JP2020149240A - Timing determination device, determination method, program, and storage medium - Google Patents

Abstract

To provide a system which determines an appropriate timing at which it takes action to urge a bearer to bear garbage.SOLUTION: A timing determination unit 10 comprises a storage unit 11, a variation coefficient distribution calculation unit 12, a number-of-interval days probability calculation unit 13, a timing determination unit 14, and an output unit 15. The storage unit stores garbage bearing date information containing of the average number of interval days, a standard deviation, and a variable coefficient for each of a plurality of bearers. The variation coefficient distribution calculation unit calculates a probability distribution of each variable coefficient and a probability Y on the basis of normal distribution from the variable coefficient. The number-of-interval days probability calculation unit calculates each standard deviation corresponding to a combination of each variable coefficient and the probability Y from the average number of interval days of the bearer, calculates a probability B of each number of candidate interval days per standard deviation, weights the probability Y corresponding to the standard deviation to the probability B, and calculates a weighted average probability C for each number of candidate interval days. The timing determination unit selects the number of candidate interval days indicating a probability falling below any threshold value after a maximum value of the probability C and determines elapsed days of the number of candidate interval days from the final bearing day as a reference date of an action timing. The output unit outputs a timing.SELECTED DRAWING: Figure 1

Description

The present invention relates to a device, a method, a program, and a recording medium for determining the timing of taking an action to encourage the bringing of garbage.

Conventionally, if garbage is disposed of in a designated garbage storage area before the designated collection date, the collector collects it with a garbage truck (hereinafter referred to as "collection type"). It has become. On the other hand, in recent years, from the viewpoint of effective utilization of resources, a new "bring-on type" has been proposed instead of the recovery type. The carry-on type is a form in which each individual brings garbage to the place where the staff is present (hereinafter referred to as "garbage station"). With such a carry-on type, it is possible to dispose of garbage at any time. In addition, the staff at the garbage station can deepen their understanding of the environment and deepen their understanding of the environment by instructing individuals who bring garbage (hereinafter referred to as "bringer") to separate the garbage they bring. It is thought that it will be possible to use a place that includes the above as a place for people to interact with each other.

However, since the bring-in type is a new form in which you have to voluntarily bring in garbage instead of leaving it to the collector to collect it, some people may drop out on the way before the bring-in type becomes a habit. Come on.

In order to prevent such dropouts, it is conceivable that the operator of the carry-on garbage station will take some action to encourage the bring-outs who are likely to drop out to bring them in and continue. However, if the timing of the action for the bringer is too early, for example, if he / she intends to bring it, the action before bringing it becomes like a reminder, and as a result, it is considered that there is a possibility of adverse effects. In addition, in the case of a bearer who has little track record of bringing in, it is extremely difficult to estimate the next date of bringing in, so it is also difficult to determine the timing accordingly.

Therefore, we provide a system that determines the appropriate timing to take action to encourage the bearer to bring it.

In order to achieve the above object, the device for determining the timing for encouraging the bringing of garbage of the present invention is
Includes storage unit, coefficient of variation distribution calculation unit, interval days probability calculation unit, timing determination unit, and output unit.
The storage unit
Memorize the date of bringing garbage for each of multiple bearers,
The carry-on date information includes an average interval day μ _i , a standard deviation σ _i, and a coefficient of variation X for the interval days of the bring-in date.
The coefficient of variation X is the ratio of the standard deviation σ _i to the average interval days μ _i .
The coefficient of variation distribution calculation unit
From the coefficient of variation X of the plurality of bearers, a probability distribution Z showing the relationship between the coefficient of variation X and its probability Y is calculated based on the normal distribution.
The interval days probability calculation unit
From the average interval days μ _it of the bearer t, which is the estimation target of the next action day, each standard deviation σ _it of the bearer t corresponding to the combination of each coefficient of variation X and the probability Y based on the probability distribution Z. Is calculated and
Wherein the average interval of days mu _it and the respective standard deviation sigma _it, based on a normal distribution, for each of the standard deviation sigma, calculates the probability B for each candidate interval days A until the next day of action,
The probability B for each of the candidate interval of days A, the weighted probability Y corresponding to the standard deviation sigma, calculates the weighted average probability C of each of the candidate interval of days A,
The timing determination unit
In the increasing direction of the candidate interval days A, after the maximum value C _{max of the} weighted average probability C, a candidate interval days A _th indicating a weighted average probability C _th below an arbitrary threshold value is selected.
The day when the candidate interval days _Ath elapses from the day when the bearer t last brought the garbage is determined as the reference date for the timing of taking an action to encourage the bearer t to bring the garbage.
The output unit
It is characterized in that the timing is output.

