JP2020166447A - Fire alarm system, information processor, fire alarm method, and program - Google Patents

Abstract

To provide a fire alarm system, an information processor, a fire alarm method, and a program capable of achieving both early detection of fire signs and reduction of non-fire alarms.SOLUTION: A fire alarm system 1 includes a sensor unit 10, and an information processor (a cloud service device 20) connected to the sensor unit 10 via a network. The sensor unit includes an odor sensor 11 that detects an odor, a motion sensor 12 that detects the movement of a human body, and a fire detection sensor 13 that detects smoke or heat. The information processor includes: an acquisition unit that acquires, from the sensor unit, the sensing result around an installation location where the sensor unit is installed; a determination unit that determines a fire occurrence status around the installation location based on the sensing result acquired by the acquisition unit; and a notification unit that notifies a preset notification destination according to the determination result of the determination unit.SELECTED DRAWING: Figure 1

Description

The present invention relates to fire alarm systems, information processing devices, fire alarm methods and programs.

Conventionally, in general houses, fire alarms have been installed in kitchens, bedrooms, stairs, and the like. As such a fire alarm, one using a fire detection sensor such as a smoke sensor or a heat sensor is generally used. Further, conventionally, a system has been proposed in which the presence or absence of a fire in the vicinity of the installation position of the fire detection sensor is determined from the sensing result of the fire detection sensor, and a notification is given when a fire occurs (for example, Patent Document 1). reference).

JP-A-2018-60578

By the way, there is a non-fire alarm as a problem of the above-mentioned fire alarm. Specifically, since the fire alarm uses a fire detection sensor that detects a fire using smoke or heat as an index, a non-fire alarm is generated by reacting with smoke or heat other than the fire. It is conceivable to reduce the non-fire alarm by adjusting the sensitivity of the fire detection sensor, but there is a possibility that the actual fire sign cannot be detected, and there is a trade-off relationship with the occurrence of the non-fire alarm. Further, even in the above-mentioned conventional system, since a fire detection sensor for detecting smoke and heat is used, it is difficult to fundamentally reduce the occurrence of non-fire alarms.

The present invention has been made in view of the above, and provides a fire alarm system, an information processing device, a fire alarm method and a program capable of achieving both early detection of fire signs and reduction of the occurrence of non-fire alarms. The purpose is to do.

In order to solve the above-mentioned problems and achieve the object, the fire alarm system according to the present invention is a fire alarm system having a sensor unit and an information processing device connected to the sensor unit via a network. The sensor unit includes an odor sensor that detects an odor, a human sensor that detects the movement of the human body, and a fire detection sensor that detects smoke or heat, and the information processing apparatus is said to be from the sensor unit. An acquisition unit that acquires the sensing results around the installation location where the sensor unit is installed, a determination unit that determines the occurrence status of a fire around the installation location based on the sensing results acquired by the acquisition unit, and the determination unit. It is provided with a reporting unit that reports to a preset reporting destination according to the determination result of.

According to the present invention, it is possible to achieve both early detection of fire signs and reduction of non-fire alarms.

FIG. 1 is a diagram showing an example of a configuration of a fire alarm system according to an embodiment. FIG. 2 is a diagram showing an example of the hardware configuration of the cloud service device according to the embodiment. FIG. 3 is a diagram showing an example of the data structure of the sensor management file according to the embodiment. FIG. 4 is a diagram showing an example of the data structure of the report destination management file according to the embodiment. FIG. 5 is a diagram schematically showing the operation of the situation determination data (learned model) according to the embodiment. FIG. 6 is a diagram showing an example of the functional configuration of the cloud service device according to the embodiment. FIG. 7 is a sequence diagram showing an operation example of the fire alarm system according to the embodiment. FIG. 8 is a flowchart showing an example of processing executed by the cloud service device of the embodiment. FIG. 9 is a diagram schematically showing the operation of the situation determination data (learned model) according to the modified example.

Hereinafter, the fire alarm system, the information processing device, the fire alarm method, and the program according to the embodiment will be described with reference to the drawings. In the embodiment described below, an example applied to a general house will be described, but the present invention is not limited to the following embodiments.

FIG. 1 is a diagram showing an example of a configuration of a fire alarm system according to an embodiment. As shown in FIG. 1, the fire alarm system 1 includes a sensor unit 10 and a cloud service device 20.

