JP2022110809A - Landing amount prediction program - Google Patents

Abstract

To highly accurately and automatically perform searches of fishing places and landing timings for increasing fish landing amounts even without special skills or experiences, when performing fishing.SOLUTION: A landing amount prediction program for predicting fish landing amounts in fishing places allows a computer to perform: an information acquisition step for acquiring sea information based on physical data which are actually measured or calculated regarding a sea area where another fish is landed; and a prediction step. The prediction step refers to three or more levels of association degrees between reference sea information based on the physical data which are actually measured or calculated regarding the sea area where fish has been landed in the past and a landing amount of fish landing displayed on a two-dimensional map of the sea area, prioritizes a higher association degree on the basis of the reference sea information in accordance with the sea information acquired by the information acquisition step, and predicts, on the two-dimensional map, a landing amount in the sea area where the another fish is landed.SELECTED DRAWING: Figure 4

Description

The present invention relates to a landing prediction program for predicting the landing of fish in offshore or coastal fishing grounds.

2. Description of the Related Art Conventionally, fishing grounds have been searched for the purpose of increasing the amount of fish landed in deep-sea fishing and inshore fishing. This fishing ground search relied on the expert know-how and intuition of fishermen. However, many of these skilled fishermen have retired in recent years, and there is a shortage of successors to the fishing industry. There was a problem that it was not progressing.

Similarly, in coastal fisheries, when conducting seine and set-net fisheries, there is a problem that the know-how for estimating the amount of landing and determining the optimal timing of landing based on that estimate has not been passed on to younger generations. there was a point

For this reason, it is being considered to make artificial intelligence learn the fishing ground search know-how of such skilled fishermen and use it to assist in searching for new fishing grounds and the timing of landing fish in the future. At present, no artificial intelligence itself has been proposed.

Therefore, the present invention has been devised in view of the above-mentioned problems, and the purpose thereof is to provide a fishing ground for increasing the amount of fish landings in deep sea fishing, inshore fishing, and coastal fishing. To propose a landing amount forecasting program capable of automatically and highly accurately searching for the timing of landing and search without special skill or experience.

In order to solve the above-described problems, a landing amount prediction program according to the present invention is a landing amount prediction program for predicting the amount of fish landing in an offshore fishing ground. reference sea information based on physical data actually measured or calculated for past sea areas, and the amount of landed fish displayed on a two-dimensional map of the sea area. By referring to the degree of correlation of the level or higher, based on the reference sea information corresponding to the sea information acquired in the information acquisition step, the one with the higher degree of correlation is prioritized, and the new fish are landed in the sea area. and a prediction step of predicting the quantity on the two-dimensional map.

To automatically and highly accurately search for fishing grounds for increasing the amount of landed fish and for the timing of landed fish in deep-sea fishery and inshore fishery without any special skill or experience.

1 is a block diagram showing the overall configuration of a system to which the present invention is applied; FIG. It is a figure which shows the specific structural example of a search apparatus. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention.

First Embodiment Hereinafter, a catch prediction program to which the present invention is applied will be described in detail with reference to the drawings.

FIG. 1 is a block diagram showing the overall configuration of a landing prediction system 1 in which a landing prediction program to which the present invention is applied is implemented. The landing amount prediction system 1 includes an information acquisition unit 9 , a search device 2 connected to the information acquisition unit 9 , and a database 3 connected to the search device 2 .

The information acquisition unit 9 is a device for a person using this system to input various commands and information. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an imaging device capable of capturing an image, such as a camera. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper document. Further, the information acquisition unit 9 may be integrated with the discriminating device 2 to be described later. The information acquisition unit 9 outputs the detected information to the discrimination device 2 . Further, the information acquisition unit 9 may be configured by means for specifying position information by scanning map information. Further, the information acquisition unit 9 may be configured with an illuminance sensor for measuring a temperature sensor, a humidity sensor, and a wind direction sensor. The information acquisition unit 9 may also be configured with a communication interface that acquires weather data from the Meteorological Agency or a private weather forecast company. The information acquisition unit 9 may be composed of a body sensor worn on the body to detect body data, and the body sensor detects, for example, body temperature, heart rate, blood pressure, number of steps, walking speed, and acceleration. It may be configured with a sensor for Also, the body sensor may acquire biological data not only of humans but also of animals. The information acquisition unit 9 may be configured as a device that acquires information such as drawings by scanning or reading from a database. The information acquisition unit 9 may be configured by an odor sensor that detects odors and scents in addition to these.