The method for determining the timing for encouraging the bringing of garbage of the present invention is as follows.
Including the coefficient of variation distribution calculation process, interval day probability calculation process, timing determination process, and output process
Using the carry-on date information regarding the carry-on of garbage for each of multiple bearers,
The carry-on date information includes an average interval day μ _i , a standard deviation σ _i, and a coefficient of variation X for the interval days of the bring-in date.
The coefficient of variation X is the ratio of the standard deviation σ _i to the average interval days μ _i .
The coefficient of variation distribution calculation step is
From the coefficient of variation X of the plurality of bearers, a probability distribution Z showing the relationship between the coefficient of variation X and its probability Y is calculated based on the normal distribution.
The interval day probability calculation step is
From the average interval days μ _it of the bearer t, which is the estimation target of the next action day, each standard deviation σ _it of the bearer t corresponding to the combination of each coefficient of variation X and the probability Y based on the probability distribution Z. Is calculated and
Wherein the average interval of days mu _it and the respective standard deviation sigma _it, based on a normal distribution, for each of the standard deviation sigma, calculates the probability B for each candidate interval days A until the next day of action,
The probability B for each of the candidate interval of days A, the weighted probability Y corresponding to the standard deviation sigma, calculates the weighted average probability C of each of the candidate interval of days A,
The timing determination step is
In the increasing direction of the candidate interval days A, after the maximum value C _{max of the} weighted average probability C, a candidate interval days A _th indicating a weighted average probability C _th below an arbitrary threshold value is selected.
The day when the candidate interval days _Ath elapses from the day when the bearer t last brought the garbage is determined as the reference date for the timing of taking an action to encourage the bearer t to bring the garbage.
The output process is
It is characterized in that the timing is output.

The program of the present invention is characterized in that a computer executes the method for determining the timing of the present invention.

The recording medium of the present invention is a computer-readable recording medium on which the program of the present invention is recorded.

According to the present invention, for example, even a bearer who has little experience in bringing garbage can estimate the next date of bringing garbage and determine an appropriate timing for taking an action to encourage the bringing of garbage. For this reason, it is possible to effectively establish a new form of garbage disposal, which is a new carry-on type instead of the collection type.

FIG. 1 is a block diagram showing an example of the timing determination device of the first embodiment. FIG. 2 is a block diagram showing an example of the hardware configuration of the timing determination device of the first embodiment. FIG. 3 is an example graph showing the probability density with respect to the number of interval days when it is assumed that the number of interval days follows a normal distribution in the first embodiment. FIG. 4 is a graph of an example showing the probability density with respect to the number of interval days when the number of interval days is assumed to follow a normal distribution in the first embodiment. FIG. 5A is an example of a histogram showing the relationship between the coefficient of variation and the number of people in the first embodiment, and FIG. 5B is a graph showing the relationship between the coefficient of variation and the probability density, and FIG. (C) is a table showing the relationship between the coefficient of variation and the probability. FIG. 6A is a table showing the relationship between the coefficient of variation, the probability and the standard deviation in the first embodiment, and FIG. 6B is a graph showing the relationship between the number of days between intervals and the probability density. FIG. 7A is a table showing the probability B for each interval day in the first embodiment, and FIG. 7B is a table showing the weighted average probability C for each interval day. FIG. 8 is a block diagram showing an example of the timing determination device of the second embodiment. FIG. 9 is an example of a flowchart showing the procedure of the second interval day number probability calculation step in the second embodiment. FIG. 10 is an example of a flowchart showing the procedure of the timing determination method in the second embodiment.

An embodiment of the present invention will be described. The present invention is not limited to the following embodiments. In each of the following figures, the same parts are designated by the same reference numerals. Further, the explanations of the respective embodiments can be referred to each other's explanations unless otherwise specified. Further, the configurations of the respective embodiments can be combined unless otherwise specified.

[Embodiment 1]
FIG. 1 is a block diagram showing a configuration of an example of the timing determination device 10 of the present embodiment. As shown in FIG. 1, the timing determination device 10 includes a storage unit 11, a coefficient of variation distribution calculation unit 12, an interval day probability calculation unit 13, a timing determination unit 14, and an output unit 15. The timing determination device 10 is also referred to as, for example, a timing determination system. The timing determination device 10 may be, for example, one device including the above-mentioned parts, or a device in which the above-mentioned parts can be connected via a communication network.

The communication line network is not particularly limited, and a known communication line network can be used, and it may be wired or wireless. Examples of the communication line network include an Internet line, a telephone line, a LAN (Local Area Network), WiFi (Wireless Fidelity), and the like. In the timing determination device 10, the processing of each part may be performed on the cloud.

Next, FIG. 2 illustrates a block diagram of the hardware configuration of the timing determination device 10. The timing determination device 10 includes, for example, a CPU (central processing unit) 101, a memory 102, a bus 103, an input device 104, a display 105, a communication device 106, a storage device 107, and the like. Each part of the timing determination device 10 is connected to each other by an interface (I / F) via a bus 103.

The CPU 101 is a processor that controls the entire timing determination device 10, and is not limited to the CPU, and may be another processor. In the timing determination device 10, for example, the program of the present invention and other programs are executed by the CPU 101, and various information is read and written.

The timing determination device 10 can be connected to the communication network by, for example, the communication device 106 connected to the bus 103, and can also be connected to an external device via the communication network. The external device is not particularly limited, and is, for example, a database, a PC (personal computer), a terminal, or the like, and the terminal is, for example, a tablet, a smartphone, a mobile phone, or the like. The connection method between the timing determination device 10 and the external device is not particularly limited, and may be, for example, a wired connection or a wireless connection. The wired connection may be, for example, a cord connection or a cable connection for using the communication network. The wireless connection may be, for example, a connection using a communication network or a connection using wireless communication. The communication line network is not particularly limited, and for example, a known communication line network can be used, which is the same as described above.

