Abnormality detection system

Abstract

This abnormality detection system comprises: a water meter having a flow rate measurement unit that is provided in a flow path through which water circulates and measures the flow rate of water circulating through the flow path, and a communication unit that performs communication with a center server; and the center server having a general communication unit that performs communication with the communication unit, a judgment unit that identifies whether a time in which the flow rate measured by the flow rate measurement unit is a prescribed value or lower continues in detection target time bands, which include a time band in which past usage results are maximum and which are consecutive time bands, and judges that there is an abnormality when said time continues, and a notification unit that performs notification when the judgment unit judges that there is an abnormality.

Description

Anomaly Detection System

[0001] The present disclosure relates to an anomaly detection system that detects abnormalities in living conditions at a consumer's home based on water usage.

[0002] A monitoring system that monitors the living conditions of a subject based on water usage is known (see Patent Document 1). In this monitoring system, a lower limit and an upper limit are set as thresholds for water usage in the determination criteria. The lower limit (e.g., a value greater than 0 liters) is set to a value that indicates that the subject is likely to continue not using water. This prevents false detection of water usage due to fluctuations in water pipe pressure even when the water is not being used. The upper limit is set to a value that indicates that the subject's water usage is significantly higher than normal. For example, this upper limit may be set to a value greater than the average water usage under normal circumstances. Another monitoring system is known that includes a water usage determination unit that determines the content of water usage using the water usage calculated by a water usage calculation unit for each use and the water usage time and the correspondence generated by a correspondence generation unit, and an anomaly notification unit that notifies the monitor of an anomaly if the number of times the determined content of water usage is performed within a certain period differs from a reference number (see Patent Document 2).

[0003] JP 2022-147117 A International Publication No. 2017 / 170691

[0004] However, there remains a problem of how to easily and accurately determine abnormalities in the living conditions of customers' homes using an approach different from the above-mentioned conventional techniques.

[0005] Therefore, an object of the present disclosure is to provide an anomaly detection system that can easily and accurately determine abnormalities in living conditions at a consumer's home.

[0006] The abnormality detection system disclosed herein is an abnormality detection system that includes a water meter installed at each consumer's home and a center server that can communicate with the water meter, wherein the water meter has a flow measurement unit that is installed in a flow path through which water flows and measures the flow rate of water flowing through the flow path, and a communication unit that communicates with the center server, and the center server has a general communication unit that communicates with the communication unit, a judgment unit that determines whether the flow rate measured by the flow meter unit remains below a predetermined value for a continuous period of time during a detection target period that includes a period of time with the highest past usage history and is a consecutive period of time, and determines that an abnormality exists if the period of time continues, and an alarm unit that issues an alarm if the judgment unit determines that an abnormality exists.

[0007] According to the present disclosure, the determination unit determines whether the flow rate measured by the flowmeter unit remains below a predetermined value for a continuous period of time during a detection period that includes and is a consecutive period of time during which historical usage is greatest, and determines that an abnormality exists if the period of time continues. In this way, by focusing on the period of greatest water usage, an abnormality is determined to exist if the flow rate remains below a predetermined value for a continuous period of time during a detection period that includes the period of greatest water usage. This makes it easy to determine whether an abnormality exists in the living conditions of a consumer's home, and makes it easier to detect the abnormality, resulting in higher detection accuracy.

[0008] According to the present disclosure, it is possible to provide an anomaly detection system that can easily and accurately determine abnormalities in living conditions at a consumer's home.

[0009] Fig. 1 is a block diagram showing an anomaly detection system according to an embodiment. Fig. 2 is a block diagram showing the detailed configuration of a customer's home and a center server in the anomaly detection system of Fig. 1. Fig. 3 is a diagram showing the cumulative value of hourly usage flow rate for each time period in a predetermined period in the past. (a) is a diagram showing hourly usage flow rate for each time period on a certain day, and (b) is a diagram showing hourly usage flow rate for each time period on a day different from the day in (a). Fig. 4 is a diagram showing hourly usage frequency for each time period in a predetermined period in the past.

[0010] An anomaly detection system according to an embodiment of the present disclosure will be described below with reference to the drawings. The anomaly detection system described below is merely one embodiment of the present disclosure. Therefore, the present disclosure is not limited to the following embodiment, and additions, deletions, and modifications are possible within the scope of the present disclosure.