The sensor unit 10 is installed in an area to be monitored in the house H. For example, the sensor unit 10 is installed in an area such as a kitchen, a bedroom, or a staircase. The position where the sensor unit 10 is installed is not particularly limited, and the sensor unit 10 can be installed on, for example, the ceiling.

The sensor unit 10 includes a plurality of types of sensors. Specifically, the sensor unit 10 includes an odor sensor 11, a motion sensor 12, and a smoke detection sensor 13 as a set. That is, the set of the odor sensor 11, the motion sensor 12, and the smoke sensor 13 has a sensing range around the installation position where the sensor unit 10 is installed. Each sensor of the sensor unit 10 may be integrally configured or may be configured as a separate body. In the case of separate bodies, the sensors may be installed at different positions, but it is preferable to set so that a part or all of the sensing range of each sensor overlaps.

The odor sensor 11 is a sensor device that detects an odor. The odor sensor 11 senses the vicinity of the installation position and outputs the odor component existing around the installation position as a sensing result. The sensing result includes a sensor identifier that can identify the odor sensor 11.

The configuration of the odor sensor 11 is not particularly limited, and various configurations can be adopted. As an example, the odor sensor 11 may be a QCM (Quartz Crystal Microbalance) sensor in which a film for adsorbing an odor component (causative substance) is provided on the surface of a crystal oscillator. In the QCM sensor, the resonance frequency of the AT-cut crystal unit changes due to the change in mass. The QCM sensor detects the odor of the causative substance as the mass of the causative substance by vibrating the AT-cut crystal oscillator and detecting the amount of change in the resonance frequency. The type and number of causative substances to be detected are not particularly limited, but at least the causative substances of fire-related odors, such as the causative substances of odors generated when a building material spreads, can be detected. It should be possible.

The motion sensor 12 is a sensor device that detects the movement of the human body. The motion sensor 12 senses the vicinity of the installation position and outputs the amount of movement representing the movement of the human body as a sensing result. The sensing result includes a sensor identifier that can identify the motion sensor 12. The configuration of the motion sensor 12 is not particularly limited, and various configurations can be adopted. For example, the motion sensor 12 may be a motion sensor using infrared rays, ultrasonic waves, or the like.

The smoke detection sensor 13 is an example of a fire detection sensor, and is a sensor device for detecting (sensing) smoke. The smoke detection sensor 13 senses the vicinity of the installation position and whether or not smoke is generated around the installation position. The information shown is output as the sensing result. The sensing result includes a sensor identifier that can identify the smoke sensing sensor 13. The configuration of the smoke detection sensor 13 is not particularly limited, and various configurations can be adopted. For example, the smoke detection sensor 13 may be a photoelectric smoke detection sensor.

The sensing result of the sensor unit 10 (smell sensor 11, motion sensor 12, smoke detection sensor 13) described above is the cloud service device 20 connected to the network N1 via the access point AP provided in the house H. Will be sent to. Here, the network N1 is, for example, the Internet, a mobile communication network, or the like.

In the present embodiment, the sensing result of the sensor unit 10 is transmitted to the cloud service device 20 via the access point AP, but the present invention is not limited to this, and the sensor unit 10 sends the sensing result to the cloud service device 20. May be directly transmitted. Further, the sensing results of the odor sensor 11, the motion sensor 12, and the smoke sensing sensor 13 may be output at once as the sensing result of the sensor unit 10, or may be output individually.

The cloud service device 20 is an example of an information processing device. The cloud service device 20 is composed of one or more server devices. The cloud service device 20 is connected to one or more houses H to be monitored via the network N1. FIG. 1 shows an example in which two houses H (house H1 and house H2) are monitored. The cloud service device 20 receives a sensing result from the sensor units 10 installed in each of the houses H, and when it detects a sign of fire or the occurrence of a fire from the sensing result, it notifies (notifies) a predetermined report destination.

For example, when the cloud service device 20 is configured as a server device housed in one housing, the cloud service device 20 is realized by a hardware configuration as shown in FIG. Here, FIG. 2 is a diagram showing an example of the hardware configuration of the cloud service device 20.

The cloud service device 20 includes a CPU (Central Processing Unit) 21, a ROM (Read Only Memory) 22, a RAM (Random Access Memory) 23, a storage unit 24, and a communication unit 25. Each of these parts is communicably connected to each other via a bus line.