The memory 102 includes, for example, a main memory, and the main memory is also referred to as a main storage device. When the CPU 101 performs processing, for example, the memory 102 reads various operation programs 108 such as the program of the present invention stored in the auxiliary storage device described later, and the CPU 101 receives data from the memory 102. , Program 108 is executed. The main memory is, for example, a RAM (random access memory). The memory 102 further includes, for example, a ROM (read-only memory).

The storage device 107 is also referred to as a so-called auxiliary storage device with respect to the main memory (main storage device), for example. The storage device 107 includes, for example, a storage medium and a drive for reading and writing to the storage medium. The storage medium is not particularly limited, and may be an internal type or an external type, for example, HD (hard disk), FD (floppy (registered trademark) disk), CD-ROM, CD-R, CD-RW, MO, Examples include a DVD, a flash memory, a memory card, and the like, and the drive is not particularly limited. The storage device 107 may be, for example, a hard disk drive (HDD) in which a storage medium and a drive are integrated. For example, the storage device 107 stores the program 108 as described above, and as described above, when the CPU 101 is executed, the memory 102 reads the operation program 108 from the storage device 107. Further, the storage device 107 is, for example, a storage unit 11, and stores the carry-on date information and the like of a plurality of bearers, which will be described later.

The timing determination device 10 may further include, for example, an input device 104 and a display 105. The input device 104 is, for example, a scanner, a touch panel, a keyboard, or the like. Examples of the display 105 include an LED display and a liquid crystal display.

The storage unit 11 stores the carry-on date information regarding the carry-on of garbage for each of a plurality of bearers (n and n are arbitrary positive integers). The carry-on date information is information on the carry-on date history in which each bringer brought garbage to the garbage station, and is stored in association with the carry-on identification information for each bringr. The bearer's identification information is, for example, information that can uniquely identify an individual, and as specific examples, a name, an abbreviation, a serial number, a user ID, an identification image (face image, caricature image, etc.), an address, and a telephone number. And so on. The carry-on date information includes an average interval day μ _i , a standard deviation σ _i, and a coefficient of variation X for the number of intervals between the bring-in date and the bring-in date. The carry-on date information further includes, for example, information such as the date of the bring-in date and the day of the week as the carry-on date history. Timing decision unit 10, for example, further may have a distance information calculation unit, from the date of the stored bring date in the storage unit 11, number of days between bring date, the average distance days mu _i, standard deviation σ _i and the coefficient of variation X may be calculated and the calculation result may be stored in the storage unit 11.

The number of interval days means the number of days until the next bring-in date based on a certain bring-in date. For example, when the next bring-in date is January 11 with respect to the bring-in date of January 5, the interval days. Will be 6 days. The average interval days μ _i and the standard deviation σ _i can be calculated for each bearer. For example, the average interval days μ _i and its standard deviation σ _i can be obtained by averaging from the total number of days of a certain bearer. ..

The variation coefficient X, the the ratio of the standard deviation sigma _i and the mean spacing days mu _i, for example, be represented as a value σ _{i / μ i} obtained by dividing the said standard deviation sigma _i the average interval of days mu _i Can be done. As described above, the present invention uses the carry-on date information of a plurality of bearers to estimate the number of interval days until the next carry-on date for a bring-in person who has a small carry-on date history. However, it is considered that the ratio of the number of days for which the bringing is delayed depends on the relative length of the interval days. That is, assuming that the number of days for bringing is delayed is one day, the probability of being delayed by one day when the average number of days of bringing is one month and the probability of being delayed by one day when the average number of days of bringing is five days. Is considered to be different. Therefore, as the carry-on date information, the coefficient of variation X, which is the ratio of the standard deviation σ _i to the average interval days μ _i , in consideration of the influence of the average number of days, is used in the present invention.

The number (n) of carryers of information stored in the storage unit 11 is not particularly limited, but a relatively large number is preferable, and for example, information of 100 or more people is preferable.

The coefficient of variation distribution calculation unit 12 calculates a probability distribution Z showing the relationship between the coefficient of variation X and its probability Y from the coefficient of variation X of the plurality of bearers based on the normal distribution.

Interval days probability calculation unit 13, the average interval days mu _it Bring's t is a presumed target of the next day of action, on the basis of the probability distribution Z, wherein bring corresponding to the combination of the variation coefficient X and the probability Y Calculate each standard deviation σ _it of the person t, and from the average interval days μ _it and each standard deviation σ _it , based on the normal distribution, for each standard deviation σ _it , the candidate interval days A until the next action day The probability B for each candidate interval day A is calculated, and the probability Y corresponding to the standard deviation σ _it is weighted to the probability B for each candidate interval day A to calculate the weighted average probability C for each candidate interval day A.

Timing determination unit 14, in the direction of increasing the candidate interval days A, the maximum value C _max after the weighted weighted average probability C, and the candidate interval of days A _th showing a weighted weighted average probability C _th below the arbitrary threshold The day on which the candidate interval days _Ath elapses from the day when the bearer t last brought the garbage is set as the reference date for the timing of taking an action to encourage the bearer t to bring the garbage. decide. Based on the reference date of the timing, for example, the date when an action such as a reminder is actually taken or the period during which the action is taken can be arbitrarily set. The period for taking the action is, for example, a period in which it is preferable to take the action on any day during the period. The day when the bearer t actually takes an action such as a reminder may be, for example, the reference date or any day of the period including the reference date (the period for taking the action). The period may include, for example, a date before the reference date, a date after the reference date, or both. The end of the period can be set according to, for example, the average number of days between the bearers. Specifically, for a bearer with a relatively long average interval, the end is relatively long from the reference date. The bearer who sets and has a relatively short average interval days may set a relatively short number of days from the reference date as the end. The arbitrary threshold value may be set in advance and stored in the storage unit 11, for example.