[0011] Fig. 1 is a block diagram showing an anomaly detection system 100 according to an embodiment. Fig. 2 is a block diagram showing detailed configurations of a center server 10 and a customer's home 20 in the anomaly detection system 100 shown in Fig. 1. Fig. 3 is a diagram showing the cumulative value of hourly usage flow rate for a predetermined period in the past for each time period.

[0012] As shown in Fig. 1, the anomaly detection system 100 includes a center server 10 and a plurality of consumer homes 20. Although Fig. 1 illustrates four consumer homes 20, the anomaly detection system 100 may include three or fewer consumer homes 20, or five or more consumer homes 20. The water flow path leading to the consumer homes 20 is connected to a water purification plant, a reservoir, or the like.

[0013] As shown in Figure 2, each consumer home 20 is provided with a water meter 13. The water meter 13 has a flow meter unit 11 and a communication unit 12. The water meter 13 may also have a storage unit (not shown) that is made up of various types of memory or a hard disk. Examples of consumer homes 20 include, but are not limited to, ordinary homes, hospitals, schools, municipal facilities, nursing homes, single-person homes, multi-generational homes, elderly housing, university dormitories, and commercial facilities, and may be any building that can use water.

[0014] Examples of methods for acquiring data on the flow rate used from the water meter 13 are given below. As a first example, as shown in FIG. 2 , data is acquired from a water meter 13 having a flow meter side unit 11 and a communication unit 12 via the communication unit 12. In this case, a message related to the flow rate value (indicator value) measured by the flow meter side unit 11 is transmitted to the center server 10 via the communication unit 12. As a second example, data is acquired from a water meter 13 that has a flow meter side unit 11 but does not have a communication unit 12. In this case, the communication unit 12 is provided independently outside the water meter 13. Note that the flow meter side unit 11 in the first and second examples is, for example, an impeller type or an ultrasonic type.

[0015] A third example involves acquiring data from a water meter 13 that has a flow meter unit 11 capable of pulse output, a communication unit 12, and no battery. In this case, the communication unit 12 is provided external to the water meter 13, converts the pulse output value from the flow meter unit 11 into a pointer value, etc., and transmits it to the center server 10. A fourth example involves attaching an attachment to a water meter 13 that does not have a communication unit 12 or a battery. In this case, the pointer value displayed on the water meter 13 is photographed by a camera provided on the attachment, and the captured image is digitized using the OCR (Optical Character Reader) function of the attachment. This digitized data is then transmitted to the center server 10 via the communication function of the attachment. The flow meter unit 11 in the third and fourth examples is, for example, an impeller type.

[0016] In this embodiment, the flowmeter unit 11 is, for example, an ultrasonic flowmeter. The flow measurement unit 11 is provided in a flow path 11a through which water flows and measures the flow rate of water flowing through the flow path 11a. Specifically, the flowmeter unit 11 measures the water flow rate based on a propagation time calculated based on an ultrasonic signal transmitted from one of two ultrasonic transmitter-receivers and received by the other ultrasonic transmitter-receiver.

[0017] The communication unit 12 has a function of wirelessly communicating with the central communication unit 4 (described later) in the center server 10. The wireless communication method between the communication unit 12 and the central communication unit 4 of the center server 10 can be, for example, a communication network such as the Internet, LAN, LPWA (Low Power Wide Area), or WI-SUN. The communication unit 12 periodically (e.g., once a day) transmits information related to a guideline value, which is information about the water usage flow rate (consumption amount) at the consumer's home 20, to the central communication unit 4 along with date information regarding usage or non-usage (i.e., zero usage flow rate), an ID identifying the consumer's home 20, and location information for the consumer's home 20. The information related to the guideline value transmitted from the communication unit 12 to the central communication unit 4 includes, for example, 24 pieces of information. Each of these 24 pieces of information represents the water usage flow rate for each hour of the day. The location information may be provided in the center server 10.

[0018] The center server 10 has a determination unit 1, a notification unit 2, a storage unit 3, and an integrated communication unit 4. Of the above components of the center server 10, the determination unit 1 and the notification unit 2 are functionally realized by a microcontroller including a CPU (Central Processing Unit) and memory (ROM (Read Only Memory) and RAM (Random Access Memory)) that stores programs, or an ASIC (Application Specific Integrated Circuit), etc. The center server 10 may also be configured as a cloud system.