The CPU 21 is an example of a processor, and controls each part of the cloud service device 20 in an integrated manner by executing a program stored in the ROM 22 or the storage unit 24. The ROM 22 stores a program or the like executed by the CPU 21. The RAM 23 is used by the CPU 21 as a work area for temporarily storing values and the like necessary for executing a program.

The storage unit 24 is a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The storage unit 24 stores programs that can be executed by the CPU 21 and various setting information. Further, the storage unit 24 has a sensor management file 241 that defines the relationship between each sensor and the installation position, a report destination management file 242 that defines the report destination for each house H, and status determination data related to the determination of the fire situation. 243 and memorize.

FIG. 3 is a diagram showing an example of the data structure of the sensor management file 241. As shown in FIG. 3, the sensor management file 241 stores the installation location where each sensor (sensor unit 10) is installed and the sensor identifier of each sensor in association with each other. Here, the installation location of the sensor unit 10 is represented by, for example, a pair of a house name which is an example of an identifier for identifying the house H and an area in the house H. The sensor identifier is an identifier for identifying each sensor (smell sensor 11, motion sensor 12, smoke detection sensor 13).

In the cloud service device 20, by referring to the sensor management file 241, the installation location and type of the sensor that outputs the sensing result are specified from the sensor identifier included in the sensing result. For example, when the sensor identifier included in the sensing result received from the house H is "smell sensor_1011", the cloud service device 20 is the scent sensing result detected in the "kitchen" of the house name "H1". Identify.

FIG. 4 is a diagram showing an example of the data structure of the report destination management file 242. As shown in FIG. 4, the report destination management file 242 stores the house name of each house H and the report destination in association with each other. Here, the report destination is divided into a normal report destination and an emergency call destination. The normal report destination means a report destination when a fire is suspected, such as when a fire sign is detected, and the emergency call destination means a notification destination when a fire occurrence is detected. For example, the address (telephone number, e-mail address, etc.) of the owner or resident of the house H, the management company that manages the house H, etc. can be registered as the normal report destination. Further, it is preferable to register the address of an organization capable of dealing with a fire, such as a fire station in the area where the house H is located, as an emergency report destination.

When the cloud service device 20 determines the fire occurrence status based on the sensing result, the cloud service device 20 refers to the report destination management file 242 and reports to the report destination according to the determination result.

The status determination data 243 is data related to the determination of the fire occurrence status. In the present embodiment, the situation determination data 243 is used to determine whether or not there is a suspicion of fire from the sensing result of the odor sensor 11.

As an example, the situation determination data 243 is threshold data that defines a threshold value (mass) as an index for determination of a specific odor component generated at the time of a fire, for example, an odor component generated at the time of burning a housing building material. You may. Further, as another example, the situation determination data 243 is a learning that can infer the possibility of a fire from the odor component detected by the odor sensor 11 with a probability value (hereinafter, fire probability). It may be a finished model.

In the latter case, the trained model can be created, for example, by the following method. First, various odor components are collected using an odor sensor 11 or the like, and each of the collected odor components is used as learning data. The learning data includes, for example, an odor component generated at the time of a fire and an odor component collected in the house H at the time of non-fire. In addition, data indicating whether or not the odor component is derived from a fire as binary values (1, 0) are prepared as teacher data. Then, the training data and the teacher data are input to the creation device that creates the trained model, and the relationship between the training data and the teacher data is machine-learned, so that the fire probability is obtained from the sensing result of the odor sensor 11. It is possible to create a trained model that can be output as an inference result.

FIG. 5 is a diagram schematically showing the operation of the situation determination data 243 (learned model). When the sensing result (odor component) of the odor sensor 11 is input to the trained model created by the above-mentioned creation method, the trained model outputs the fire probability as an inference result. Such a fire probability is represented by, for example, a numerical value between 0 and 1. For example, in the teacher data, when the fire origin is defined as "1" and the non-fire origin is defined as "0", the larger the value of the fire probability, the more suspected the fire.

Returning to FIG. 2, the communication unit 25 is a communication interface for connecting to the network N1. The communication unit 25 communicates with the sensor unit 10 via the access point AP connected to the network N1 under the control of the CPU 21.

Further, the cloud service device 20 has the functional configuration shown in FIG. Here, FIG. 6 is a diagram showing an example of the functional configuration of the cloud service device 20.

As shown in FIG. 6, the cloud service device 20 includes a sensing result acquisition unit 211, a source identification unit 212, a status determination unit 213, and a notification control unit 214 as functional configurations.

