JP6566499B2 - Shipment quantity prediction device, shipment quantity prediction method, and program - Google Patents

Description

The present invention predicts a unit volume when shipping the agricultural via current shipping field, delivery quantity prediction apparatus, shipments prediction method, and relates to a program for realizing these.

  In recent years, retailers such as supermarkets have been required to ship fixed quantities to producers on a regular basis, especially for soft vegetables such as spinach and lettuce, so there is a contract between producers and retailers. Transactions are increasing. In order to deal with such contract transactions, a shipping cooperative producer group is formed among the producers, and the producers belonging to the group are operated to complement each other's quantity of agricultural products to be delivered. ing.

  In such operations, the person in charge at the collection / shipping site and the local instructor (hereinafter, these persons are collectively referred to as “manager”) collect the amount of agricultural products collected from each producer at the collection / shipping place. In order to reach the contracted shipment quantity, the producers are instructed to harvest and ship.

  By the way, in order to negotiate a contract with a retailer, the above-mentioned shipping cooperative producer group needs to grasp the expected shipping time and the predicted shipping quantity of each producer as accurately as possible. For this reason, the manager of the collection / shipment site listens to each producer for the expected shipment date and the expected shipment quantity, and predicts the quantity that can be shipped by the entire organization. There are cases where accuracy is lacking.

  On the other hand, for example, Patent Literature 1 discloses an agricultural production information management system that predicts a future shipping time and a shipping quantity for each field. Specifically, the system disclosed in Patent Literature 1 acquires past shipment plans and past shipment results stored in a database, and compares the acquired past shipment plans with past shipment results. Thus, it is predicted how much agricultural products are deficient in which field at which shipping time.

  Furthermore, in the system disclosed in Patent Document 1, when the database stores changes in past temperature and changes in past rainfall, these data include changes in the temperature of this year and changes in this year's rainfall. By applying the above, the future shipping time and the shipping quantity are predicted more accurately.

  Therefore, using the system disclosed in Patent Document 1, it is considered that the producer can predict the shipping time and the shipping quantity more accurately than before.

Japanese Patent No. 5356663

  However, in the system disclosed in Patent Document 1, past shipment records must be stored in a database. In addition, the possibility of a deviation between the predicted shipping time and the actual shipping time is not taken into consideration. For this reason, there exists a problem that it cannot respond when it is necessary to estimate a shipment quantity every day like a contract transaction.

  That is, since the contract transaction needs to ship a quantity determined on a daily basis, when the contract is made based on the shipping time and the shipping quantity predicted by the system disclosed in Patent Document 1, It is highly probable that a breach of contract will occur.

An example of the object of the present invention is to solve the above problem and consider that even if the past shipment record is not accumulated in the database, there is a deviation in the shipment time predicted using the experience and know-how accumulated by the producer. Thus, it is an object of the present invention to provide a shipment quantity prediction device, a shipment quantity prediction method, and a program capable of predicting the shipment time and shipment quantity of agricultural products.

In order to achieve the above object, a first shipment quantity predicting apparatus according to one aspect of the present invention includes:
A data acquisition unit configured to acquire an expected shipment quantity set by an agricultural producer, an expected number of days from a reference date to an expected shipment date of the agricultural product, and a deviation day before and after the expected number of days;
An expected value calculation unit for calculating an expected value of the shipping quantity on the expected shipping date and the days before and after the statistical shipping process using the predicted shipping quantity, the expected number of days, and the deviation days;
It is characterized by having.

In order to achieve the above object, a second shipment quantity prediction device according to one aspect of the present invention is provided.
A data acquisition unit for acquiring a reference date, an expected shipment date, and an estimated shipment quantity set by a producer of agricultural products;
A result acquisition unit that acquires the number of days from the reference date to the actual shipping date as the actual number of days;
A result accumulating unit for accumulating the acquired actual number of days;
In the case where the actual number of days is stored in the result storage unit, the average and standard deviation of the actual number of days are calculated based on the stored actual number of days, and the calculated average number of standard days and the standard deviation are calculated. An expected value calculation unit that calculates an expected value of the shipping quantity on the expected shipping date and on the days before and after the estimated shipping date, using a determined normal distribution and the predicted shipping quantity;
It is characterized by having.

In order to achieve the above object, a first shipment quantity prediction method according to one aspect of the present invention includes:
(A) obtaining an expected shipment quantity, an expected shipment number set from a reference date to an expected shipment date of the agricultural product, and a number of deviation days before and after the expected number of days set by the producer of the agricultural product;
(B) calculating an expected value of the shipping quantity on the predicted shipping date and the days before and after the predicted shipping date by statistical processing using the predicted shipping quantity, the expected number of days, and the number of deviation days;
It is characterized by having.

In order to achieve the above object, a second shipment quantity prediction method according to one aspect of the present invention includes:
(A) obtaining a reference date, an expected shipment date, and an estimated shipment quantity set by the producer of the agricultural product;
(B) obtaining the number of days from the reference date to the actual shipping date as the actual number of days;
(C) accumulating the actual number of days; and
(D) When the actual number of days is accumulated in the step (c), the average and standard deviation of the actual days are calculated based on the accumulated actual days, and the calculated actual days Using the normal distribution determined by the average and standard deviation, and the expected shipment quantity, calculating the expected value of the shipment quantity on the expected shipment date and the days before and after,
It is characterized by having.