[0019] When the determination unit 1 determines that an abnormality has occurred as described below, the notification unit 2 notifies, for example, a local government, a housing management company, etc. This allows the local government, etc. to visit the consumer's home and check the safety of the residents, etc.

[0020] The storage unit 3 is composed of, for example, various types of memory, a hard disk, etc. The storage unit 3 stores information such as the water usage flow rate at the customer's home 20 received from the communication unit 12 of the customer's home 20 via the central communication unit 4.

[0021] The central communication unit 4 communicates with the communication unit 12 of each consumer home 20. The communication method of the central communication unit 4 is the same as the above-mentioned communication method of the communication unit 12. The central communication unit 4 periodically (for example, once a day) receives information related to guideline values, which are information on the water usage flow rate (consumption amount) at the consumer home 20, from the communication unit 12. The information received by the central communication unit 4 is stored in the memory unit 3.

[0022] The determination unit 1 determines whether or not the flow rate measured by the flowmeter unit 11 continues to be below a predetermined value during a detection target time period, which is a consecutive time period including a time period with the greatest past usage. The detection target time period can be set for each consumer home 20. The determination unit 1 determines that an abnormality exists if the time period continues. This will be explained in detail below.

[0023] The time period with the greatest actual usage is, for example, the time period with the greatest cumulative flow rate for each time period over a predetermined period of time in the past (e.g., one month). In this case, the determination unit 1 calculates the cumulative hourly flow rate (e.g., the cumulative daily hourly flow rate) for each time period over a predetermined period of time in the past (e.g., one month) based on the water flow rate measured by the flowmeter unit 11. This provides information such as that shown in FIG. 3.

[0024] In the example of Fig. 3, the time period in which the cumulative value of the hourly usage flow rate over one month is the highest is 6:00 AM. In this case, the determination unit 1 determines the detection target time period to be a time period that includes a predetermined period before and after 6:00 AM, which is the time period in which usage results are the highest. In this case, the predetermined period may be, for example, 6 to 24 hours. As an example, if the predetermined period is 24 hours, the detection target time period is the 24-hour period before and after 6:00 AM (a 48-hour period).

[0025] The determination unit 1 can use the minimum value of the cumulative value of the hourly flow rate usage over a one-month period as the predetermined value, for example. In this case, in FIG. 3, the predetermined value is the cumulative value of the hourly flow rate usage at 2:00 AM. The determination unit 1 determines whether or not the cumulative value of the hourly flow rate usage continues to be equal to or less than the predetermined value during the detection period. If this continues for a certain period during the detection period, the determination unit 1 determines that an abnormality has occurred.

[0026] Alternatively, the detection target time period may be as follows: The detection target time period may be a time period determined based on the continuous water usage time period over a predetermined period in the past (e.g., one month). This continuous usage time period is a continuous period during which the usage flow rate exceeds zero. For example, if the continuous water usage time period over the past month is 24 hours, the detection target time period may be 24 hours. Note that the continuous usage time period may be a continuous period during which the usage flow rate exceeds a predetermined value greater than zero. Furthermore, the detection target time period does not have to be the same as the continuous usage time period, and may be, for example, a time period longer than the continuous usage time period. Note that the detection target time period may be determined by the user. In this case, the initial value of the detection target time period may be set to, for example, 24 hours. Alternatively, an artificial intelligence function may be provided in the determination unit 1, and the detection target time period may be determined by learning using the artificial intelligence function.

[0027] In a modified example, the determination unit 1 may determine that an abnormality exists when the maximum value of the flow rate measured by the flowmeter unit 11 continues to be zero (a predetermined value in this example) for a predetermined number of days as a detection time period. Figure 4(a) is a diagram showing the hourly flow rate usage for each time period on a certain day, and (b) is a diagram showing the hourly flow rate usage for each time period on a day different from the day in (a).

[0028] In this embodiment, the determination unit 1 acquires the hourly flow rate for each time period for a certain day based on the measurement results from the flowmeter unit 11. The determination unit 1 then acquires the maximum and minimum values ​​of the acquired hourly flow rate. Specifically, as shown in FIG. 4( a), the determination unit 1 acquires a flow rate of 0.09 at 1:00 on a certain month and day as the maximum value, and acquires a flow rate of 0 at midnight on the same day as the minimum value. Furthermore, as shown in FIG. 4( b), the determination unit 1 acquires a flow rate of 0 on a certain month and day as the maximum and minimum values. The determination unit 1 then determines that an abnormality has occurred if the maximum flow rate remains zero for a predetermined number of days as the detection target time period.