The database 3 accumulates various information necessary for predicting the amount of landing. That is, in the database 3, any one or more of reference sea information, reference time information, reference fish school position information, reference image information, reference market information, reference external environment information, etc., and search solutions are stored. They are linked to each other and stored.

The searching device 2 is composed of an electronic device such as a personal computer (PC), for example, but in addition to the PC, it is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc. It may be one that is made into. A user can obtain a search solution by this search device 2 .

FIG. 2 shows a specific configuration example of the search device 2. As shown in FIG. This searching device 2 performs wired or wireless communication with a control unit 24 for controlling the entire searching device 2 and an operation unit 25 for inputting various control commands via operation buttons, keyboards, etc. A communication unit 26 for searching, an estimating unit 27 for making various judgments, and a storage unit 28, represented by a hard disk, for storing a program for performing a search to be executed are connected to the internal bus 21, respectively. . Further, the internal bus 21 is connected with a display unit 23 as a monitor for actually displaying information.

The controller 24 is a so-called central control unit for controlling each component implemented in the search device 2 by transmitting control signals via the internal bus 21 . In addition, the control unit 24 transmits commands for various controls through the internal bus 21 according to operations through the operation unit 25 .

The operation unit 25 is embodied by a keyboard or a touch panel, and a user inputs an execution command for executing a program. The operation unit 25 notifies the control unit 24 when the execution command is input by the user. Upon receiving this notification, the control unit 24 cooperates with each component including the estimation unit 27 to execute desired processing operations. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The estimation unit 27 estimates a search solution. The estimation unit 27 reads various information stored in the storage unit 28 and various information stored in the database 3 as necessary information in executing the estimation operation. This estimation unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

The display unit 23 is composed of a graphic controller that creates a display image based on control by the control unit 24 . The display unit 23 is implemented by, for example, a liquid crystal display (LCD).

When the storage unit 28 is configured with a hard disk, predetermined information is written to each address based on the control by the control unit 24, and this information is read as necessary. The storage unit 28 also stores a program for executing the present invention. This program is read and executed by the control unit 24 .

The operation of the landing amount prediction system 1 configured as described above will be described.

The landing prediction system 1 uses reference sea information as input data, as shown in FIG. 3, for example. Reference sea information is any information that is based on actual measured or calculated physical data for sea areas where fish have been landed in the past. The sea area where the fish was landed here is not limited to a certain point such as within a radius of 1 to 2 km around the position where the fish was actually landed in the past, but within a radius of 100 to 200 km around the position. It may be within a radius of 1000 km. Furthermore, it may be within 200 nautical miles of the national land of Japan or each country, and may exceed 200 nautical miles without being limited to this. It may be expanded to areas such as the entire Seto Inland Sea, the Sea of Japan, and the like, and may also be expanded to the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the like.

The physical data may be any data that indicates the state of the sea, such as seawater temperature, salinity, current velocity and direction, tide, sea surface altitude, occurrence of red tide, amount of carbon dioxide, and the like. or one or more. The physical data may also include oxygen concentration, wave conditions and heights, and wave conditions.

Such reference sea information may be physical data surveyed for the entire sea area, or may be surveyed for a part of the sea area. Further, the surveyed physical data may be averaged over the entire sea area, or the results of surveying physical data for a plurality of points within the sea area may be shown.

As input data, such reference sea information is arranged. Reference sea information as such input data is coupled to the output. In this output, the landing amount is displayed as the output solution.

The amount of landing referred to here is the amount of landing indicated on the two-dimensional map data indicating the sea area. As shown in FIG. 4, this landed amount indicates the time-series landed amount shown on a two-dimensional map. A map of the sea area is shown on a two-dimensional plane consisting of the x and y axes in the figure. And the z-axis indicates the time axis. Landing amounts (catch amounts) are shown in chronological order of t1, t2, t3, and t4. This landing amount is indicated by the size of the circle in FIG. A larger circle may indicate a larger amount of catch, and a smaller circle may indicate a smaller amount of catch. Also, the landing amount may be indicated for each fish species. In the example of FIG. 4, fish species include saury, yellowtail, sea bream, and the like. The landing amount of each fish species is shown in chronological order on the two-dimensional sea area map data.