In order to achieve the above object, the first program according to one aspect of the present invention includes:
On the computer,
(A) obtaining an expected shipment quantity, an expected shipment number set from a reference date to an expected shipment date of the agricultural product, and a number of deviation days before and after the expected number of days set by the producer of the agricultural product;
(B) calculating an expected value of the shipping quantity on the predicted shipping date and the days before and after the predicted shipping date by statistical processing using the predicted shipping quantity, the expected number of days, and the number of deviation days;
Allowed to run and wherein the Turkey.

Furthermore, in order to achieve the above object, the second program according to one aspect of the present invention includes:
On the computer,
(A) obtaining a reference date, an expected shipment date, and an estimated shipment quantity set by the producer of the agricultural product;
(B) obtaining the number of days from the reference date to the actual shipping date as the actual number of days;
(C) accumulating the actual number of days; and
(D) When the actual number of days is accumulated in the step (c), the average and standard deviation of the actual days are calculated based on the accumulated actual days, and the calculated actual days Using the normal distribution determined by the average and standard deviation, and the expected shipment quantity, calculating the expected value of the shipment quantity on the expected shipment date and the days before and after,
Allowed to run and wherein the Turkey.

  As described above, according to the present invention, even if the past shipment record is not accumulated in the database, the agricultural product is produced in consideration of the deviation in the shipment time predicted using the experience and know-how accumulated by the producer. It is possible to predict the shipping time and the shipping quantity.

FIG. 1 is a block diagram showing a configuration of a shipment quantity prediction apparatus according to Embodiment 1 of the present invention. FIG. 2 is a diagram showing an example of a normal distribution used in Embodiment 1 of the present invention. FIG. 3 is a flowchart showing the operation of the shipment quantity predicting apparatus according to Embodiment 1 of the present invention. FIG. 4 is a diagram showing an example of expected shipment quantity values listed in the first embodiment of the present invention. FIG. 5 is a block diagram showing the configuration of the shipment quantity prediction apparatus according to Embodiment 2 of the present invention. FIG. 6 is a flowchart showing the operation of the shipment quantity predicting apparatus according to Embodiment 2 of the present invention. FIG. 7 is a block diagram showing an example of a computer that implements the shipment quantity prediction apparatus according to Embodiments 1 and 2 of the present invention.

(Embodiment 1)
Hereinafter, a shipment quantity prediction apparatus, a shipment quantity prediction method, and a program according to Embodiment 1 of the present invention will be described with reference to FIGS.

[Device configuration]
Initially, the structure of the shipment quantity prediction apparatus in Embodiment 1 of this invention is demonstrated using FIG. FIG. 1 is a block diagram showing a configuration of a shipment quantity prediction apparatus according to Embodiment 1 of the present invention.

  A shipment quantity prediction apparatus 10 shown in FIG. 1 is an apparatus for predicting the shipment quantity of agricultural products shipped via a collection / shipping place. As shown in FIG. 1, the shipment quantity prediction device 10 includes a data acquisition unit 11 and an expected value calculation unit 12.

  The data acquisition unit 11 acquires the expected shipment quantity, the expected number of days from the reference date to the expected shipment date of the agricultural product, and the number of deviation days before and after the expected shipment date set by the producer of the agricultural product. The expected value calculation unit 12 calculates the expected value of the shipping quantity on the expected shipping date and the days before and after it by statistical processing using the predicted shipping quantity, the expected number of days, and the number of deviation days.

  As described above, in the present embodiment, statistical processing is performed in consideration of the deviation of the shipping time predicted by the experience and know-how accumulated by the producer without using the past shipping record. As a result, the shipment quantity is predicted not only for the expected shipment date but also before and after that. The shipment quantity prediction apparatus 10 according to the first embodiment can predict the shipment time and the shipment quantity of agricultural products in consideration of the occurrence of a deviation in the predicted shipment time.

  Next, in addition to FIG. 1, the configuration and function of the shipment quantity prediction apparatus 10 according to the first embodiment will be described more specifically with reference to FIG. First, as shown in FIG. 1, in the first embodiment, the shipment quantity prediction apparatus 10 is connected to the terminal device 21 of the producer 20 via a network 40 such as the Internet. The shipment quantity prediction apparatus 10 is also connected to the terminal device 31 of the manager 30 at the collection / shipping place.

  In the first embodiment, each producer has the expected shipment quantity, the reference date, the expected number of days from the reference date to the expected shipment date, and the expected number of days, Enter the number of deviation days before and after the estimated shipping date. Examples of the reference date include a day when seeds are sown and a day when seedlings are planted. When each piece of data is input, the terminal device 21 transmits the input data to the shipment quantity prediction device 10. As a result, the data acquisition unit 11 acquires the predicted shipment quantity, the predicted shipment date, and the number of deviation days from each producer 20.