[0029] In the above, the time period with the greatest usage record was determined to be the time period with the greatest cumulative flow rate for that time period over a predetermined period in the past. However, a modified example will now be described. Figure 5 is a diagram showing the usage frequency per hour for each time period over a predetermined period in the past.

[0030] In this embodiment, the time period with the highest usage record is determined by the time period with the highest usage frequency for each time period during a predetermined period in the past. The determination unit 1 calculates the usage frequency per hour for each time period during a predetermined period in the past (e.g., one month) based on the water usage flow rate measured by the flowmeter unit 11. This provides information such as that shown in FIG. 5.

[0031] The usage frequency is a ratio calculated for each time period, and is the ratio of the total number of days in a given past period (e.g., 30 days in a month) on which the hourly usage rate exceeds zero. To explain the usage frequency using an example in Figure 5, assume that there are two days in a 30-day period where the usage rate exceeds zero at 2:00 AM. In this case, the usage frequency is calculated as 2 / 30, which is approximately 7%.

[0032] 5, the time period with the highest usage frequency is 10 p.m. In this case, the determination unit 1 determines the time period including a predetermined time before and after 10 p.m., which is the time period with the highest usage record, as the detection target time period.

[0033] In this case, as in the above, the determination unit 1 can use the minimum value of the cumulative value of the hourly flow rate usage over, for example, one month as the predetermined value. Alternatively, zero may be used as the predetermined value. The determination unit 1 determines whether or not the cumulative value of each hourly flow rate usage is below the predetermined value for a continuous period during the detection period. If this period continues during the detection period, the determination unit 1 determines that an abnormality has occurred.

[0034] As described above, according to the anomaly detection system 100 of this embodiment, the time period with the greatest historical usage is determined to be the time period with the greatest cumulative flow rate for each time period over a predetermined period in the past (e.g., one month), or the time period with the greatest frequency of use for each time period over a predetermined period in the past. During a target detection time period, which is a time period including the time period with the greatest historical usage, the determination unit 1 determines whether the flow rate measured by the flowmeter unit 11 remains below a predetermined value for a sustained period. If this persists, the determination unit 1 determines that an abnormality exists. In this way, by focusing on the time period with the greatest historical water usage, an abnormality is determined to exist when the flow rate remains below a predetermined value for a sustained period during a target detection time period including the time period. This facilitates the determination of an abnormality in the living conditions of the consumer's home 20, and facilitates the detection of the abnormality, resulting in increased detection accuracy.

[0035] Although several modifications have been given in the above-described embodiment, the following modifications can also be adopted without departing from the gist of the present disclosure.

[0036] In the above embodiment, the determination unit 1 is provided in the center server 10, but the present invention is not limited to this. The determination unit 1 may also be provided in the water meter 13.

[0037] In the above embodiment, if the stop of water use is detected before the notification by the notification unit 2, the notification may not be made.

[0038] In the above embodiment, if the number of days on which the daily flow rate at a consumer's home 20 is zero exceeds, for example, 10% of the total number of days included in a predetermined period in the past, the consumer's home 20 may be excluded from detection targets. Note that the ratio may be set based on the attributes of the consumer's home 20.

[0039] Furthermore, in the above embodiment, the detection time period may be set as follows. The detection time period may be determined based on the continuous non-use time of water during a predetermined period in the past (e.g., one month). Specifically, if the maximum duration of the non-use time measured by the flowmeter unit 11 during the predetermined period in the past is, for example, 24 hours or more, the detection time period may be set to a time exceeding the maximum duration. As a result, the detection time period is set to a time period exceeding the non-use duration. Furthermore, to further increase the monitoring level, the detection time period may be set to a time period exceeding the maximum duration plus a predetermined time (e.g., 48 hours).

[0040] (Additional Notes) The following techniques are disclosed by the above description of the embodiments.

[0041] (Technology 1) An anomaly detection system comprising a water meter installed at each consumer's home and a center server capable of communicating with the water meter, wherein the water meter has a flow measurement unit installed in a flow path through which water flows and measures the flow rate of water flowing through the flow path, and a communication unit that communicates with the center server, and the center server has an integrated communication unit that communicates with the communication unit, a judgment unit that determines whether the flow rate measured by the flow meter unit remains below a predetermined value for a continuous period of time during a detection target period that is a consecutive period of time that includes a period of time during which past usage is greatest, and determines that an abnormality has occurred if the period of time continues, and an alarm unit that issues an alarm if the judgment unit determines that an abnormality has occurred.