Incidentally, it is not necessary to classify the landing amount by fish species, and it may be represented by the total value of the landing amount of each fish species. In addition, the landing amount is not limited to the case of including a time-series transition as shown in the z-axis direction, and may be constituted by the landing amount at a certain point in time. In such a case, the amount of landed fish at any one point in time from t1 to t4 in FIG. 4 may be indicated. Alternatively, it may be indicated by the total value of the landing amount at each time point t1 to t4.

In other words, through the reference sea information and the data set of the landing amount, the actual landing amount for various data generated in the reference sea information can be known. In other words, the reference sea information data and the landing amount constitute a data set. Therefore, by collecting reference sea information and a data set of the amount of landing, it is possible to know what the amount of landing was in what kind of sea state in the past.

In addition, when creating a dataset of learning data, the time when fishing was actually performed in the past, the location where fishing was performed (position on the two-dimensional map data), the amount of landing when fishing was performed, and the amount of landing It can be obtained by inputting data such as fish species that have been collected. This data entry may be entered manually, or, for example, the location and time of fishing, as well as the amount of landing and fish species, may be read from a previous logbook record, and the read data may be entered manually or You can enter it automatically. Also, if the trajectory of the positional information on the previous voyage for fishing is saved in chronological order as electronic data, the electronic data may be directly captured. At this time, if the fishing location information is specified on the electronic data, it may be acquired from there.

Further, in creating the data set of this learning data and in obtaining the physical data described above, the seawater temperature may be acquired from, for example, an artificial satellite, instead of using a thermometer. Data may also be obtained by attaching a sensor capable of measuring water temperature and salinity concentration to a buoy or the like. The salinity concentration and the amount of carbon dioxide may be measured by a sensor attached to a fishing boat or directly manually. The velocity and direction of ocean currents may be measured using an ultrasonic Doppler multi-layer anemometer, etc., but the present invention is not limited to this. For example, ocean current simulation data published by the Ministry of Land, Infrastructure, Transport and Tourism may be used. In addition, if past ocean current velocity and direction data are obtained by the Japan Coast Guard, private organizations, etc., they may be read as learning data. Similarly, the velocity and direction of ocean currents, tides, sea surface altitudes, and the occurrence of red tides may be obtained from data held by public or private organizations. At this time, the map data consisting of the two-dimensional coordinates of the landing amount shown in FIG. 4 and the physical data described above are associated with each other and learned.

Even when acquiring such reference sea information, it may include time-series transitions from t1 to t4 as shown in the z-axis direction, but is not limited to this. It may consist of physical data. In such a case, the physical data at any one point in time from t1 to t4 in FIG. 4 may be shown. Alternatively, it may be represented by an average value of physical data at each time point t1 to t4.

In addition, this physical data may be measured at each position of the two-dimensional map data in the same manner as the amount of landing, but it is not limited to this, and the physical data is averaged over the entire sea area. Alternatively, the physical data for the entire sea area may be representative of one or more physical data measured in the sea area.

In the example of FIG. 3, it is assumed that the input data are reference sea information P01 to P03, for example. Reference sea information as such input data is coupled to the output. In this output, the landing amount is displayed as the output solution.

The reference sea information is associated with the landing amount as the output solution through three or more degrees of association. The sea information for reference is arranged on the left side through this degree of association, and the landing amount is arranged on the right side through the degree of association. The degree of relevance indicates the degree of relevance to which landing amount the reference sea information arranged on the left side has a high degree of relevance. In other words, this degree of association is an index that indicates the high possibility that each reference sea information is associated with a landing amount, and is an index for selecting the most probable landing amount from the reference sea information. It shows accuracy. In the example of FIG. 3, w13 to w19 are shown as association degrees. These w13 to w19 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of correlation between each combination as an intermediate node and the landing amount as an output. , conversely, the closer to 1 point, the lower the degree of correlation between each combination as an intermediate node and the amount of landing as an output.

The search device 2 acquires three or more degrees of association w13 to w19 shown in FIG. 3 in advance. In other words, the search device 2 accumulates past data as to which of the reference sea information and the landing amount in that case was adopted in determining the actual search solution, and analyzes these data. By doing so, the degree of association shown in FIG. 3 is created.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference sea information P01, analysis is performed from the data of the determination result of the past landing amount. In the case of the reference sea information P01, if there are many cases of the landing amount A, the degree of association leading to this landing amount A is set higher, and if there are many cases of the landing amount C, this landing amount C Set a higher degree of association leading to For example, in the example of the reference sea information P01, the landing amount A and the landing amount C are linked. The degree is set to 2 points. The time-series distribution of the landing amount is shown for each of the landing amounts A to D for each time or every time interval.