The output unit 15 outputs the timing. For example, the output unit 15 may output the timing to the external device as described above via the communication device 106, or may output the timing to the display 105 of the timing device 10 for display. Further, the candidate interval days _Ath determined by the timing determination unit 14 and the days on which the candidate interval days _Ath have elapsed may be further stored in the storage unit 11 as, for example, information of the bearer t. ..

Next, the timing determination method of the present embodiment will be described. The timing determination method of the present embodiment can be carried out using, for example, the timing determination device 10 shown in FIGS. 1 and 2. The timing determination method of the present embodiment is not limited to the use of the timing determination device 10.

The user of the present invention is, for example, an operator, an administrator, a staff, or the like of a garbage station because it encourages a person who uses the garbage station to bring garbage.

If the bearer's carry-on date information is stored as a sufficient amount of historical information, the average number of days between carry-on dates and its standard deviation are considered to be accurate. As a specific example, the average number of days μ _i = 6.17 Days and the standard deviation σ _i = 0.98 are calculated from the history information of a certain bearer, and the history information of the bearer is sufficient. It is assumed that the number of days between people follows a normal distribution. Then, when the interval days follow a normal distribution, a normal distribution curve obtained by graphing the probability density function is obtained as shown in FIG. The equation in FIG. 3 is a probability density function. In the above equation, μ is the average interval days μ _i , and σ is its standard deviation σ _i . In the graph of FIG. 3, the area of the filled area is the probability of bringing it on the 6th day from the actual last bringing date. The definite integral for calculating the area is represented by the formula 1 described later, and in the case of FIG. 3, A in the formula 1 is 6. Then, in the case of a bearer who has obtained a sufficient amount of history information in this way, for example, the number of interval days when the peak of the normal distribution curve (average interval days μ _i = 6.17) is exceeded and the probability density becomes almost zero. (The number of days marked with * in FIG. 3) can be considered as the timing when the operator of the garbage station takes an action to encourage the bearer to bring it, assuming that the carry is interrupted.

However, if the carry-on date information of the bearer is not a sufficient amount of historical information, the calculated standard deviation cannot be said to be accurate, and even if the assumption that the number of interval days is a normal distribution is used, the following It is difficult to estimate the number of days interval until the date of bringing. As a specific example, a normal distribution curve that graphs the probability density function assuming that the average number of days μ _i obtained from the history information of the bearer is the same (6.17 Days) but different standard deviations is shown. , FIG. 4 illustrates. Then, as shown in FIG. 4, the number of interval days (*) in which the probability density becomes almost zero beyond the peak in the normal distribution curve due to the fluctuation of the standard deviation (σ = 0.5, 1.0, 1.5). The number of days marked) has various results.

In addition, it is thought that garbage is always generated in daily life and accumulates at a constant pace. On the other hand, the behavior of bringing garbage is very different from the collection type, and there are variations such as earlier or later intervals. In addition, the intervals (also called cycles) and variations in the intervals that are brought in are considered to have different tendencies depending on the individual due to the influence of individual life patterns. Such a feature is based on a factor completely different from, for example, the cycle of going to a sports club, and is the first finding by the present inventions in terms of the disposal of carry-on garbage.

Therefore, in the present invention, for the bearer t, which is the target of estimation of the next action date, even if the carry-on date information is not sufficient, the carry-on date information of a plurality of bearers can be used for the cycle. And the variation, we estimate the next action date with high reliability, and decide the timing of the action to encourage bringing.

The present invention will be specifically described below.

First, the coefficient of variation distribution calculation step calculates a probability distribution Z showing the relationship between the coefficient of variation X and its probability Y from the coefficient of variation X of the plurality of bearers based on the normal distribution. The coefficient of variation distribution calculation step can be executed, for example, by the coefficient of variation distribution calculation unit 12 of the timing determination device 10.

The probability distribution Z can be calculated, for example, as follows. As described above, the storage unit 11 of the timing determination device 10 stores the carry-on date information regarding the carry-on of garbage for each of the plurality of bearers, and this is used. The carry-on date information is as described above. Since each of the plurality of bearers has a coefficient of variation X, a histogram as shown in FIG. 5A can be obtained based on the stored carry-on date information of all the bearers. In the histogram of FIG. 5A, the horizontal axis is the range of the coefficient of variation, and the vertical axis is the number of bearers corresponding to the range of each coefficient of variation. Assuming that this histogram follows a normal distribution, and further calculating the probability density with respect to the coefficient of variation X, a graph of the probability density function of FIG. 5B is obtained. The equation in FIG. 5B is the same probability density function as in FIG. 3, where μ is the mean μ _x of the coefficient of variation X and σ is its standard deviation σ _x . Then, based on the graph of this probability density function, the probability Y of taking each coefficient of variation X can be calculated from the probability density. The table of FIG. 5C shows each coefficient of variation X and the corresponding probabilities Y. In this way, a probability distribution Z showing the relationship between the coefficient of variation X and its probability Y is obtained.