  In the first embodiment, for example, as shown in FIG. 2, the expected value calculation unit 12 sets the standard deviation to a value obtained by dividing the value of the number of days of deviation by the setting coefficient α = 3, assuming the average number of days as μ. An expected value is calculated using a normal distribution, which is σ. FIG. 2 is a diagram showing an example of a normal distribution used in Embodiment 1 of the present invention. The expected value is calculated by such processing with the probability of 99.73% within the range of μ ± 3σ from the characteristics of the normal distribution, assuming that the expected number of days from the reference date to the expected shipping date follows a normal distribution. This is because the expected number of days falls and can be approximated to 3σ≈days of deviation.

  Moreover, in this Embodiment 1, the data acquisition part 11 can further acquire the parameter | index showing the certainty of the estimated shipment quantity, the estimated number of days, and the deviation days which the producer set. This index representing the certainty should be set based on the producer's know-how. In this case, the expected value calculation unit 12 can reduce the value of the setting coefficient α that divides the value of the deviation days as the probability that the index represents is lower.

  For example, in the terminal device 21, it is assumed that the user can select confidence for each prediction in three stages (high, medium, and low) as the index. In this case, when the user inputs “high”, the expected value calculation unit 12 sets α to “3”. Similarly, the expected value calculation unit 12 sets α to “2” when the user inputs “middle”, and sets α to “1” when the user inputs “low”.

  For example, when the user inputs “medium” and sets the number of deviation days to 3, the expected value calculation unit 12 sets α to “2” and σ = 3/2. 1.5 ". Thus, the higher the probability represented by the index is, the larger the value of the setting coefficient α is, as shown in FIG. 2, the setting coefficient α corresponds to the coefficient of σ on the horizontal axis shown in FIG. This is because the higher the value of α, the higher the possibility that the actual shipping date will fall within the range of deviation days. Specifically, from the characteristics of the normal distribution, within the range of μ ± 3σ, μ ± 2σ, μ ± σ, the shipping date has a probability of 99.73%, 95.45%, 68.27%, respectively. Will fit in.

  Specifically, the expected value calculation unit 12 sets h as the expected shipment quantity, t as the number of days from the reference date on the date on which the expected value is calculated, and the following formulas (1) and (2) ) To calculate the expected value.

  By the calculation process using the above formulas (1) and (2), for each producer 20, the expected shipping date and the expected values for the number of deviation days before and after that are calculated. Therefore, the manager of the collection / shipment site can predict the quantity of agricultural products gathered at the collection / shipment site before and after the expected shipment date. This point will be described later with reference to FIG.

  Moreover, said Formula (2) can also be rewritten as follows.

[Device operation]
Next, the operation of the shipment quantity prediction apparatus 10 according to Embodiment 1 of the present invention will be described with reference to FIG. FIG. 3 is a flowchart showing the operation of the shipment quantity predicting apparatus according to Embodiment 1 of the present invention. In the following description, FIGS. 1 and 2 are referred to as appropriate. Moreover, in this Embodiment 1, the shipment quantity prediction method is implemented by operating the shipment quantity prediction apparatus 10. Therefore, the description of the shipment quantity prediction method in the first embodiment is replaced with the following description of the operation of the shipment quantity prediction apparatus 10.

  First, as a premise, each producer uses the terminal device 21 to predict the expected shipment quantity, the reference date, the expected number of days from the reference date to the expected shipment date, the number of deviation days before and after the expected shipment date, and the indicator (confidence level). And the data is transmitted to the shipment quantity prediction apparatus 10.

  As shown in FIG. 3, in the shipment quantity prediction apparatus 10, first, the data acquisition unit 11 acquires the estimated shipment quantity, the reference date, the expected number of days, the number of deviation days, and the index transmitted from each terminal device 21. (Step A1).

  Next, the expected value calculation unit 12 calculates the average μ and the standard deviation σ necessary for the normal distribution (step A2). Specifically, the expected value calculation unit 12 sets the expected number of days as an average μ. The expected value calculation unit 12 calculates a setting coefficient α from the index, and calculates a standard deviation σ from the calculated α.

  Next, the expected value calculation unit 12 calculates the expected value of the shipment quantity using the normal distribution determined by the average μ and the standard deviation σ obtained in step A2 (step A3). Specifically, the expected value calculation unit 12 calculates an expected value for each user using the above formulas (1) and (2) (step A3).

  For example, assume that a certain user has an estimated shipment quantity of 100 kg, a reference date of October 7, an estimated number of days of 20, a deviation of ± 3 days, and an index of “medium”. In this case, for this user, h = 100, μ = 20, and σ = 3/2, and for each of t = −3, −2, −1, 0, +1, +2, +3, the above equation (1) And an expected value is calculated using (2).

  Next, the expected value calculation unit 12 lists the expected value of the shipment quantity calculated in step A3 in time series (step A4). Specifically, as illustrated in FIG. 4, the expected value calculation unit 12 sums up the expected values calculated for each user for each day and each week, and lists the expected values.

  FIG. 4 is a diagram showing an example of expected shipment quantity values listed in the first embodiment of the present invention. The example of FIG. 4 shows a case where producers A and B ship spinach as agricultural products. In this case, it is assumed that spinach can be shipped in 20 days from sowing. Further, it is assumed that the reference date is a sowing date, and the producers A and B have input data after seeding.

