The at-home probability may be calculated based on the amount of deviation between the “energy use amount per predetermined time” and the “home use energy use amount”. The greater the deviation amount, the higher the home probability, and the smaller the deviation amount, the lower the home probability.

  In the above example, since the predetermined time is set to “15 minutes”, “30 minutes”, “1 hour”, etc., it becomes possible to perform home prediction using high-granularity energy usage data. That is, at-home prediction at that time can be performed every predetermined time such as “15 minutes”, “30 minutes”, and “1 hour”.

  In addition, the minimum value in “at-home determination energy consumption” used in this at-home determination condition (priority: high) indicates, for example, standby power consumed by an electric device that is always operating, such as a refrigerator, Further, the error amount indicates additional power (power related to allowable fluctuation) accompanying an operation necessary for continuous operation.

  Subsequently, home prediction is performed using “past visit history and call history” for each user as the next highest priority home determination condition (priority: medium) (also referred to as “second priority home determination condition”). There is something to do. This home determination condition (priority: medium) is a condition used for home prediction that is performed when the amount of energy used for the home determination condition with the highest priority shown above cannot be acquired from each facility.

  In home prediction using this home determination condition (priority: medium), a predetermined time such as several minutes before and after the time of the visit by referring to the visit time from the past visit history, the visit result of the time, etc. The home or absence in the band is determined (the same applies to the call history).

  As a home determination condition with the lowest priority (priority: low) (also referred to as “third priority home determination condition”), there is one that performs home prediction using user attribute information. This home determination condition (priority: low) is used when the energy consumption used in the above-described home determination condition (priority: high) cannot be acquired from each facility, and in the home determination condition (priority: medium) This is home prediction performed when there is no past visit history or call history.

  This home determination condition (priority: low) is similar to other users who have home predictions (they have common points) without using the energy consumption of the user who makes home predictions or the visit history to the facility. This is a condition used to predict the user's home based on attribute information.

  In other words, when using the at-home determination condition (priority: low), “predicted reference data based on user attributes” in which home prediction is performed for each combination of user attribute information items is created (aggregated) and stored. (See FIG. 6), home prediction is performed using the prediction reference data and at least a part of the user attribute information of the target user.

  As described above, the prediction control process performed in the prediction control apparatus 100 enables home prediction for all users by using the home determination conditions according to the users. By using a plurality of these home determination conditions, It is also possible to perform home prediction comprehensively. For example, it is possible to perform the predictive control process using the home determination condition (priority: high) and the home determination condition (priority: medium), and the home determination condition (priority: medium) It is also possible to perform the predictive control process using the home determination condition (priority: low).

  In addition, in the result determined using a plurality of home determination conditions, for example, the home prediction result determined under the home determination condition (priority: high) and the home determination condition (priority: high) When the at-home prediction result determined by taking into consideration the degree: medium) is different, the judgment criteria in the at-home judgment condition (priority: high), specifically, “at-home judgment energy consumption” is reviewed (updated) ) Processing may be performed. This makes it possible to perform home prediction with higher accuracy even with home prediction using only the home determination condition (priority: high).

  This will be specifically described. For example, as a result of home prediction using the home determination condition (priority: high), the “previous visit” of the home determination condition (priority: medium) is determined during the time zone determined as “absent” (temporary determination). If there is a result indicating that the user is at home based on the “history or call history”, the “home determination energy consumption”, which is a parameter used for home prediction using the home determination condition (priority: high), is used as the visit result. It is also possible to update the explained variable and the amount of electric power per predetermined time (30 minutes or the like) as an explanatory variable by machine learning. As a result, the determination logic for home prediction using the home determination condition (priority: high) is updated (reviewed).

  In the home determination in the prediction control apparatus 100 described above, an example using electric energy that is main energy is shown. However, in addition to this main energy, processing for home determination may be performed using sub energy. In this case, the predictive control device 100 can also use the usage amount of the secondary energy as one variable for correcting the determination result of the home determination using the usage amount of the main energy (electric energy). It is also possible to determine at home by using the usage amount of secondary energy in addition to the usage amount of electrical energy.