The functional configuration of the cloud service device 20 may be partially or completely realized by software (program), or may be realized by a hardware circuit (not shown). As one mode, each part of the above-mentioned functional configuration is realized by the cooperation of the CPU 21 and the program stored in the storage unit 24. The program may be provided, for example, by being downloaded from another information processing device connected to the network N1 via the network, or may be provided by being incorporated in a portable storage medium or the like in advance. ..

The sensing result acquisition unit 211 is an example of an acquisition unit. The sensing result acquisition unit 211 acquires the sensing results transmitted from each of the sensor units 10 via the communication unit 25.

The source specifying unit 212 specifies the installation location of the source sensor that transmitted the sensing result, based on the sensor identifier included in the sensing result acquired by the sensing result acquisition unit 211. Specifically, the source identification unit 212 refers to the sensor management file 241 and sets the set of “house name” and “area” corresponding to the sensor identifier included in the sensing result as the installation location of the source sensor. Identify as.

The situation determination unit 213 is an example of the determination unit. The situation determination unit 213 determines the fire occurrence status around the installation location specified by the source identification unit 212 based on the sensing result acquired by the sensing result acquisition unit 211. Specifically, the situation determination unit 213 comprehensively determines the occurrence status of a fire by using the sensing results of the odor sensor 11, the motion sensor 12, and the smoke detection sensor 13. Hereinafter, an operation example of the situation determination unit 213 will be described.

First, the situation determination unit 213 determines whether or not a fire is suspected from the sensing result of the odor sensor 11 by using the situation determination data 243. Here, the reason why the sensing result of the odor sensor 11 is first determined is that the odor spreads faster than the flame or smoke in the initial stage of the fire. Therefore, early detection of fire signs can be achieved by determining the sensing results of other sensors in a complex manner based on the sensing results of the odor sensor 11.

For example, when the situation determination data 243 is the threshold data, the situation determination unit 213 compares the sensing result of the odor component generated at the time of fire detected by the odor sensor 11 with the value of the threshold data. Here, the situation determination data 243 determines that there is a suspicion of fire (fire sign) when the sensing result of the odor sensor 11 is equal to or greater than the threshold value, and determines that there is no suspicion of fire when the sensing result is less than the threshold value.

On the other hand, when the situation determination data 243 is a trained model, the situation determination unit 213 suspects a fire based on the inference result (fire probability) obtained by inputting the sensing result of the odor sensor 11 into the trained model. Determine if there is. For example, the situation determination data 243 determines that there is a suspicion of fire when the fire probability is 40% or more, and determines that there is no suspicion of fire when the fire probability is less than 40%. Here, the threshold value related to the fire probability is not particularly limited and can be arbitrarily set.

Further, the situation determination unit 213 is based on the sensing result of the odor sensor 11 described above, and based on the sensing result of the motion sensor 12 or the smoke sensing sensor 13, the occurrence status of the fire around the installation place where the odor sensor 11 is installed. To judge.

Specifically, the situation determination unit 213 determines whether or not the activity of the movement of the human body is less than the threshold value, based on the sensing result of the motion sensor 12 that senses the same installation location as the odor sensor 11. For example, when the activity is less than the threshold value, the situation determination unit 213 determines that there is a suspicion of fire. When the activity is equal to or higher than the threshold value, the situation determination unit 213 determines that there is no suspicion of fire.

Further, the situation determination unit 213 determines whether or not smoke is generated based on the sensing result of the smoke sensing sensor 13 that senses the same installation location as the odor sensor 11. Here, when it is determined that smoke is generated, the situation determination unit 213 determines that a fire is occurring. Further, when it is determined that no smoke is generated, the situation determination unit 213 maintains the determination of suspected fire.

In this way, the situation determination unit 213 uses the sensing results of the odor sensor 11, the motion sensor 12, and the smoke sensor 13 to collectively determine the fire occurrence status. Therefore, as compared with the case where only the smoke detection sensor 13 is used to determine the fire occurrence status, the index value related to the fire occurrence can be determined from various angles, so that the false detection (non-fire report) is reduced. be able to. Further, since the situation determination unit 213 determines the fire occurrence status from the sensing results of the motion sensor 12 and the smoke sensing sensor 13 based on the sensing result of the odor sensor 11, it is possible to detect the fire sign at an early stage. ..