  Specifically, the producer A inputs October 7 as the base date, 100 kg as the expected shipment quantity, 20 days as the expected number of shipments, ± 3 days as the number of deviation days on October 7, On the 17th month, October 17 is entered as the reference date, 200 kg as the expected shipment quantity, 20 days as the expected number of days, and ± 3 days as the number of deviation days. In addition, on October 11, Producer B has input October 11 as the reference date, 300 kg as the expected shipment quantity, 20 days as the expected number of days, and ± 3 days as the number of deviation days.

  In the example of FIG. 4, the expected value calculation unit 12 calculates an expected value for each day for the producer A and the producer B, and further, on the day when the expected values for both the producers A and B are calculated. Sums the expected values of both. The expected value calculation unit 12 also calculates a total value of expected values for each week. And the expected value calculation part 12 lists the total value of the expected value of both the producers A and B for every day, and the total value of the expected value of both the producers A and B for every week. In the example of FIG. 4, the total value for each week is calculated. However, in the first embodiment, the total value may be calculated every 10 days, for example, and the number of days is particularly limited. It is not a thing.

  Thereafter, the expected value calculation unit 12 creates image data for the list and transmits the created image data to the terminal device 31 in order to display the created list on the screen of the terminal device 31 of the administrator 30 (step A5). ).

[Effect in Embodiment 1]
As described above, according to the first embodiment, even if the past shipment record is not accumulated in the database, based on the experience and know-how accumulated by the producer, not only the expected shipment date but also before and after that. The quantity that can be shipped is predicted. Accordingly, the manager of the collection / shipping site can smoothly proceed with the contract negotiation with the retailer.

  In addition, in the first embodiment, the agricultural products to be predicted for the shipment quantity are not particularly limited, but the present first embodiment is an agricultural product that requires freshness, for example, soft vegetables, outdoor vegetables, It is especially effective for fruits and fresh flowers.

  Furthermore, in this Embodiment 1, each data acquisition from a producer may be performed for every agricultural field and every unit area. In this case, the expected value of the shipment quantity is calculated for each data acquisition unit (specifically, for each field and for each unit area). Each piece of data acquired from the producer may be updated as needed. In that case, the expected value of the shipment quantity is also recalculated and updated.

[program]
The program according to the first embodiment of the present invention may be a program that causes a computer to execute steps A1 to A5 shown in FIG. By installing and executing this program on a computer, the shipment quantity prediction apparatus 10 and the shipment quantity prediction method in the present embodiment can be realized. In this case, a CPU (Central Processing Unit) of the computer functions as the data acquisition unit 11 and the expected value calculation unit 12 to perform processing.

  The program in the present embodiment may be executed by a computer system constructed by a plurality of computers. In this case, for example, each computer may function as either the data acquisition unit 11 or the expected value calculation unit 12, respectively.

(Embodiment 2)
Next, a shipment quantity prediction device, a shipment quantity prediction method, and a program according to Embodiment 2 of the present invention will be described with reference to FIGS.

[Device configuration]
Initially, the structure of the shipment quantity prediction apparatus in Embodiment 2 of this invention is demonstrated using FIG. FIG. 5 is a block diagram showing the configuration of the shipment quantity prediction apparatus according to Embodiment 2 of the present invention.

  As shown in FIG. 5, the shipment quantity prediction apparatus 50 in the second embodiment differs from the shipment quantity prediction apparatus 10 in the first embodiment shown in FIG. I have. For this reason, in the second embodiment, the processing in the expected value calculation unit 52 is also different. The data acquisition unit 51 functions in the same manner as the data acquisition unit 11 in the first embodiment. In the second embodiment, the data acquisition unit 51 acquires a reference date, an estimated shipment date, and an estimated shipment quantity set by the producer of agricultural products. Hereinafter, the difference from the first embodiment will be mainly described.

  The result acquisition unit 53 acquires the number of days from the reference date set by each producer to the actual shipping date as the actual number of days. The result accumulation unit 54 accumulates the acquired actual number of days.

  In the second embodiment, the expected value calculation unit 52 calculates an expected value using these when the actual number of days is stored in the result storage unit 54. Specifically, the expected value calculation unit 52 calculates the average μ and the standard deviation σ of the actual number of days. The standard deviation σ is obtained from the difference between the actual shipping date and the expected shipping date.

  Subsequently, the expected value calculation unit 52 calculates an expected value by using the normal distribution determined by the average and standard deviation of the calculated actual days and the estimated shipment quantity of the producer. Specifically, the expected value calculation unit 52 in the above formulas (1) and (2), the expected shipment quantity is h, and the number of days from the reference date on the date on which the expected value is calculated is t, Calculate the expected value.

  Further, in the second embodiment, the expected value calculation unit 52 groups the actual number of days accumulated in the result accumulation unit 54 for each one of the producer and the actual shipment date, or for each combination of both. can do. In this case, the expected value calculation unit 52 calculates the average and standard deviation of the actual number of days for each group obtained by the grouping, and uses the normal distribution determined by the calculated average and standard deviation of the actual number of days. Is calculated.

  In addition, when the expected value calculation unit 52 performs grouping for each producer and calculates the expected value, the expected value of each producer is further added, and the value obtained by the addition is totaled in the entire production area. It can also be the expected value of the shipment quantity.