  Thus, it becomes possible to improve the accuracy of the determination result of the home determination by the prediction control apparatus 100 by using a plurality of different types of energy.

  In addition to the above-described home prediction function, the prediction control apparatus 100 determines a visit route that defines a visit order based on information that can be visited from each facility obtained from the prediction result of the home prediction process. It also has a function (visit patrol plan formulation function) to formulate a visit patrol plan by creating. In addition to the prediction results of the home prediction process, this visit patrol plan includes map data (data for calculating distance and time), data on the number of people that can be visited (number of people, skills, etc.), and details of the visit (time required for the visit) Etc.).

  This planning process makes the visit patrol plan a direct output (product, output), while the home prediction result of each facility in the home prediction process itself is an indirect output, such as the home prediction result. It becomes possible to improve the confidentiality of highly confidential information.

  If you visit the facility using this visit patrol plan, the visitor will be able to visit the target person at home with a higher probability, and the possibility of revisiting will be reduced, thus reducing the possibility of an efficient visit. It becomes possible.

  In the above description and FIG. 1, an example in which the prediction control device 100 and the information management server 200 are configured by separate devices is shown, but these may be realized by a single device. In addition, the user management database 201 (customer DB), the energy data management database 202 (collected data DB), and the visit history management database 203 (visit history DB) may be stored in the storage medium of the prediction control apparatus 100. Good. That is, the dotted line portion shown in FIG. It is also possible to store a program for predictive control processing performed in this single device in a storage medium (not shown) in the device and execute it by a calculation unit (CPU) or the like.

  FIG. 2 is a diagram showing user information stored in a user management database included in the prediction control system according to the embodiment of the present invention.

  The user information shown in FIGS. 2A and 2B includes user identification information (user ID) for identifying a user and attribute information related to the user. For convenience, FIG. 2A and FIG. It is described in (b), and may be constituted by a single normalized information. In FIG. 2A, the attribute items “name”, “address”, “family structure”, and “contract energy plan” are stored in association with the user ID. The “contract energy plan” is a service plan provided for an energy contract used by a user. As an example shown in FIG. 2A, a user whose user ID is “user 001” has “Taro” as attribute information for “name” of the attribute item, and “address” of the attribute item "Tokyo" is shown as attribute information, "Single (male)" is shown as attribute information for "Family composition" of the attribute item, and "Contract energy plan" is shown as the attribute item. "Plan A" is shown as an attribute item.

  Subsequently, in FIG. 2B, the attribute items of “building use”, “aged age”, and “owned device” are associated with the user ID. Note that “owned equipment” refers to energy providing equipment corresponding to the type of energy to be provided. When the provided energy is “gas”, “gas water heater” is indicated and provided. When the energy is “electric”, “electric water heater” is shown.

  In the example shown in FIG. 2B, the user whose user ID is “user 001” shows “detached” as attribute information for the attribute item “building use”, and the attribute item “building” “30 years or more” is indicated as attribute information for “years”, and “gas water heater” is indicated as attribute information for “owned equipment” of the attribute item.

  FIG. 3 is a diagram showing energy usage data stored in an energy data management database included in the prediction control system according to the embodiment of the present invention.

  The energy usage data shown in FIG. 3 is obtained by associating “energy usage per predetermined time” with each user. FIG. 3 shows an example in which the amount of energy used for each date is measured every “30 minutes” as a predetermined time. In the example illustrated in FIG. 3, energy measured at “11:00”, “11:30”, and “12:00” on “May 13, 2017” for the user whose user ID is “user 001”. The usage amounts are indicated as “5”, “5”, and “4”, respectively, and “11:00”, which is the same time as “May 14, 2017” on the next day, The energy usage measured at “11:30” and “12:00” is “6”, “7”, and “7”, respectively.

  That is, as shown in FIG. 3, it is possible to grasp the energy usage status in the facility where the user is located with high granularity from the energy usage data at short predetermined time intervals.

  In addition, in FIG. 3, although the energy usage of any energy among electricity, gas, oil (gasoline, kerosene), etc. is shown, for each energy (electricity, gas, oil (gasoline, kerosene) ) May be managed individually.