It should be noted that the execution order of the determinations using the sensing results of the motion sensor 12 and the smoke sensor 13 is not particularly limited, and they can be interchanged with each other or executed in parallel. In the present embodiment, when smoke is not detected in the sensing result of the smoke sensing sensor 13, the determination using the sensing result of the motion sensor 12 is executed.

The notification control unit 214 is an example of the notification unit. The report control unit 214 reports to the report destination according to the determination result of the status determination unit 213 based on the report destination management file 242.

Specifically, when the notification control unit 214 determines that there is a suspicion of fire by the status determination unit 213, the address of the normal notification destination associated with the installation location (house name) of the sensor unit 10 related to the determination. Is read from the report destination management file 242. Then, the notification control unit 214 notifies the read address of information including a message notifying that a fire sign has been detected.

Further, when the status determination unit 213 determines that a fire has occurred, the report control unit 214 manages the address of the emergency call destination associated with the installation location (house name) of the sensor unit 10 related to the determination. Read from file 242. Then, the report control unit 214 notifies the read address of information including a message notifying that a fire has occurred.

In addition, the method of reporting to the reporting destination shall not be particularly limited. For example, the report control unit 214 may send an e-mail or a message to the report destination address (e-mail address, telephone number, etc.) in cooperation with the communication unit 25. Further, for example, the report control unit 214 may be in a form of making a voice report to the address (telephone number) of the report destination by using a voice synthesis technique or the like.

Further, the report control unit 214 may also notify the installation location of the sensor unit 10, the address of the house H, and the like when reporting to the report destination. Further, the notification control unit 214 may also notify the motion sensor 12 of information indicating whether or not a person exists in the house H based on the determination result.

Next, an operation example of the above-mentioned fire alarm system 1 will be described with reference to FIG. 7. Here, FIG. 7 is a sequence diagram showing an operation example of the fire alarm system 1.

First, each of the sensor units 10 installed in the house H transmits the result obtained by sensing to the access point AP (step S11). When the access point AP receives the sensing result from the sensor unit 10, it transfers it to the cloud service device 20 (step S12).

It is assumed that the timing at which the sensor unit 10 (smell sensor 11, motion sensor 12, smoke detection sensor 13) outputs the sensing result can be arbitrarily set regardless of the timing. For example, the odor sensor 11, the motion sensor 12, and the smoke sensor 13 may be configured to perform sensing at predetermined time intervals and output the sensing results individually or at once. Further, for example, the odor sensor 11, the motion sensor 12, and the smoke sensor 13 may be configured to output the sensing results individually or at once in response to a request from the cloud service device 20.

In the cloud service device 20, when the sensing result is acquired by the sensing result acquisition unit 211, the source identification unit 212 specifies the installation location of the source sensor unit 10 (step S13). In addition, the situation determination unit 213 determines the occurrence status of a fire around the installation location specified by the source identification unit 212 based on the acquired sensing result (step S14).

When the status determination unit 213 determines that there is a suspicion of fire, the notification control unit 214 makes a notification to the address of the normal notification destination associated with the installation location of the sensor unit 10 (step S15). When the situation determination unit 213 determines that a fire has occurred, the notification control unit 214 makes a notification to the emergency call destination address associated with the installation location of the sensor unit 10 (step S16).

Next, the process executed by the cloud service device 20 will be described with reference to FIG. FIG. 8 is a flowchart showing an example of processing executed by the cloud service device 20. This process corresponds to steps S13 to S16 of FIG. 7.

First, the sensing result acquisition unit 211 acquires the sensing result transmitted from the sensor unit 10 (step S21). Next, the source specifying unit 212 refers to the sensor management file 241 and specifies the installation location corresponding to the sensor identifier included in the sensing result as the source installation location (step S22).

Subsequently, the situation determination unit 213 is based on the sensing result (odor component) of the odor sensor 11 acquired by the sensing result acquisition unit 211 and the situation determination data 243, and the situation of fire occurrence around the place where the transmission source is arranged. Is determined (step S23). Here, if it is determined that there is no suspicion of fire (step S24; No), the situation determination unit 213 ends this process.

When it is determined that there is a suspicion of fire (step S24; Yes), the situation determination unit 213 smokes around the installation location of the transmission source based on the sensing result of the smoke detection sensor 13 acquired by the sensing result acquisition unit 211. Is determined (step S25). If the sensing result of the smoke sensing sensor 13 corresponding to the installation location of the transmission source does not exist, the status determination unit 213 sends the sensing result to the corresponding smoke sensing sensor 13 via the sensing result acquisition unit 211. May be a form that requires.