[0042] With this configuration, the determination unit determines whether the flow rate measured by the flowmeter unit remains below a predetermined value for a continuous period of time during a detection period that includes and is a consecutive period of time during which historical water usage is greatest, and determines that an abnormality exists if the period of time continues. In this way, by focusing on the period of greatest water usage, an abnormality is determined if the flow rate remains below a predetermined value for a continuous period of time during a detection period that includes the period of greatest water usage. This makes it easy to determine whether there is an abnormality in the living conditions of a consumer's home, and makes it easier to detect the abnormality, resulting in higher detection accuracy.

[0043] (Technology 2) The anomaly detection system according to Technology 1, wherein the time period with the greatest usage record is the time period with the greatest cumulative value of the usage flow rate for each time period over a predetermined period in the past.

[0044] This configuration significantly improves the reliability of anomaly detection. In addition, since it is difficult to calculate the frequency of water usage in the early stages of use of a water meter, the time period when the cumulative value of the water usage flow rate is at its maximum can be effectively utilized.

[0045] (Technology 3) The anomaly detection system according to Technology 1, wherein the time period with the greatest usage record is the time period with the greatest usage frequency for each time period in a predetermined period of time in the past.

[0046] This configuration can significantly improve the reliability of abnormality detection.

[0047] (Technology 4) The anomaly detection system described in Technology 3, wherein the frequency of use is a ratio shown for each time period, and is the ratio of the total number of days in which the hourly usage flow rate exceeds zero to the total number of days included in the specified past period.

[0048] This configuration makes it easier to clarify the water usage trends at the customer's home, thereby improving the accuracy of abnormality detection.

[0049] (Technology 5) An anomaly detection system according to any one of Technologies 1 to 4, wherein the detection target time period is a time period determined based on the continuous water usage time during a predetermined period in the past.

[0050] This configuration makes it possible to appropriately set the detection target time period, which is the time period that should be the detection target, thereby improving the accuracy of anomaly detection.

[0051] (Technology 6) An abnormality detection system described in any one of Technologies 1 to 5, wherein the judgment unit judges that an abnormality exists if the flow rate measured by the flow meter side unit remains zero for a specified number of days as the detection target time period.

[0052] This configuration makes it easier to identify whether or not there is an abnormality on a daily basis.

[0053] REFERENCE SIGNS LIST 1 Determination unit 2 Notification unit 3 Storage unit 4 General communication unit 10 Center server 11 Flow meter side unit 11a Flow path 12 Communication unit 13 Water meter 20 Customer's home 100 Abnormality detection system

Claims

1. An anomaly detection system comprising a water meter installed at each consumer's home and a center server capable of communicating with said water meter, wherein said water meter has: a flow measurement unit installed in a flow path through which water flows and measuring the flow rate of water flowing through said flow path; and a communication unit for communicating with said center server, and said center server has: an integrated communication unit for communicating with said communication unit; a judgment unit for determining whether the flow rate measured by said flow meter unit remains below a predetermined value for a continuous period of time during a detection period that is a consecutive period of time that includes a period of time during which past usage is greatest, and determining that an abnormality has occurred if said period of time continues; and an alarm unit for issuing an alarm if said judgment unit determines that an abnormality has occurred.

2. The anomaly detection system according to claim 1, wherein the time period during which the actual usage is greatest is the time period during which the cumulative value of the usage flow rate for each time period during a specified period in the past is greatest.

3. The anomaly detection system according to claim 1, wherein the time period with the greatest usage record is the time period with the greatest usage frequency for each time period during a predetermined period in the past.

4. The anomaly detection system of claim 3, wherein the frequency of use is a ratio shown for each time period, and is the ratio of the total number of days in which the hourly usage flow rate exceeds zero to the total number of days included in the specified past period.

5. The anomaly detection system according to claim 1, wherein the detection target time period is a time period determined based on the continuous water usage time during a predetermined period in the past.

6. The anomaly detection system of claim 1, wherein the judgment unit judges that an anomaly has occurred if the flow rate measured by the flow meter unit remains zero for a specified number of days during the detection period.

Images