  FIG. 4 is a diagram showing the visit history information stored in the visit history management database provided in the prediction control system according to the embodiment of the present invention.

  The visit history information in FIG. 4 is obtained by associating each item of “visit date” and “visit result” with the user ID of the user. In FIG. 4, for example, a visit to a facility where a user whose user ID is “user 002” is on the visit date and time of “April 10, 2017 12:05”, and the visit result of this visit date and time As “absent”. That is, this corresponds to the case where the visit history is stored in the visit history of the target person's facility. In the visit history to the facility where the user whose user ID is “user 003” is present, whether or not there is a visit is not stored. That is, this corresponds to the case where the visit history of the target person's visit to the facility is not stored.

  FIG. 5 is a schematic diagram schematically illustrating a prediction control process performed by the prediction control apparatus according to the embodiment of the present invention.

  5, FIG. 5A shows a table obtained by cutting out a part of the “energy usage per predetermined time” data shown in FIG. 3. As an example, the user ID is “user 001”. It shows the energy usage of two users (two persons) who are “user 002”. In FIG. 5A, the energy usage amount of “user 001” measured at “11:00”, “11:30”, “12:00” of “2017/05/13” in the meter 400 is shown. “5”, “5”, and “4”, and the energy usage amount of “user 002” is “4”, “3”, and “3”. In addition, the energy usage of “user 001” measured at “11:00”, “11:30”, and “12:00”, which is the same time of “2017/05/14” on the next day, is “6”, “ 7 and “7”, and the energy usage amount of “user 002” is “1”, “1”, and “5”. Of course, the table of FIG. 5A does not include users who cannot measure the “energy usage” by the instrument 400.

  FIG. 5B compares “energy usage per predetermined time” shown in FIG. 5A with “at-home determination energy usage” and sets “1” when it is determined that the user is at home. The table is composed of home prediction results (first home prediction results) in a state where “0 (zero)” is set when it is determined that the user is absent. In this example, the home prediction result when “at-home determination energy consumption” is “2.5 (total value when the minimum value is“ 2 ”and the error amount is“ 0.5 ”)” is used. Show.

  FIG. 5C shows the home visit result based on the comparison between the “energy use amount per predetermined time” and the “home use energy use amount” shown in FIG. It is a table which shows the home prediction result (2nd home prediction result) which carried out the ensemble.

  In FIG. 5C, the home prediction result of “user 002” at “2017/05/14 12:00” is “1 (at home)” with respect to the first home prediction result shown in FIG. 5B. To “0 (absent)”. This is because, for example, “Absence” is indicated in “12:05” of “2017/4/10” as the visit history information of “user 002” in FIG. "Energy usage per unit" and past visit histories are taken into consideration (ensemble), and it is determined that there is a high possibility of being "absent" (updated). Of course, the determination may be made by applying a predetermined weight to the “energy consumption per predetermined time” and the past visit history.

  FIG. 5B and FIG. 5C show home prediction results based on the presence / absence of home (“100%” or “0%”) for each predetermined date and time in the prediction control process. is there. Therefore, the home prediction results as shown in FIG. 5B and FIG. 5C may be output as a “home status list”.

  Next, FIG. 5D shows the home prediction result based on the home probability.

  In FIG. 5 (d), FIG. 5 (d-1) shows a home probability per predetermined time (per 30 minutes), and FIG. 5 (d-2) shows three time zones ( The probability of being at home for each time zone is shown for night, morning, and afternoon).

  5 (d-1) and FIG. 5 (d-2) are either one of the “first home prediction result” in FIG. 5B or the “second home prediction result” in FIG. The home prediction result by the home probability is shown by statistically processing both and the visit history information of FIG. For example, it is possible to calculate by applying a predetermined value based on the home prediction result to the number of stays at home and the number of absences with respect to the total number of visit histories.

  FIG. 6 is a diagram showing prediction reference data used for the prediction control process performed by the prediction control apparatus according to the embodiment of the present invention.