Next, the interval day number probability calculation step is performed. The interval day probability calculation step can be executed, for example, by the interval day probability calculation unit 13 of the timing determination device 10. The interval in days probability calculating step, first, the average interval days mu _it Bring's t is a presumed target of the next day of action, on the basis of the probability distribution Z, corresponding to the combination of the variation coefficient X and the probability Y Each standard deviation σ _it of the bearer t is calculated. In this embodiment, as there is not a sufficient amount to bring date information Bring's t, standard deviation obtained directly from Bring date information Bring's t is not used, using only average spacing days mu _it. It is exemplified below as the average interval of days μ _it = 6.17Days Bring's t.

Since the relationship between the coefficient of variation X and the standard deviation σ _i is X = σ _i / μ _i , the standard deviation σ _i is σ _i = X · μ _i (X is the coefficient of variation, μ _i is the average number of days between intervals). It can be calculated from the formula of. Therefore, based on the probability distribution Z illustrated in FIG. 5C, each standard deviation σ _it of the bearer t corresponding to the combination of each coefficient of variation X and the probability Y in the probability distribution Z is calculated. The calculated standard deviation σ _it of the bearer is shown in the table of FIG. 6 (A) together with the probability distribution Z. From this table, for example, the probability that the bearer t takes the standard deviation σ _it = 0.617 can be determined to be about 0.034.

Since the probability Y does not appear as it is relatively low, the standard deviation σ _it may be calculated for all, but for example, for the coefficient of variation X corresponding to the probability range including the highest probability. , May be calculated selectively. An example is shown with reference to FIG. 5 (B). Based on FIG. 5B, the lower limit of the range of the coefficient of variation X can be set to, for example, "0.0". On the other hand, as the upper limit of the range of the coefficient of variation, "μ _x + 3σ _x " is selected as the upper limit of the range of the coefficient of variation X from the average μ _x of the coefficient of variation X and the standard deviation (variance) σ _{x of the} coefficient of variation X. .. In that case, about 99% of the events are included in the range from the lower limit to the upper limit of the coefficient of variation. Therefore, for example, if the condition μ = μ _x = 0.6 and σ = σ _x = 0.25 in FIG. 5B, the upper limit of the coefficient of variation X can be determined to be 1.35. Therefore, for example, the coefficient of variation X may be selectively calculated in the range of 0 to 1.35.

The interval in days probability calculating step, then, the average interval of days mu _it and the respective standard deviation sigma _it, based on a normal distribution, for each of the standard deviation sigma _it, each candidate interval days A until the next day of action The probability B of each candidate interval day A is calculated, and the probability Y corresponding to the standard deviation σ _it is weighted to the probability B for each candidate interval day A to calculate the weighted average probability C for each candidate interval day A.

Assuming that the average interval days μ _it and the standard deviation σ _it in the table of FIG. 6 (A) follow a normal distribution, the probability density with respect to the interval days is further calculated for each standard deviation σ _it . A part of this result is illustrated in the graph of the probability density function of FIG. 6 (B). In FIG. 6B, three types of examples in which the standard deviation σ _it is 0.617, 1.234, and 1.851 are shown, but the present invention is not limited to this, and the same applies to each standard deviation σ _it . The probability density function is calculated in. Then, the probability B is calculated for each candidate interval day A from the graph of the probability density function of each standard deviation σ _it . Since the probability Y of each standard deviation σ _it is also known, the probability B for each candidate interval day A is further weighted with the probability Y corresponding to the standard deviation σ _it , and the sum is taken. The weighted average probability C for each candidate interval day A can be calculated.

More specifically, it will be described with reference to FIG. In Figure 7, the standard deviation sigma _it shows three examples of 2.468,3.085,3.702, this is not limited, for each standard deviation sigma _t, similarly, as follows The probability is calculated. That is, by applying the average interval days μ _it and each standard deviation σ _it to Equation 1 described later and performing an integral calculation, as shown in FIG. 7 (A), the candidate interval days A for each standard deviation σ _it. The probability is calculated for each. This step is carried out, for example, by the procedure as shown in the flowchart of FIG. 9 described in the second embodiment. Then, each standard deviation σ _it has a unique probability Y. For example, as shown in FIG. 7 (A), if σ _it = 2.468, the probability Y is 0.132850 and σ _it = 3.085 based on the table of FIG. 6 (A). , Based on the table of FIG. 6 (A), the probability Y is 0.153928, and if σ _it = 3.702, the probability Y is 0.152934 based on the table of FIG. 6 (A). Therefore, the weighted average probability C for each candidate interval day A is calculated by weighting the probability B of each candidate interval day A and further weighting the probability Y corresponding to the standard deviation σ _it and taking the sum. .. For example, when the number of candidate interval days A = 6Days, from the shaded result and probability Y in FIG. 7 (A), [0.159 × 0.132850] + [0.128 × 0.153928] + [0.107 × 0.152934] ... , The final weighted average probability can be calculated by weighting the probability B with the probability Y and obtaining the sum.

Next, in the timing determination step, in the increasing direction of the candidate interval days A, the number of candidate interval days showing the weighted average probability C _th below an arbitrary threshold value after the maximum value C _{max of the} weighted average probability C. When A _th is selected and the day when the candidate interval days _Ath elapses from the day when the bearer t last brought the garbage, the timing for taking an action to encourage the bearer t to bring the garbage is taken. Determined as the base date. The timing determination step can be executed, for example, by the timing determination unit 14 of the timing determination device 10.