[Device operation]
Next, the operation of the shipment quantity prediction apparatus 50 according to the second embodiment of the present invention will be described with reference to FIG. FIG. 6 is a flowchart showing the operation of the shipment quantity predicting apparatus according to Embodiment 2 of the present invention. In the following description, FIG. In the second embodiment, the shipment quantity prediction method is implemented by operating the shipment quantity prediction apparatus 50. Therefore, the description of the shipment quantity prediction method in the second embodiment is replaced with the following description of the operation of the shipment quantity prediction apparatus 50.

  First, in the second embodiment, as a premise, the record acquisition unit 53 acquires the number of days from the reference date set by each producer to the actual shipment date, and these are stored in the record storage unit 54 as the actual number of days. Assume that it has been accumulated.

  As shown in FIG. 6, first, the expected value calculation unit 52 groups the actual number of days accumulated in the result accumulation unit 54 for each producer (step B1).

  Next, the expected value calculation unit 52 calculates, for each producer, which is a grouping unit, the average μ and the standard deviation σ of the actual number of days required for the normal distribution based on the accumulated number of actual days (step B2).

  Next, the expected value calculation unit 52 calculates the expected value of the shipping quantity using the normal distribution determined by the average μ and the standard deviation σ obtained in step B2 and the predicted shipping quantity for each producer (step) B3).

  Next, the expected value calculation unit 52 lists the expected values of the shipment quantities calculated in step B3 in time series (step B4). Specifically, also in the second embodiment, as in the example shown in FIG. 4, the expected value calculation unit 52 sums the expected values calculated for each user for each day and each week, and calculates the expected value. List.

  Thereafter, the expected value calculation unit 52 creates image data of the list in order to display the created list on the screen of the terminal device 31 of the administrator 30, and transmits the created image data to the terminal device 31 (step B5). ).

[Effects of Embodiment 2]
As described above, according to the second embodiment, even if the past shipment record (actual shipment quantity) is not accumulated in the database, only the expected shipment date is based on the experience and know-how accumulated by the producer. Rather, before and after that, the quantity that can be shipped is predicted. Furthermore, an expected value based on actual data (actual shipping date) can be calculated. Therefore, since the manager of the collection / shipment site can refer to the actual data, the contract negotiation with the retailer can proceed more smoothly.

[program]
The program in the second embodiment of the present invention may be a program that causes a computer to execute steps B1 to B5 shown in FIG. By installing this program in a computer and executing it, the shipment quantity prediction device 50 and the shipment quantity prediction method in the present embodiment can be realized. In this case, a CPU (Central Processing Unit) of the computer functions as a data acquisition unit 51, an expected value calculation unit 52, and a result acquisition unit 53 to perform processing.

  The program in the present embodiment may be executed by a computer system constructed by a plurality of computers. In this case, for example, each computer may function as any of the data acquisition unit 51, the expected value calculation unit 52, and the result acquisition unit 53.

(Physical configuration)
Here, a computer that realizes the shipment quantity prediction apparatus by executing the programs in the first and second embodiments will be described with reference to FIG. FIG. 7 is a block diagram showing an example of a computer that implements the shipment quantity prediction apparatus according to Embodiments 1 and 2 of the present invention.

  As shown in FIG. 7, the computer 110 includes a CPU 111, a main memory 112, a storage device 113, an input interface 114, a display controller 115, a data reader / writer 116, and a communication interface 117. These units are connected to each other via a bus 121 so that data communication is possible.

  The CPU 111 performs various calculations by developing the program (code) in the present embodiment stored in the storage device 113 in the main memory 112 and executing them in a predetermined order. The main memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory). Further, the program in the present embodiment is provided in a state of being stored in a computer-readable recording medium 120. Note that the program in the present embodiment may be distributed on the Internet connected via the communication interface 117.

  Specific examples of the storage device 113 include a hard disk drive and a semiconductor storage device such as a flash memory. The input interface 114 mediates data transmission between the CPU 111 and an input device 118 such as a keyboard and a mouse. The display controller 115 is connected to the display device 119 and controls display on the display device 119.

  The data reader / writer 116 mediates data transmission between the CPU 111 and the recording medium 120, and reads a program from the recording medium 120 and writes a processing result in the computer 110 to the recording medium 120. The communication interface 117 mediates data transmission between the CPU 111 and another computer.

  Specific examples of the recording medium 120 include general-purpose semiconductor storage devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic storage media such as a flexible disk, or CD- An optical storage medium such as ROM (Compact Disk Read Only Memory) can be used.

  It should be noted that the shipment quantity prediction apparatus according to the first and second embodiments can be realized by using hardware corresponding to each unit instead of a computer in which a program is installed. Furthermore, a part of the shipment quantity prediction apparatus may be realized by a program, and the remaining part may be realized by hardware.

  Part or all of the above-described embodiments can be expressed by (Appendix 1) to (Appendix 21) described below, but is not limited to the following description.