  FIG. 6 shows predicted reference data indicating the home probability of each time zone (in units of 30 minutes) for the combination of user attribute information items. As the items of the user attribute information of the prediction reference data shown in FIG. 6, “building use” and “building age” are shown, and the home prediction of the user's facility having the value (home probability) in this item as the user attribute information Will be used.

  At this time, what kind of combination is taken, that is, what attribute information is classified and patterned, can be defined according to the classification form required for business, and each attribute information It is possible to search and define by a statistical method using a correlation, a correlation distribution, or the like.

  According to FIG. 6, it is possible to predict the user's home at each time zone based on the user attribute information, so the energy usage amount of the facility where the user is (data used for the first priority home determination condition) User attribute information is registered in the user management database 201 based on the predicted reference data even if the visit history (data used for the second priority home determination condition) or the like is not registered in the predetermined database in advance. Home prediction is possible for all users.

  FIG. 7 is a flowchart showing the flow of the prediction control process performed by the prediction control apparatus in the embodiment of the present invention.

  In FIG. 7, the prediction control apparatus 100 sends a home prediction request from a predetermined terminal (PC, mobile) or from a “home prediction request source” such as an input device (keyboard, mouse, etc.) connected to the self-prediction control apparatus 100. The process is started upon reception. This home prediction request includes information specifying a user who performs home prediction as a “home prediction condition” for performing home prediction. For example, it is designated to perform home prediction for all registered users, or to perform home prediction for one or more designated users.

  When receiving the home prediction request, the prediction control apparatus 100 extracts user information related to the user included in the “home prediction condition” (S701). The user information at this time includes a user ID for identifying the user and user attribute information.

  Subsequently, the prediction control apparatus 100 determines whether or not the data of “first priority at-home determination condition” for “1 user” in the user information is stored (S702). Since the “first priority home determination condition” is a condition for performing home prediction based on the “energy consumption per predetermined time” as described above, the “first priority home determination condition” This data indicates the amount of energy used received from the facility where “1 user” is located. Therefore, the process of step 702 is a process of determining whether or not the energy usage is stored for “1 user”.

  When it is determined that the data of the “first priority at-home determination condition” is stored by storing the energy usage amount by this determination process (YES in S702), the predictive control device 100 determines the “first Based on the “priority home determination condition”, the home / absence determination processing in each time zone is performed (S703). This determination process determines whether the user is “at home” or “absent” by using “energy usage per predetermined time” of “1 user” and “at-home determination energy usage”. If it is not determined that the “first priority home determination condition” data is stored (NO in S702), the process proceeds to step 705 described later.

  Then, the prediction control apparatus 100 creates a first home prediction result by home / absence determination processing in each time zone based on the “first priority home determination condition” (S704). In the first home prediction result, as shown in FIG. 5B, for example, a result based on the magnitude relationship between “energy usage per predetermined time” and “home determination energy usage” is shown. .

  Subsequently, the prediction control apparatus 100 determines whether or not the data of “second priority home determination condition” for “1 user” is stored (S705). Since the “second priority home determination condition” is a condition for performing home prediction based on the past visit history and call history for “1 user” as described above, The “priority home determination condition” data indicates a visit history and a call history. Therefore, the process of step 705 is a process of determining whether or not a visit history or a call history is stored for “1 user”.

  When it is determined that the data of the “second priority home determination condition” is stored by storing past visit history and call history data by this determination processing (YES in S705), the predictive control device 100 performs home / absence determination processing in each time zone based on the “second priority home determination condition” (S706). In this determination process, it is determined whether the user is “at home” or “absent” for each time period using the past visit history, call history, etc. of “1 user”.

  Subsequently, the prediction control apparatus 100 creates a second home prediction result by home / absence determination processing in each time zone based on the “second priority home determination condition” (S707). In the second home prediction result, information indicating whether the user is “at home” or “absent” such as past visit history and call history is shown, and the first home prediction result is created by the processing in step 704. In this case, the first at-home prediction result is shown (in an ensemble) by adding information such as “home” or “absence” such as past visit history and call history.