Further, the degree of association shown in FIG. 3 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

In such a case, as shown in FIG. 5, reference sea information is input as input data, each landing amount is output as output data, and at least one or more hidden layers are provided between the input node and the output node. , may be machine-learned. Conversely, it may be configured such that the landing amount is input and the reference sea information is output.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-mentioned learned data will be used to predict the landing amount when actually making a new prediction of the landing amount. In such a case, the sea information of the sea area for which the actual new landing amount is to be predicted is acquired. This sea information is composed of the same kind of data as the above-described reference sea information, and the acquisition method is also the same as that of the reference sea information.

Sea information to be newly acquired is input by the information acquisition unit 9 described above. The information acquisition unit 9 may acquire such sea information as electronic data.

Based on the sea information newly acquired in this way, a search is made for the amount of landed fish that has a high possibility of actually being determined with respect to the sea information. In such a case, reference is made to the degree of association shown in FIG. 3 (Table 1), which has been acquired in advance. For example, if the newly acquired sea information is the same as or similar to P02, the landing B is associated with w15 and the landing C is associated with w16. In such a case, the landing B, which has the highest degree of correlation, is selected as the optimum solution. However, it is not essential to select the one with the highest degree of correlation as the optimum solution, and the landing amount C, which has a low degree of correlation but is recognized for its correlation itself, may be selected as the optimum solution. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

Such a landing amount may be obtained with respect to the position in the sea area, or may be divided into a certain number of areas in the sea area and averaged for each area and output. The simplest way is to obtain the amount of landing for the position where the amount of landing was investigated when creating the learning data as shown in FIG. In such a case, since the amount of landing has been previously investigated at the same position, it is possible to obtain a highly accurate search solution by using this as learning data.

In this way, the amount of landed fish to be determined is searched from newly acquired sea information. The landed amount searched for is obtained by fish species or by the total value of a plurality of fish species.

At this time, the search device 2 may propose the optimum fishing ground based on the predicted landing amount. In such a case, the weighting is set in advance so that the position with the larger amount of landing is the most suitable fishing ground, and based on the actually obtained amount of landing, the weighting is referred to and the fishing ground is proposed. good too. Further, when proposing this fishing ground, the current position information of the fishing boat may be acquired, and the fishing ground may be proposed based on the acquired position information. Positional information is acquired by GPS or the like. Weighting may be set in advance so that a position closer to the current position of the fishing boat is the most suitable fishing ground, and a fishing ground may be proposed by referring to the weighting based on the actually acquired position information. At this time, the optimum fishing season may also be proposed by referring to the chronological trend.

Furthermore, in the present invention, it is also possible to acquire desired landing amount information for the landing amount that reflects the needs of consumers. This desired landing amount information is information that indicates how much fish is in demand from consumers, retail stores and wholesale markets that reflect consumer demand. This desired landing amount information is configured as the amount of fish (landing amount) to be provided, aggregated from retail stores and wholesale markets. The desired landing amount information may indicate the amount of each fish type. A fishing ground may be proposed based on such desired landing amount information. In such a case, a fishing ground that is likely to be able to achieve a landing amount that meets the desired landing amount information is proposed in comparison with the landing amount shown on the two-dimensional map obtained through the degree of association described above. If the amount of landing indicated in the desired amount of landing information is small, a fishing ground that matches the small amount of landing is searched and searched from the amount of landing on the two-dimensional map, and overfishing of more than necessary fish is prevented. can do. On the other hand, if the amount of landing indicated by the desired amount of landing information is large, a fishing ground suitable for the large amount of landing is searched and retrieved from the amount of landing on the two-dimensional map and proposed.

At the stage when the desired landing volume information is uploaded, the landing volume of each fishing ground shown on the two-dimensional map obtained through the above-mentioned correlation is weighted, and the landing volume closer to the desired landing volume information is weighted. You may make it heavy. Then, a fishing ground may be selected based on the weighting.