As illustrated in FIG. 7B, the interval day probability calculation step calculates, for each candidate interval day A, a weighted average probability C indicating the possibility of occurrence. Based on the table of FIG. 7B, since the candidate interval days A = 6Days has the highest probability C, the possibility that the bearer t will bring the garbage next is 6 days after the final bring-in date. Probability is high. However, after 6 days, which is the most likely, when the garbage station operator takes an action to urge the bearer t to bring it, for example, he feels that he was urged even though he was thinking of bringing it the next day. , You may not bring it. Therefore, in the present invention, the number of days that are extremely unlikely to be brought is selected by using the threshold value, not the days that are most likely to be brought. That is, in the direction of increasing the candidate interval days A, likely probability C is the maximum value C _max after, selecting the candidate interval of days A _th indicates the probability C _th below the arbitrary threshold. The threshold value can be set arbitrarily, and examples thereof include 0.01, 0.005, and 0.001. When the threshold value is set to 0.01 (1%) with respect to the probability C in FIG. 7B, the candidate interval days A = 13 Days can be selected as the candidate interval days A _th . Then, the day when 13 days have passed from the day when the bearer t last brought the garbage can be determined as the reference date for the timing of taking the action for encouraging the bearer t to bring the garbage.

The threshold value can be arbitrarily set by further feeding back the result of the action performed by the operator on the bearer based on the result of the timing determination, for example.

Next, the output step outputs the timing. In the present invention, the “timing output” may be, for example, the output of the timing reference date, the day on which the action is taken based on the reference date, or the period during which the action is taken. The output step can be executed by, for example, the output unit 15 of the timing determination device 10, and may be output from the timing determination device 10 to the external device as described above, or may be displayed on the display 105 of the timing determination device 10. You may.

[Embodiment 2]
For example, some bearers do not have a sufficient amount of carry-on date information accumulated, while others do. In the first embodiment, even a bearer who has not accumulated a sufficient amount of carry-on date information can accurately estimate the number of days between bring-in and determine the timing. In the second embodiment, a mode in which the number of candidate days is estimated from the bring-in date information of the bring-in date for which a sufficient amount of bring-in date information has been accumulated and the timing is determined will be illustrated. It should be noted that this embodiment does not exclude the processing according to the first embodiment for the bearer who has accumulated a sufficient amount of carry-on date information.

FIG. 8 is a block diagram showing a configuration of an example of the timing determination device 10 of the present embodiment, and is the same as the timing determination device 10 of the first embodiment unless otherwise specified. The timing determination device 10 of the present embodiment includes the interval day number probability calculation unit 13 in the first embodiment as the first interval day probability calculation unit 13, and further includes the selection unit 21 and the second interval day probability calculation unit 22. ..

Based on the bring-in date information of the bring-in date, the selection unit 21 excludes the bring-in date from the estimation target when the bring-in date information is less than two, and the bring-in date information is less than four (or average). When the number of interval days information is less than 3 (the same applies hereinafter), and when the average number of interval days is not normal, the bearer t is subject to processing the bring date information by the first interval day probability calculation unit 13. Select as a person. If the information on the carry-on date is less than two, the information on the number of days between the bring-in t does not exist, so that it cannot be estimated and is excluded from the estimation target. In addition, when the information on the bring-in date is less than 4, for example, since the normality test is not possible, the information on the bring-in date is 4 or more (or the information on the average interval days is 3 or more, and so on). However, if there is no normality, the first interval days probability calculation unit 13 performs processing on the assumption that a sufficient amount of reliable information does not exist.

Further, when the information on the carry-on date is four or more and the information on the average interval days has normality based on the carry-on date information of the bring-in person t, the selection unit 21 sets the bring-in date t. 2 The interval day probability calculation unit 22 selects the person to process the bring-in date information.

As described above, according to the present embodiment, the selection unit 21 can change the means for calculating the interval day probability depending on whether or not the bearer t is a bearer for which a sufficient amount of carry-on date information is not accumulated.

When the selection unit 21 selects the bringer t as the target person for processing the bring-in date information by the second interval day probability calculation unit 22, the second interval day probability calculation unit 22 determines the average number of interval days of the bringer t. From μ _i and the standard deviation σ _i , the probability B for each candidate interval day A is calculated based on the normal distribution. Then, the timing determination unit 14 selects the candidate interval days _Ath indicating the probability _Bth below an arbitrary threshold value after the maximum value B _{max of the} probability B in the increasing direction of the candidate interval days A, and the bearer. The day on which the candidate interval days _Ath elapses from the day when t last brought the garbage is determined as the reference date for the timing of taking the action for prompting the bearer t to bring the garbage.

The timing determination method of the present embodiment includes the interval day number probability calculation step in the first embodiment as the first interval day probability calculation step, and further includes the selection step and the second interval day probability calculation step. This is the same as the timing determination method of the first embodiment.

In the selection step, when the bring-in date information is less than two, the bringer t is excluded from the estimation target, and when the bring-in date information is less than four, the bring-in date information is excluded from the estimation target. If there is no normality in the average number of days between intervals, the bearer t is selected as the target person for processing the bring-in date information by the first interval days probability calculation step. Further, in the selection step, when the information on the carry-on date is four or more and the information on the average interval days has normality based on the carry-on date information of the bring-in person t, the bring-in date t is referred to. 2 The interval day probability calculation unit 22 selects the person to process the bring-in date information. The selection step can be executed, for example, by the selection unit 21 of the timing determination device 10.