  Then, the prediction control apparatus 100 calculates the home probability of the user based on at least one result of the first home prediction result and the second home prediction result (S708). In the process of step 702, when it is determined that the data of the “first priority home determination condition” is stored, the “first home prediction result” generated in the process of step 704 and the “first home prediction result” generated in the process of step 707 are displayed. The user's home probability is calculated using the “second home prediction result”. Also, in the process of step 702, if it is not determined that the data of “first priority home determination condition” is stored, the “first home prediction result” has not been generated. The user's home probability is calculated using the “second home prediction result”.

  After the user's home probability is calculated in the process of step 708 as described above, the predictive control device 100 subsequently stores the data of “first priority home determination condition” in the process of step 702. If it is not determined (NO in S702), the user attribute information of “1 user”, which is the data of “third priority home determination condition”, is read (S710).

  Since the “third priority home determination condition” is a condition for performing home prediction using user attribute information, the data of “third priority home determination condition” indicates user attribute information.

  And the prediction control apparatus 100 specifies a user's at-home probability from prediction reference data as shown in FIG. 6 based on the user attribute information (S711). This identification process is a process of identifying any home probability as the home probability of the “one user” because the home probability is indicated as the predicted reference data as shown in FIG. 6.

  And the prediction control apparatus 100 produces the 3rd at-home prediction result which shows the at-home probability in each time slot | zone based on the user attribute information of "1 user", and the data of "3rd priority at-home determination conditions" ( S712). This creation process is a process that is always performed when the first home prediction result has not been created, regardless of whether the second home prediction result has been created by the process of step 707. That is, if the first home prediction result is not created based on the highest priority home determination condition (first priority home determination condition), the prediction control apparatus 100 performs home prediction based on the user attribute information. It shows that.

  Further, after the user's home probability is calculated by the process of step 708, when it is determined by the process of step 702 that the data of the “first priority home determination condition” is stored (YES in S702), that is, The “first home prediction result” is created based on the data of the “first priority home determination condition”, and the “second home prediction result” is calculated based on the data of the “second priority home determination condition”. If it has been created, the prediction control apparatus 100 performs processing in step 713 to be described later.

  On the other hand, if it is not determined by the processing in step 705 that the data of “second priority home determination condition” is stored (NO in S705), that is, whether or not there is a visit in the visit history of the user's facility Is not stored, and it is determined that the “first home prediction result” has not been created by the process in step 702 (NO in S702), the prediction control apparatus 100 is described above. Each process after the process of step 710 is performed. Therefore, even if neither “first priority at-home determination condition” data nor “second priority at-home determination condition” data is stored for “1 user”, It is possible to perform home prediction based on the attribute information of “1 user”.

  If it is not determined in step 705 that the data of “second priority home determination condition” is stored (NO in S705), that is, whether or not there is a visit is stored in the visit history of the user's facility. If it is determined that the data of the “first priority at-home determination condition” is stored in the process of step 702 (YES in S702), that is, there is one user. When the energy usage data received from the facility is stored, the prediction control apparatus 100 calculates the home probability of the user based on the first home prediction result (S708). And the prediction control apparatus 100 performs the process in step 713 mentioned later.

  The prediction control apparatus 100 determines whether or not home prediction has been completed for all users by performing the processing from step 702 to step 712 as described above for all users (S713).

  When the home prediction for all the users specified in the home prediction request is completed by performing the processes shown in steps 702 to 712 (YES in S713), the prediction control apparatus 100 continues to The home probabilities are totaled, and for each user, a “home situation list” indicating home prediction results in which home probabilities for each time period are associated is created (S714).

  Then, the prediction control apparatus 100 generates “prediction reference data” based on the user attribute information of each user (S715). The prediction reference data generated in step 715 is stored in the storage unit of the prediction control apparatus 100 and can be registered in an arbitrary database. Further, it is possible to output the “at-home status list” to a terminal connected to the prediction control apparatus 100 and output it to a display device or a predetermined medium of this terminal.

  This prediction reference data is stored in step 710 when performing home prediction for a user who does not store either “first priority home determination condition” data or “second priority home determination condition” data. This is data that is read out from a section and used for home prediction.