Also, when learning the degree of association, the degree of association with the amount of landings in chronological order may be learned. It is also possible to give priority to those with a higher degree of association, and predict the chronological amount of landed fish on the two-dimensional map for the sea area where the new fish will be landed. In such a case, the chronological change tendency of the landing amount from t1 to t4 in FIG. 4 is learned with the same chronological reference sea information. Then, if the newly acquired sea information has a tendency similar to the reference sea information at time t2, the tendency of t3 and t4 as the subsequent time-series landing amount is output as this time-series change trend. You may do so.

In the example of FIG. 6, it is assumed that the input data are reference sea information P01 to P03 and reference time information P14 to P17. An intermediate node shown in FIG. 6 is obtained by combining the reference sea information as input data with the reference time information. Each intermediate node is also connected to an output. In this output, each landing amount is displayed as an output solution.

In the example of FIG. 6, it is assumed that a combination of reference ocean information and reference time information is formed. This reference timing information is information about the timing of landed fish in the past, and is composed of time points t1 to t4, etc., which are arranged chronologically in the z-axis direction shown in FIG. The time interval between times t1 to t4 may consist of any time units, such as minutes, hours, days, months as well as years. Also, the time intervals do not necessarily have to be equal intervals. In addition, the point in time is not limited to a certain point in time, but may consist of a certain amount of time, and the unit of time may be minutes, hours, days, months, or even years. good too.

If the reference time information P14 is time t1, the reference time information P15 is time t2, the reference time information P16 is time t3, and the reference time information P17 is time t4, then the time and the reference corresponding to that time are Learn the sea information and the amount of landing at each point corresponding to that time as a data set.

In the example of FIG. 6, it is assumed that the input data are reference sea information P01 to P03 and reference time information P14 to P17. An intermediate node shown in FIG. 6 is obtained by combining the reference sea information as input data with the reference time information. Each intermediate node is also connected to an output. In this output, the landing amount is displayed as the output solution.

Each combination (intermediate node) of the reference sea information and the reference time information is associated with the landing amount as the output solution through three or more degrees of association. The sea information for reference and the time information for reference are arranged on the left side through this degree of association, and the amount of landing is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference sea information and the reference time information arranged on the left side are highly associated with each landing amount. In other words, this degree of association is an index that indicates the probability that each reference sea information and reference time information is associated with the amount of landed landing. It indicates the accuracy in selecting each probable landing amount. In addition to sea information, the amount of landing may change depending on the time of year, and decisions can be made based on this.

In the example of FIG. 6, w13 to w22 are shown as association degrees. These w13 to w22 are shown in 10 stages as shown in Table 1. The closer to 10 points, the higher the degree of correlation between each combination as an intermediate node and the output. The closer it is, the lower the degree of correlation between each combination as an intermediate node and the output.

The search device 2 acquires in advance three or more degrees of association w13 to w22 shown in FIG. In other words, the search device 2 accumulates past data as to which of the reference sea information, the reference time information, and the amount of landing in that case was preferable in determining the actual search solution, and stores these data. By analyzing and analyzing, the degree of association shown in FIG. 6 is created.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference sea information P01 and the reference time information P16, the landing amount is analyzed from the past data. If there are many cases of landing amount A, the degree of correlation leading to this landing amount A is set higher. The degree of association leading to the landing amount A is set low. For example, in the example of the intermediate node 61a, the outputs of the landing amount A and the landing amount B are linked. The degree is set to 2 points.

Further, the degree of association shown in FIG. 6 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

In the example of the degree of association shown in FIG. 6, the node 61b is a node that combines the reference weather information P14 with the reference sea information P01. is w16. The node 61c is a node that combines the reference weather information P15 and P17 with the reference sea information P02, and the degree of relevance of the landing amount B is w17 and the relevance degree of the landing amount D is w18.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually performing a search for determining the amount of landing. In such a case, the determination of the landing amount is newly added to the sea information to acquire the time information. This period information corresponds to the reference period information described above, and the acquisition method is also the same.