When the selection step selects the bearer t as the target person for processing the bring-in date information by the second interval day probability calculation step, the second interval day probability calculation step is the average number of interval days of the bearer t. From μ _i and the standard deviation σ _i , the probability B for each candidate interval day A is calculated based on the normal distribution. Then, in the timing determination step, in the increasing direction of the candidate interval days A, after the maximum value B _{max of the} probability B, the candidate interval days _Ath showing the probability _Bth below an arbitrary threshold value is selected, and the bearer The day on which the candidate interval days _Ath elapses from the day when t last brought the garbage is determined as the reference date for the timing of taking the action for prompting the bearer t to bring the garbage. The second interval day probability calculation step can be executed, for example, by the second interval day probability calculation unit 22 of the timing determination device 10.

The second interval day probability calculation step will be described by taking the flowchart of FIG. 9 as an example. First, based on the bring date information Bring's t, it calculates an average interval of days mu _it (S101), and calculates the standard deviation σ _it (S102). These may be calculated, or the information stored in advance in the storage unit 11 may be used.

Next, A in the following equation 1 is set to the initial value "1" (S103). Equation 1 is, for example, a definite integral equation for calculating the area of the filled area in the probability density function of FIG. In Equation 1, A is the candidate interval days from the last bring-in date to the next expected bring-in date, μ is the average interval days μ _it , σ is its standard deviation σ _it , and x is its standard deviation σ _it. , Is a real variable in the integral method.

Next, the probability B of the number of candidate interval days A = 1 day is calculated by the above formula 1 (S104), and this is recorded (S105). Then, go (S106) increases the interval days A by-day interval days A may determine whether more than "μ _it + 3σ _it" earlier (S107), "μ _it + 3σ _it" if: (NO), repeats the process from the step (S104), the interval days a is, if more than "μ _it + 3σ _it" earlier (YES), and ends by outputting the results obtained (END).

By these steps, for example, when the average interval days μ _it = 6.17 Days and the standard deviation σ _it = 0.98, the probability B for each candidate interval days A is calculated as shown in the table of FIG. , Is output. Then, with respect to this probability B, 9 days can be selected as the interval days A below the threshold value (for example, 0.01) as in the first embodiment.

Next, the timing determination method of the present embodiment will be described by taking the flowchart of FIG. 10 as an example.

First, the bearer t, which is the target of estimation of the next action date, is determined (S201). Then, based on the bring-in date information of the bearer t, it is determined whether or not there are two or more bring-in date information (S202), and if there are two or more (YES), four carry-on date information is further obtained. It is determined whether or not it is the above (S204). If there are four or more pieces of information on the date of bringing in (YES), a normal test is performed on the information (S205) to determine whether or not the information is normal (S206). If there is normality (YES), assuming that a sufficient amount of carry-on date information has been accumulated for the bearer t, the second interval day probability calculation step described above is performed (S207), and the reference date for timing is determined. (S210).

On the other hand, when the information on the bring-in date is less than two (S202, NO), it is determined that the timing cannot be determined because there is no information on the number of interval days (S203). In addition, when the information on the bring-in date is less than 4 (S204, NO) and when it is judged that there is no normality by the normal test (S205) (S206, NO), the information on the number of interval days is sufficient. If not, the coefficient of variation distribution calculation step is performed (S208). For the coefficient of variation distribution, for example, information stored in the storage unit 11 calculated in advance may be used. Then, the first interval day probability calculation step described in the first embodiment is further performed (S209), and the reference date of the timing is determined (S210).

Then, as a result of the determined timing, the result of not being able to determine the timing is output (S211), and the process ends.

[Embodiment 3]
The program of the present embodiment is a program capable of executing the timing determination method of the present invention on a computer. Alternatively, the program of this embodiment may be recorded on, for example, a computer-readable recording medium. The recording medium is not particularly limited, and examples thereof include the storage medium described above.

Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made within the scope of the present invention in terms of the structure and details of the present invention.

10 Timing determination device 11 Storage unit 12 Coefficient of variation distribution calculation unit 13 Interval days probability calculation unit 14 Timing determination unit 15 Output unit

Claims (10)