(Appendix 1)
A data acquisition unit configured to acquire an expected shipment quantity set by an agricultural producer, an expected number of days from a reference date to an expected shipment date of the agricultural product, and a deviation day before and after the expected number of days;
An expected value calculation unit for calculating an expected value of the shipping quantity on the expected shipping date and the days before and after the statistical shipping process using the predicted shipping quantity, the expected number of days, and the deviation days;
A shipment quantity predicting device comprising:

(Appendix 2)
The expected value calculation unit calculates the expected value using a normal distribution, with an average number of expected days and a value obtained by dividing the value of the deviation days by a setting coefficient as a standard deviation σ.
The shipment quantity prediction apparatus according to appendix 1.

(Appendix 3)
The expected value calculation unit uses h as the expected shipment quantity, t as the number of days from the reference date on the date on which the expected value is calculated, and using the following formulas (1) and (2): Calculating the expected value;
The shipment quantity prediction apparatus according to attachment 2.

(Appendix 4)
The data acquisition unit further acquires an index representing the likelihood of the estimated shipment quantity, the estimated number of days, and the number of deviation days set by the producer,
The expected value calculation unit increases the value of the setting coefficient that divides the value of the deviation days as the probability that the index represents is higher.
The shipment quantity prediction apparatus according to appendix 2 or 3.

(Appendix 5)
A data acquisition unit for acquiring a reference date, an expected shipment date, and an estimated shipment quantity set by a producer of agricultural products;
A result acquisition unit that acquires the number of days from the reference date to the actual shipping date as the actual number of days;
A result accumulating unit for accumulating the acquired actual number of days;
In the case where the actual number of days is stored in the result storage unit, the average and standard deviation of the actual number of days are calculated based on the stored actual number of days, and the calculated average number of standard days and the standard deviation are calculated. An expected value calculation unit that calculates an expected value of the shipping quantity on the expected shipping date and on the days before and after the estimated shipping date, using a determined normal distribution and the predicted shipping quantity;
A shipment quantity predicting device comprising:

(Appendix 6)
The expected value calculation unit is obtained by grouping the actual number of days stored in the result storage unit for each one of the producer and the actual shipping date, or for a combination of both, and by grouping. For each group, calculate the average and standard deviation of the actual number of days, calculate the expected value using a normal distribution determined by the calculated average and standard deviation of the actual number of days, and the estimated shipment quantity,
The shipment quantity prediction apparatus according to attachment 5.

(Appendix 7)
The expected value calculation unit performs grouping for each producer to calculate the expected value, and further adds the expected values of each of the producers. The expected value of the shipment quantity,
The shipment quantity prediction device according to attachment 6.

(Appendix 8)
(A) obtaining an expected shipment quantity, an expected shipment number set from a reference date to an expected shipment date of the agricultural product, and a number of deviation days before and after the expected number of days set by the producer of the agricultural product;
(B) calculating an expected value of the shipping quantity on the predicted shipping date and the days before and after the predicted shipping date by statistical processing using the predicted shipping quantity, the expected number of days, and the number of deviation days;
A shipment quantity prediction method characterized by comprising:

(Appendix 9)
In the step (b), the expected value is calculated using a normal distribution in which the expected number of days is an average μ, and the value obtained by dividing the deviation day value by a setting coefficient is a standard deviation σ. ,
The shipment quantity prediction method according to attachment 8.

(Appendix 10)
In the step (b), the expected shipment quantity is h, the number of days from the reference date on the date for which the expected value is calculated is t, and the following formula (1) and formula (2) are used. Calculating the expected value;
The shipment quantity prediction method according to attachment 9.

(Appendix 11)
In the step (a), an index that represents the likelihood of the estimated shipment quantity, the estimated number of days, and the number of deviation days set by the producer is further acquired;
In the step (b), the higher the probability represented by the index, the greater the value of the setting coefficient that divides the value of the deviation days.
The shipment quantity prediction method according to appendix 9 or 10.

(Appendix 12)
(A) obtaining a reference date, an expected shipment date, and an estimated shipment quantity set by the producer of the agricultural product;
(B) obtaining the number of days from the reference date to the actual shipping date as the actual number of days;
(C) accumulating the actual number of days; and
(D) When the actual number of days is accumulated in the step (c), the average and standard deviation of the actual days are calculated based on the accumulated actual days, and the calculated actual days Using the normal distribution determined by the average and standard deviation, and the expected shipment quantity, calculating the expected value of the shipment quantity on the expected shipment date and the days before and after,
A shipment quantity prediction method characterized by comprising:

(Appendix 13)
In the step (d), the accumulated number of actual days is grouped for each one of the producer and the actual shipping date, or for a combination of both, and for each group obtained by grouping, Calculating the average and standard deviation of the actual number of days, using the normal distribution determined by the calculated average and standard deviation of the actual number of days, and calculating the expected value, using the expected shipment quantity,
The shipment quantity prediction method according to attachment 12.

(Appendix 14)
In the step (d), grouping is performed for each producer to calculate the expected value, and further, the expected values of the producers are added together, and the value obtained by the addition is calculated for the entire production area. The expected value of the total shipment quantity,
The shipment quantity prediction method according to attachment 13.

(Appendix 15)
On the computer,
(A) obtaining an expected shipment quantity, an expected shipment number set from a reference date to an expected shipment date of the agricultural product, and a number of deviation days before and after the expected number of days set by the producer of the agricultural product;
(B) calculating an expected value of the shipping quantity on the predicted shipping date and the days before and after the predicted shipping date by statistical processing using the predicted shipping quantity, the expected number of days, and the number of deviation days;
Help Rogura-time to the execution.