When smoke is not detected in step S25 (step S25; No), the status determination unit 213 determines the human body around the installation location of the transmission source based on the sensing result of the motion sensor 12 acquired by the sensing result acquisition unit 211. It is determined whether or not the activity of the movement is less than the threshold value (step S26). If the sensing result of the motion sensor 12 corresponding to the installation location of the transmission source does not exist, the situation determination unit 213 transmits the sensing result to the corresponding motion sensor 12 via the sensing result acquisition unit 211. It may be a form that requires.

Here, when the activity of the movement of the human body is equal to or higher than the threshold value (step S26; No), the situation determination unit 213 determines that there is no suspicion of fire and ends this process. When the activity of the movement of the human body is less than the threshold value (step S26; Yes), the notification control unit 214 reads the address of the normal notification destination associated with the installation location of the transmission source from the notification destination management file 242. A fire sign is notified to the address (step S27), and this process is terminated.

On the other hand, when smoke is detected in step S25 (step S25; Yes), the situation determination unit 213 determines that a fire has occurred (step S28). In this case, the report control unit 214 reads the address of the emergency call destination associated with the installation location of the transmission source from the report destination management file 242, reports the occurrence of a fire to that address (step S29), and performs this process. finish.

As described above, according to the present embodiment, the cloud service device 20 is installed with the sensor unit 10 using the sensing results of the sensor unit 10 (smell sensor 11, motion sensor 12 and smoke detection sensor 13). Determine the status of fires around the installation site in a complex manner. Then, the cloud service device 20 makes a report to a predetermined report destination according to the determination result of the fire occurrence status. As a result, in the cloud service device 20, the fire occurrence status can be determined in a complex manner from the sensing results of the odor sensor 11, the motion sensor 12, and the smoke sensor 13, so that early detection of fire signs and non-fire It is possible to achieve both a reduction in the generation of information.

Further, in the cloud service device 20, the reporting destination can be switched according to the determination result of the fire occurrence status, that is, the detection of the fire sign or the fire occurrence. As a result, the cloud service device 20 can make a report to a report destination suitable for the determination result of the fire occurrence status, so that it is possible to efficiently promote the countermeasure against the fire.

(Modification example 1)
In the above-described embodiment, as an example of the situation determination data 243, a learned model for inferring the fire probability from the odor component detected by the odor sensor 11 has been described. However, the trained model is not limited to this, and a trained model created by another method may be used.

For example, the sensing result of the odor sensor 11 and the sensing result detected by either one or both of the motion sensor 12 and the smoke sensing sensor 13 are used as a set of learning data, and the sensing result of this set is derived from a fire. Data indicating whether or not the value is binary (1, 0) is prepared as teacher data. Then, a plurality of pairs of training data and teacher data are input to the creation device that creates the trained model, and the relationship between the training data and the teacher data is machine-learned to cause the odor sensor 11 and the human sensor. A trained model capable of inferring the fire probability can be created from the sensing results of either one or both of the 12 and the smoke sensing sensor 13.

FIG. 9 is a diagram schematically showing the operation of the situation determination data 243b (learned model) according to this modification. For the trained model created by the above-mentioned creation method, the sensing result of the odor sensor 11 (odor component), the sensing result of the motion sensor 12 (movement activity), and the sensing result of the smoke sensing sensor 13 (smoke). If you enter (presence or absence of), the trained model outputs the fire probability as the inference result.

That is, the fire probability output by the situation determination data 243b is a composite determination of the fire occurrence status of the house H from the sensing results of the odor sensor 11, the motion sensor 12, and the smoke detection sensor 13. Therefore, the situation determination unit 213 determines the occurrence status of the fire using the situation determination data 243b, thereby achieving both early detection of fire signs and reduction in the occurrence of non-fire reports, as in the above-described embodiment. Can be planned.

It should be noted that the threshold value for determining the situation can be arbitrarily set regardless of the particular situation. For example, the situation determination unit 213 determines that there is no suspicion of fire when the fire probability output by the situation determination data 243b is less than 40%, and when the fire probability is 40% or more and less than 70%, it is suspected of fire. If it is determined that there is a fire and the probability of fire is 70% or more, it may be determined that a fire has occurred.