Based on the sea information and season information newly acquired in this way, the optimal amount of landed fish is searched for. In such a case, reference is made to the degrees of association shown in FIG. 6 (Table 1) that have been acquired in advance. For example, if the newly acquired ocean information is the same as or similar to P02 and the time information is the same or similar to P17, the node 61d is associated via the degree of association. This node 61d is associated with the landing amount C by w19 and the landing amount D by w20. In such a case, the landing amount C with the highest degree of correlation is selected as the optimum solution. However, it is not essential to select the one with the highest degree of correlation as the optimum solution, and the landing amount D, which has a low degree of correlation but is recognized for its correlation itself, may be selected as the optimum solution. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

For example, when the time point t1 is September to October and the reference sea information at the time point t is P01, the landing amount C means that a certain fish species was caught in a very large amount at a certain position in the sea area. Assume that there is At this time, if these data sets are learned, if the newly input time information is September to October and the sea information at that time corresponds to the reference sea information, the landing amount C The fish species and the amount of landing shown in .

Table 2 below shows examples of degrees of association w1 to w12 extending from the input.

Intermediate nodes 61 may be selected based on degrees of association w1 to w12 extending from this input. In other words, the greater the degree of association w1 to w12, the heavier the weight in selecting the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weighting in selecting the intermediate nodes 61 may all be the same.

FIG. 7 shows an example in which three or more levels of correlation are set between combinations of reference sea information and reference fish school position information described above, and landing amounts for the combinations.

The reference fish school position information is information relating to the position on the two-dimensional map of the fish school detected in the sea area where the fish were landed in the past. The position of a school of fish that constitutes this reference fish school position information may be obtained by a well-known fish finder, or may be obtained from an aerial image or satellite image taken by an artificial satellite such as an unmanned aerial vehicle such as a drone, an aircraft, a helicopter, or the like. You may make it detect based on. When discriminating through images, if the surface of the water becomes white and turbid due to fish splashing on the surface, the white turbidity may be detected. If it appears, it may be detected. When discriminating a school of fish from such an image, a feature amount may be extracted from the image and machine learning or deep learning technology may be used for discrimination. Such reference fish school position information is similarly shown on the two-dimensional map. If the reference sea information and the landing amount are indicated in chronological order such as t1 to t4, the reference fish school position information is also measured in the same chronological order in order to match this, You may make it learn.

In the example of FIG. 7, the input data are, for example, reference sea information P01-P03 and reference fish school position information P18-21. An intermediate node shown in FIG. 7 is a combination of reference ocean information and reference fish school position information as such input data. Each intermediate node is also connected to an output. In this output, the landing amount is displayed as the output solution.

Each combination (intermediate node) of the reference sea information and the reference fish school position information is associated with the landing amount as this output solution through three or more levels of association. The reference sea information and the reference fish school position information are arranged on the left side through this degree of association, and the landing amount is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference sea information and the reference fish school position information arranged on the left side are closely related to the landing amount. In other words, this degree of association is an index that indicates the high possibility that each piece of reference sea information and reference fish school position information is associated with the amount of landing. It indicates the accuracy in selecting the most probable landing amount. In addition to the sea information, the position of the school of fish greatly affects the amount of landed fish, so the fish school position information for reference is also learned.

The search device 2 acquires in advance three or more degrees of association w13 to w22 shown in FIG. In other words, the search device 2 accumulates past data on which of the reference sea information and the reference fish school position information and the landing amount in that case was preferable in determining the actual search solution. By analyzing these, the degree of association shown in FIG. 7 is created.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference sea information P01 and the reference fish school position information P20, the landing amount is analyzed from the past data. Also, the degree of association shown in FIG. 7 may be composed of nodes of a neural network in artificial intelligence.

In the example of the degree of association shown in FIG. 7, the node 61b is a node that combines the reference sea information P01 with the reference fish school position information P18, the degree of association of the landing amount C is w15, and the association of the landing amount E is w15. degree is w16. The node 61c is a node of a combination of the reference fish school position information P19 and P21 with respect to the reference sea information P02, and the degree of relevance of the landing B is w17 and the relevance of the landing D is w18.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually giving advice. In such a case, fish school position information is acquired in addition to the sea information described above. The fish school position information corresponds to the reference fish school position information.

Based on the sea information and fish school position information newly acquired in this way, the amount of landed fish is searched for. In such a case, reference is made to the degrees of association shown in FIG. 7 (Table 1) that have been acquired in advance. For example, when the newly acquired sea information is the same as or similar to P02 and the fish school position information is P21, the node 61d is associated via the degree of association, and this The node 61d is associated with the landing amount C with w19 and with the landing amount D with the association degree w20. In such a case, the landing amount C with the highest degree of correlation is selected as the optimum solution. However, it is not essential to select the one with the highest degree of correlation as the optimum solution, and the landing amount D, which has a low degree of correlation but is recognized for its correlation itself, may be selected as the optimum solution. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association. As described above, by learning about a person requiring attention as reference fish school position information, it is possible to identify a person requiring attention from the face image of the extracted fish school position information by referring to the learning data. , it is possible to output the optimal landing amount corresponding to this as a search solution.