(Appendix 16)
In the step (b), the expected value is calculated using a normal distribution in which the expected number of days is an average μ, and the value obtained by dividing the deviation day value by a setting coefficient is a standard deviation σ. ,
The program according to appendix 15.

(Appendix 17)
In the step (b), the expected shipment quantity is h, the number of days from the reference date on the date for which the expected value is calculated is t, and the following formula (1) and formula (2) are used. Calculating the expected value;
The program according to appendix 16.

(Appendix 18)
In the step (a), an index that represents the likelihood of the estimated shipment quantity, the estimated number of days, and the number of deviation days set by the producer is further acquired;
In the step (b), the higher the probability represented by the index, the greater the value of the setting coefficient that divides the value of the deviation days.
The program according to appendix 16 or 17.

(Appendix 19)
On the computer,
(A) obtaining a reference date, an expected shipment date, and an estimated shipment quantity set by the producer of the agricultural product;
(B) obtaining the number of days from the reference date to the actual shipping date as the actual number of days;
(C) accumulating the actual number of days; and
(D) When the actual number of days is accumulated in the step (c), the average and standard deviation of the actual days are calculated based on the accumulated actual days, and the calculated actual days Using the normal distribution determined by the average and standard deviation, and the expected shipment quantity, calculating the expected value of the shipment quantity on the expected shipment date and the days before and after,
Help Rogura-time to the execution.

(Appendix 20)
In the step (d), the accumulated number of actual days is grouped for each one of the producer and the actual shipping date, or for a combination of both, and for each group obtained by grouping, Calculating the average and standard deviation of the actual number of days, using the normal distribution determined by the calculated average and standard deviation of the actual number of days, and calculating the expected value, using the expected shipment quantity,
The program according to appendix 19.

(Appendix 21)
In the step (d), grouping is performed for each producer to calculate the expected value, and further, the expected values of the producers are added together, and the value obtained by the addition is calculated for the entire production area. The expected value of the total shipment quantity,
The program according to appendix 20 .

  Although the present invention has been described 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 to the configuration and details of the present invention within the scope of the present invention.

  This application claims the priority on the basis of Japanese application Japanese Patent Application No. 2015-194706 for which it applied on September 30, 2015, and takes in those the indications of all here.

  As described above, according to the present invention, it is possible to predict the shipping time and the shipping quantity of agricultural products in consideration of the occurrence of a deviation in the predicted shipping time. The present invention is useful in the agricultural field.

10 Shipment Quantity Prediction Device (Embodiment 1)
DESCRIPTION OF SYMBOLS 11 Data acquisition part 12 Expected value calculation part 20 Producer 21 Terminal apparatus 30 Manager 31 Terminal apparatus 40 Network 50 Shipment quantity prediction apparatus (Embodiment 2)
51 Data Acquisition Unit 52 Expected Value Calculation Unit 53 Result Acquisition Unit 54 Result Storage Unit 110 Computer 111 CPU
112 Main Memory 113 Storage Device 114 Input Interface 115 Display Controller 116 Data Reader / Writer 117 Communication Interface 118 Input Device 119 Display Device 120 Recording Medium 121 Bus

Claims (21)

A data acquisition unit configured to acquire an expected shipment quantity set by an agricultural producer, an expected number of days from a reference date to an expected shipment date of the agricultural product, and a deviation day before and after the expected number of days;
An expected value calculation unit for calculating an expected value of the shipping quantity on the expected shipping date and the days before and after the statistical shipping process using the predicted shipping quantity, the expected number of days, and the deviation days;
A shipment quantity predicting device comprising: The expected value calculation unit calculates the expected value using a normal distribution, with an average number of expected days and a value obtained by dividing the value of the deviation days by a setting coefficient as a standard deviation σ.
The shipment quantity prediction apparatus according to claim 1. The expected value calculation unit uses h as the expected shipment quantity, t as the number of days from the reference date on the date on which the expected value is calculated, and using the following formulas (1) and (2): Calculating the expected value;
The shipment quantity prediction apparatus according to claim 2.