  From the above, the predictive control processing in the predictive control device 100 of the present invention predicts the home situation with high accuracy based on the prediction determination condition according to each user (at home prediction). ) Is possible.

  That is, even if it is a case where the data of the energy usage from the facility where the user is present cannot be acquired, or even when the visit to the facility where the user is present is the first time, the predictive control device 100 of the present invention provides high accuracy. The home situation can be predicted.

  The embodiment described above is one embodiment of the present invention, and is not limited to these examples, and can be implemented with appropriate modifications within a range not changing the gist thereof.

DESCRIPTION OF SYMBOLS 100 Prediction control apparatus 200 Information management server 201 User management database 202 Energy data management database 203 Visit history management database 300 Information communication control apparatus 400 Instrument 500 Home system 501 Home energy management apparatus 502 Energy utilization apparatus

Claims (7)

Attribute information storage means for storing attribute information related to a target person to be visited by a visitor;
Energy information consumed in a facility where the target person can stay at home is measured by a meter, and the energy information is acquired from the meter,
Based on the energy information acquired by the acquisition means, first at-home situation prediction means for predicting the at-home situation of the subject at the time of measuring the energy information;
Prediction reference used for home prediction of another target person associated with the attribute information based on the home condition predicted by the first home condition prediction means and the attribute information on the target person of the home condition Creating means for creating data;
When the energy information of the facility cannot be acquired, the at-home situation of the target person is predicted with reference to the prediction reference data based on the attribute information of the target person stored in the attribute information storage means. A prediction control device comprising: at-home condition prediction means. A visit history storage means for storing a visit history to the facility of the subject person,
The visit history includes a case where the presence or absence of a visit to the facility of the subject is stored and a case where the presence or absence of the visit is not stored,
The predictive control apparatus according to claim 1. The first at-home status prediction means includes:
The home status of the target person is predicted using the visit history of the target person stored in the visit history storage means together with the energy information of the target person. The predictive control device described. The second at-home status prediction means includes:
When the energy information at the facility cannot be acquired and the visit history storage means does not store the presence / absence of the visit in the visit history of the subject to the facility, the home status of the subject is predicted. The predictive control device according to claim 2, which has a particular feature. Based on the attribute information of the target person who has predicted the home status by at least one of the first home status prediction means and the second home status prediction means, the home status of other target persons having the attribute information is determined. Further comprising generating means for generating predictable prediction reference data;
The second at-home status prediction means includes:
The at-home situation of the target person is predicted using the prediction reference data generated by the generation unit based on the attribute information of the target person regarding the facility visited by the visitor. Or the prediction control apparatus of Claim 4. Attribute information storage means for storing attribute information related to a target person to be visited by a visitor;
A home control means for predicting the home status of the target person;
An energy utilization device provided at a facility visited by the visitor and operating using energy;
Measuring means for measuring energy information consumed by the energy using device,
The home prediction means includes
Based on the energy information measured by the measuring means, further comprising first at-home situation prediction means for predicting the at-home situation of the subject at the time of measuring the energy information,
The predictive control device includes:
Prediction reference used for home prediction of another target person associated with the attribute information based on the home condition predicted by the first home condition prediction means and the attribute information on the target person of the home condition Creating means for creating data;
When the energy information cannot be measured in the facility, the at-home situation of the subject is predicted with reference to the prediction reference data based on the attribute information of the subject stored in the attribute information storage means. And a home prediction means. Store the attribute information about the target person to be visited by the visitor in the storage medium,
A step in which the predictive control device measures energy information consumed in a facility where the target person can stay at home;
A step in which a predictive control device predicts the at-home situation of the subject at the time of measuring the energy information based on the measured energy information;
A step in which the prediction control device creates prediction reference data to be used for home prediction of another target person associated with the attribute information based on the predicted home state and the attribute information on the target person of the home state ,
When the energy information cannot be measured in the facility, the prediction control device predicts the at-home status of the target person with reference to the prediction reference data based on the attribute information of the target person;
A predictive control method comprising:

Images