Includes storage unit, coefficient of variation distribution calculation unit, interval days probability calculation unit, timing determination unit, and output unit.
The storage unit
Memorize the date of bringing garbage for each of multiple bearers,
The carry-on date information includes an average interval day μ _i , a standard deviation σ _i, and a coefficient of variation X for the interval days of the bring-in date.
The coefficient of variation X is the ratio of the standard deviation σ _i to the average interval days μ _i .
The coefficient of variation distribution calculation unit
From the coefficient of variation X of the plurality of bearers, a probability distribution Z showing the relationship between the coefficient of variation X and its probability Y is calculated based on the normal distribution.
The interval days probability calculation unit
From the average interval days μ _it of the bearer t, which is the estimation target of the next action day, each standard deviation σ _it of the bearer t corresponding to the combination of each coefficient of variation X and the probability Y based on the probability distribution Z. Is calculated and
Wherein the average interval of days mu _it and the respective standard deviation sigma _it, based on a normal distribution, for each of the standard deviation sigma, calculates the probability B for each candidate interval days A until the next day of action,
The probability B for each of the candidate interval of days A, the weighted probability Y corresponding to the standard deviation sigma, calculates the weighted average probability C of each of the candidate interval of days A,
The timing determination unit
In the increasing direction of the candidate interval days A, after the maximum value C _{max of the} weighted average probability C, a candidate interval days A _th indicating a weighted average probability C _th below an arbitrary threshold value is selected.
The day when the candidate interval days _Ath elapses from the day when the bearer t last brought the garbage is determined as the reference date for the timing of taking an action to encourage the bearer t to bring the garbage.
The output unit
Output the timing,
A device that determines the timing to encourage the bringing of garbage. In addition, it includes a selection
The selection unit
Based on the carry-on date information of the bring-in date, if there are less than two bring-in date information, the bring-in date t is excluded from the estimation target.
If there are less than four bring-in date information, and if the average number of days is not normal, the bring-in t is selected as the target person for processing the bring-in date information by the interval-day probability calculation unit. The determination device according to claim 1. The interval day probability calculation unit is included as the first interval day probability calculation unit.
In addition, it includes a second interval day probability calculation unit.
The selection unit
If there are four or more bring-in date information and the average interval days information has normality based on the bring-in date information of the bearer t, the carry-on t is referred to as the second interval day probability calculation unit. Select as the target person to process the bring-in date information by
The second interval day probability calculation unit
From the average interval days μ _it and the standard deviation σ _{it of the} bearer t, the probability B for each candidate interval days A is calculated based on the normal distribution.
The timing determination unit
In the increasing direction of the candidate interval days A, a candidate interval days A _th indicating a probability B _th that falls below an arbitrary threshold value after the maximum value B _{max of the} probability B is selected.
Claimed to determine the day on which the candidate interval days _Ath elapses from the day when the bearer t last brought the garbage as a reference date for the timing of taking an action to encourage the bearer t to bring the garbage. 2. The determination device according to 2. The determination device according to any one of claims 1 to 3, wherein each number of days is the number of days excluding holidays at the place of bringing. Including the coefficient of variation distribution calculation process, interval day probability calculation process, timing determination process, and output process
Using the carry-on date information regarding the carry-on of garbage for each of multiple bearers,
The carry-on date information includes an average interval day μ _i , a standard deviation σ _i, and a coefficient of variation X for the interval days of the bring-in date.
The coefficient of variation X is the ratio of the standard deviation σ _i to the average interval days μ _i .
The coefficient of variation distribution calculation step is
From the coefficient of variation X of the plurality of bearers, a probability distribution Z showing the relationship between the coefficient of variation X and its probability Y is calculated based on the normal distribution.
The interval day probability calculation step is
From the average interval days μ _it of the bearer t, which is the estimation target of the next action day, each standard deviation σ _it of the bearer t corresponding to the combination of each coefficient of variation X and the probability Y based on the probability distribution Z. Is calculated and
Wherein the average interval of days mu _it and the respective standard deviation sigma _it, based on a normal distribution, for each of the standard deviation sigma, calculates the probability B for each candidate interval days A until the next day of action,
The probability B for each of the candidate interval of days A, the weighted probability Y corresponding to the standard deviation sigma, calculates the weighted average probability C of each of the candidate interval of days A,
The timing determination step is
In the increasing direction of the candidate interval days A, after the maximum value C _{max of the} weighted average probability C, a candidate interval days A _th indicating a weighted average probability C _th below an arbitrary threshold value is selected.
The day on which the candidate interval days _Ath elapses from the day when the bearer t last brought the garbage is determined as the reference date for the timing of taking an action to encourage the bearer t to bring the garbage.
The output process is
Output the timing,
A method of determining the timing to encourage the bringing of garbage, which is characterized by this. In addition, it includes a selection process
The selection step is
Based on the carry-on date information of the bring-in date, if there are less than two bring-in date information, the bring-in date t is excluded from the estimation target.
If there are less than four bring-in date information, and if the average number of days is not normal, the bring-in t is selected as the target person for processing the bring-in date information by the interval day probability calculation step. The determination method according to claim 5. The interval day probability calculation step is included as the first interval day probability calculation step.
Further, the second interval day probability calculation step is included.
The selection step is
When there are four or more bring-in date information and the average interval days information has normality based on the bring-in date information of the bring-in t, the bring-in t is used in the second interval day probability calculation step. Select as the target person to process the bring-in date information by
The second interval day probability calculation step is
From the average interval days μ _it and the standard deviation σ _{it of the} bearer t, the probability B for each candidate interval days A is calculated based on the normal distribution.
The timing determination step is
In the increasing direction of the candidate interval days A, a candidate interval days A _th indicating a probability B _th that falls below an arbitrary threshold value after the maximum value B _{max of the} probability B is selected.
Claimed to determine the day on which the candidate interval days _Ath elapses from the day when the bearer t last brought the garbage as a reference date for the timing of taking an action to encourage the bearer t to bring the garbage. The determination method according to 6. The determination method according to any one of claims 5 to 7, wherein each number of days is the number of days excluding holidays at the place of bringing. A program comprising causing a computer to execute the method for determining the timing according to any one of claims 5 to 8. A computer-readable recording medium on which the program according to claim 9 is recorded.