The data acquisition unit further acquires an index representing the likelihood of the estimated shipment quantity, the estimated number of days, and the number of deviation days set by the producer,
The expected value calculation unit increases the value of the setting coefficient that divides the value of the deviation days as the probability that the index represents is higher.
The shipment quantity prediction apparatus according to claim 2 or 3. A data acquisition unit for acquiring a reference date, an expected shipment date, and an estimated shipment quantity set by a producer of agricultural products;
A result acquisition unit that acquires the number of days from the reference date to the actual shipping date as the actual number of days;
A result accumulating unit for accumulating the acquired actual number of days;
In the case where the actual number of days is stored in the result storage unit, the average and standard deviation of the actual number of days are calculated based on the stored actual number of days, and the calculated average number of standard days and the standard deviation are calculated. An expected value calculation unit that calculates an expected value of the shipping quantity on the expected shipping date and on the days before and after the estimated shipping date, using a determined normal distribution and the predicted shipping quantity;
A shipment quantity predicting device comprising: The expected value calculation unit is obtained by grouping the actual number of days stored in the result storage unit for each one of the producer and the actual shipping date, or for a combination of both, and by grouping. For each group, calculate the average and standard deviation of the actual number of days, calculate the expected value using a normal distribution determined by the calculated average and standard deviation of the actual number of days, and the estimated shipment quantity,
The shipment quantity prediction apparatus according to claim 5. The expected value calculation unit performs grouping for each producer to calculate the expected value, and further adds the expected values of each of the producers. The expected value of the shipment quantity,
The shipment quantity prediction apparatus according to claim 6. A shipment quantity prediction method executed by a computer,
(A) obtaining an expected shipment quantity, an expected shipment number set from a reference date to an expected shipment date of the agricultural product, and a number of deviation days before and after the expected number of days set by the producer of the agricultural product;
(B) calculating an expected value of the shipping quantity on the predicted shipping date and the days before and after the predicted shipping date by statistical processing using the predicted shipping quantity, the expected number of days, and the number of deviation days;
A shipment quantity prediction method characterized by comprising: In the step (b), the expected value is calculated using a normal distribution in which the expected number of days is an average μ, and the value obtained by dividing the deviation day value by a setting coefficient is a standard deviation σ. ,
The shipment quantity prediction method according to claim 8. In the step (b), the expected shipment quantity is h, the number of days from the reference date on the date for which the expected value is calculated is t, and the following formula (1) and formula (2) are used. Calculating the expected value;
The shipment quantity prediction method according to claim 9.

In the step (a), an index that represents the likelihood of the estimated shipment quantity, the estimated number of days, and the number of deviation days set by the producer is further acquired;
In the step (b), the higher the probability represented by the index, the greater the value of the setting coefficient that divides the value of the deviation days.
The shipment quantity prediction method according to claim 9 or 10. A shipment quantity prediction method executed by a computer,
(A) obtaining a reference date, an expected shipment date, and an estimated shipment quantity set by the producer of the agricultural product;
(B) obtaining the number of days from the reference date to the actual shipping date as the actual number of days;
(C) accumulating the actual number of days; and
(D) When the actual number of days is accumulated in the step (c), the average and standard deviation of the actual days are calculated based on the accumulated actual days, and the calculated actual days Using the normal distribution determined by the average and standard deviation, and the expected shipment quantity, calculating the expected value of the shipment quantity on the expected shipment date and the days before and after,
A shipment quantity prediction method characterized by comprising: In the step (d), the accumulated number of actual days is grouped for each one of the producer and the actual shipping date, or for a combination of both, and for each group obtained by grouping, Calculating the average and standard deviation of the actual number of days, using the normal distribution determined by the calculated average and standard deviation of the actual number of days, and calculating the expected value, using the expected shipment quantity,
The shipment quantity prediction method according to claim 12. In the step (d), grouping is performed for each producer to calculate the expected value, and further, the expected values of the producers are added together, and the value obtained by the addition is calculated for the entire production area. The expected value of the total shipment quantity,
The shipment quantity prediction method according to claim 13. On the computer,
(A) obtaining an expected shipment quantity, an expected shipment number set from a reference date to an expected shipment date of the agricultural product, and a number of deviation days before and after the expected number of days set by the producer of the agricultural product;
(B) calculating an expected value of the shipping quantity on the predicted shipping date and the days before and after the predicted shipping date by statistical processing using the predicted shipping quantity, the expected number of days, and the number of deviation days;
A program that executes In the step (b), the expected value is calculated using a normal distribution in which the expected number of days is an average μ, and the value obtained by dividing the deviation day value by a setting coefficient is a standard deviation σ. ,
The program according to claim 15. In the step (b), the expected shipment quantity is h, the number of days from the reference date on the date for which the expected value is calculated is t, and the following formula (1) and formula (2) are used. Calculating the expected value;
The program according to claim 16.

In the step (a), an index that represents the likelihood of the estimated shipment quantity, the estimated number of days, and the number of deviation days set by the producer is further acquired;
In the step (b), the higher the probability represented by the index, the greater the value of the setting coefficient that divides the value of the deviation days.
The program according to claim 16 or 17. On the computer,
(A) obtaining a reference date, an expected shipment date, and an estimated shipment quantity set by the producer of the agricultural product;
(B) obtaining the number of days from the reference date to the actual shipping date as the actual number of days;
(C) accumulating the actual number of days; and
(D) When the actual number of days is accumulated in the step (c), the average and standard deviation of the actual days are calculated based on the accumulated actual days, and the calculated actual days Using the normal distribution determined by the average and standard deviation, and the expected shipment quantity, calculating the expected value of the shipment quantity on the expected shipment date and the days before and after,
A program that executes In the step (d), the accumulated number of actual days is grouped for each one of the producer and the actual shipping date, or for a combination of both, and for each group obtained by grouping, Calculating the average and standard deviation of the actual number of days, using the normal distribution determined by the calculated average and standard deviation of the actual number of days, and calculating the expected value, using the expected shipment quantity,
The program according to claim 19. In the step (d), grouping is performed for each producer to calculate the expected value, and further, the expected values of the producers are added together, and the value obtained by the addition is calculated for the entire production area. The expected value of the total shipment quantity,
The program according to claim 20.

Images