In the example of FIG. 7, an example of acquiring the position of a school of fish in the reference fish school position information and the fish school position information through an image has been described. This reference fish school position information and fish school position information are used to determine the position of the school of fish from the image, but are not limited to this, and the image can be used as it is as learning data without determining the position of the school of fish. good too. In such a case, as shown in FIG. 8, the degree of association between the landing amount and the combination of the reference sea information and the reference image information is learned. The reference image information is an image of the surface of the sea or underwater captured by a camera, as described above. Then, when image information is newly acquired, a solution search is performed with reference to the degree of association based on reference image information corresponding to this image information.

FIG. 9 shows an example in which three or more levels of correlation are set between combinations of reference sea information and reference weather information, and the landing amount for the combinations.

Reference weather information is all information related to the weather of the sea area where the fish were landed in the past, including temperature, humidity, precipitation, wind direction, wind speed, sunshine hours, as well as pressure distribution and cloud conditions. These reference weather information may be shown on the two-dimensional map described above. Such reference weather information may be learned from data held by the Japan Meteorological Agency or private weather forecasting companies. If the reference sea information and the amount of landed fish are shown in chronological order, such as t1 to t4, then the reference weather information is also measured in the same chronological order and learned. You can let it run.

In the example of FIG. 9, the input data are, for example, reference sea information P01-P03 and reference weather information P18-21. An intermediate node shown in FIG. 9 is a combination of reference sea information and reference weather information as such input data. Each intermediate node is also connected to an output. In this output, the landing amount is displayed as the output solution.

Each combination (intermediate node) of the reference sea information and the reference weather information is associated with the landing amount as this output solution through three or more levels of association. The sea information for reference and the weather information for reference are arranged on the left side through this degree of association, and the landing amount is arranged on the right side through the degree of association. The degree of association indicates the degree to which the reference sea information and the reference weather information arranged on the left side are closely related to the landing amount. In other words, this degree of association is an index that indicates the probability that each reference sea information and reference weather information is associated with the amount of landed fish. It shows the accuracy in selecting each likely landing amount. In addition to sea information, reference weather information is also learned because the amount of landed fish greatly depends on the position of the school of fish.

The search device 2 acquires in advance the degrees of association w13 to w22 of three or more stages shown in FIG. In other words, the search device 2 accumulates past data as to which of the reference sea information, the reference weather information, and the amount of landing was preferable in that case, in order to determine the actual search solution. is analyzed to create the degrees of association shown in FIG.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference sea information P01 and the reference weather information P20, the landing amount is analyzed from the past data. Further, the degree of association shown in FIG. 9 may be composed of nodes of a neural network in artificial intelligence.

In the example of the degree of association shown in FIG. 9, the node 61b is a node that combines the reference weather information P18 with the reference sea information P01. is w16. The node 61c is a node of a combination of the reference weather information P19 and P21 with respect to the reference ocean information P02.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually giving advice. In such a case, weather information is obtained in addition to the sea information described above. The weather information corresponds to the reference weather information.

Based on the sea information and weather information newly acquired in this way, the amount of landed fish is searched for. In such a case, reference is made to the degrees of association shown in FIG. 9 (Table 1) that have been acquired in advance. For example, when the newly acquired sea information is the same as or similar to P02 and the weather information is P21, the node 61d is associated via the degree of association, and this node 61d is associated with the landing amount C by w19 and the landing amount D by w20. In such a case, the landing amount C with the highest degree of correlation is selected as the optimum solution. However, it is not essential to select the one with the highest degree of correlation as the optimum solution, and the landing amount D, which has a low degree of correlation but is recognized for its correlation itself, may be selected as the optimum solution. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association. As described above, by learning about a person requiring caution as reference weather information, it is possible to identify a person requiring caution from the face image of the extracted weather information by referring to the learning data. It is possible to output the optimum landing amount according to the search solution as a search solution.

FIG. 10 shows a combination of reference sea information corresponding to reference information U and reference market information corresponding to reference information V, and three or more degrees of association with sales data for the combination. example.