(Modification 2)
In the above-described embodiment, the smoke detection sensor 13 is used as the fire detection sensor, but the present invention is not limited to this, and the heat detection sensor that detects heat may be used as the fire detection sensor. Also in this case, since the reflection status of the fire can be determined in a complex manner together with the sensing results of the other sensors (smell sensor 11, motion sensor 12), the early signs of the fire can be determined as in the above embodiment. It is possible to achieve both discovery and reduction of non-fire alarms.

(Modification 3)
In the above-described embodiment, the cloud service device 20 holds the sensor management file 241, the report destination management file 242, and the status determination data 243, but the present invention is not limited to this. For example, the external device accessible to the cloud service device 20 stores any or all of the sensor management file 241 and the report destination management file 242 and the status determination data 243, so that the cloud service device 20 stores in the external device. The above-mentioned processing may be performed using the created file.

Although the embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. The embodiments can be modified in various ways.

1 Fire alarm system 10 Sensor unit 11 Smell sensor 12 Human sensor 13 Smoke detection sensor 20 Cloud service device 211 Sensing result acquisition unit 212 Source identification unit 213 Situation judgment unit 214 Notification control unit

Claims (10)

A fire alarm system having a sensor unit and an information processing device connected to the sensor unit via a network.
The sensor unit includes an odor sensor that detects an odor, a motion sensor that detects the movement of the human body, and a fire detection sensor that detects smoke or heat.
The information processing device
An acquisition unit that acquires sensing results around the installation location where the sensor unit is installed from the sensor unit, and
Based on the sensing result acquired by the acquisition unit, a determination unit that determines the state of fire occurrence around the installation location, and a determination unit.
A reporting unit that reports to a preset reporting destination according to the determination result of the determination unit, and
A fire alarm system equipped with. The fire alarm system according to claim 1, wherein the determination unit determines a fire occurrence status around the installation location from the sensing result of the motion sensor or the fire detection sensor based on the sensing result of the odor sensor. .. The fire alarm system according to claim 2, wherein the determination unit determines whether or not there is a suspicion of fire based on the value of a specific odor component detected by the odor sensor. The determination unit applies the sensing result of the odor sensor to a trained model created by using a plurality of types of odor components to be training data and teacher data indicating whether or not the odor component is derived from a fire. The fire alarm system according to claim 2, wherein it is determined whether or not there is a suspicion of fire based on the inference result obtained by inputting the odor component contained in. Claims 2 to 4 determine that a fire has occurred when the determination unit determines that there is a suspicion of fire from the sensing result of the odor sensor and when smoke or heat is detected from the sensing result of the fire detection sensor. The fire alarm system according to any one of the above. Even if the determination unit determines that there is a suspicion of fire from the sensing result of the odor sensor, if the amount of movement of the human body represented by the sensing result of the motion sensor is equal to or greater than the threshold value, a fire occurs. The fire alarm system according to any one of claims 2 to 4, wherein it is determined that there is no suspicion. The fire alarm system according to any one of claims 1 to 6, wherein the reporting unit switches the reporting destination according to the determination result of the determination unit. Obtain the sensing result around the installation location where the sensor unit is installed from a sensor unit including an odor sensor that detects odor, a motion sensor that detects the movement of the human body, and a fire detection sensor that detects smoke or heat. Acquisition department and
Based on the sensing result acquired by the acquisition unit, a determination unit that determines the state of fire occurrence around the installation location, and a determination unit.
A reporting unit that reports to a preset reporting destination according to the determination result of the determination unit, and
Information processing device equipped with. A fire alarm method executed by an information processing device.
From the sensor unit including the odor sensor that detects the odor, the motion sensor that detects the movement of the human body, and the fire detection sensor that detects smoke or heat, the acquisition unit is located around the installation location where the sensor unit is installed. Get the sensing result,
The determination unit determines the fire occurrence status around the installation location based on the sensing result acquired by the acquisition unit.
The reporting unit reports to a preset reporting destination according to the determination result of the determination unit.
Fire alarm methods including that. Information processing device computer,
Obtain the sensing result around the installation location where the sensor unit is installed from a sensor unit including an odor sensor that detects odor, a motion sensor that detects the movement of the human body, and a fire detection sensor that detects smoke or heat. Acquisition department and
Based on the sensing result acquired by the acquisition unit, a determination unit that determines the state of fire occurrence around the installation location, and a determination unit.
A reporting unit that reports to a preset reporting destination according to the determination result of the determination unit, and
A program to make it work.

Images