Reference market information is various information about market conditions. The market conditions referred to here may target any range, such as a single company, the entire industry including the company, the entire Japan, or the entire world. Examples of this reference market information include interest rates, exchange rates, stock prices of each brand, crude oil, futures, precious metals, bitcoins, and other price movements. This reference market condition information may be displayed as a time-series chart, a line graph, or the like for these targets. Further, information such as Bollinger band, MACD, moving average line, etc. may be attached. In addition, this market information may include the fundamental indicators of the company of each brand. Return on equity) and other indicators may be included. Information such as charts, Bollinger bands, MACD, moving averages, etc. showing price movements between currencies may also be attached to exchange rates. The reference market condition information may categorize the market potential itself. The reference market information may be information classified by type. For example, it may be classified by whether or not the stock price growth rate is 0% or more per year. In addition, they may be categorized according to patterns (for example, patterns such as whether the growth rate of the stock price increases rapidly or gradually).

In the example of FIG. 10, the output obtained for the reference information U may be used as input data as it is, and may be associated with the output via an intermediate node 61 in combination with the reference information V. FIG. For example, for reference information U, after outputting the amount of landed fish as an output solution, using this as an input as it is, using the degree of relevance in combination with other reference information V, sales data from fishing is used as an output solution. may be searched.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually giving advice. In such a case, current market information is obtained in addition to the sea information described above. The market information corresponds to the reference market information.

Based on the sea information newly acquired in this way, the landing amount is searched through the reference information U. A specific method is as described above. After outputting the amount of landed fish in this way, the sales data associated with the amount of landed fish and the reference information V based on the market information may be output. As described above, the landing amount may be composed of the landing amount for each fish species. Once the unit price is determined for each fish species, the sales for each fish species can be derived by multiplying the unit price by the amount of landing. The total sales can be obtained by calculating the total sales for each derived fish species. Since the unit price is affected by market conditions in determining the total sales, this is used as an explanatory variable and determined as an output solution.

Instead of reference market information, reference external environment information may be learned. Reference external environment information is various information related to external environment information. External environment information here includes economic data (GDP, employment statistics, industrial production index, capital investment, labor force survey, etc.), household data (household consumption survey, household data, average working hours per week, savings amount, etc.). statistical data, annual income statistical data, etc.), real estate data (office vacancy rate, unit price per tsubo, rent market, land price, vacant house data, etc.), natural environment data (disaster data, temperature data, precipitation data, wind direction data, humidity data etc.). The external environment information includes all external information of the automated teller machine, in addition to the information reflecting part or all of these data. The external environment information for reference may categorize the external environment itself. For example, it may be classified by separating data in employment statistics. In addition, they may be categorized according to patterns (for example, patterns such as whether the growth rate of GDP increases rapidly or gradually).

In such a case, a combination of reference sea information corresponding to reference information U and reference external environment information corresponding to reference information V, and the sales data for the combination are set at three or more degrees of association. example is shown.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually giving advice. In such a case, the current external environment information is obtained in addition to the sea information described above. The external environment information corresponds to the reference external environment information.

Based on the sea information newly acquired in this way, the landing amount is searched through the reference information U. A specific method is as described above. After outputting the amount of landed fish in this way, the sales data linked to the amount of landed fish may be output based on the reference information V based on the amount of landed fish and the external environment information.

Also, the present invention is not limited to the above-described embodiments, and for example, as shown in FIG. may In such a case, a solution search is performed based on three or more levels of association with the landing amount according to the newly acquired information. The basic reference information is, for example, reference sea information, etc., but is not limited to this, and any reference information (reference time information, reference fish school position information, reference image information, reference weather information, market information for reference, external environment information for reference, etc.) are also applicable.

In these cases, similarly, when information corresponding to reference information used as learning data is input, solution search is performed based on the above-described method.

The search solution obtained through the degree of association may be further modified or weighted based on other reference information.

The other reference information referred to here corresponds to any reference information other than the basic reference information when any of the reference information described above is used as the basic reference information.

For example, as one of the other reference information, in certain reference fish school position information P14, it is assumed that there were many circumstances in which B was determined as the landing amount in the past. When tone information corresponding to such reference tone information P14 is newly acquired, processing is performed to increase the weighting of the search solution B as the amount of landing, in other words, the search solution B as the amount of landing is obtained. It is set in advance so as to perform processing to

For example, the other reference information G is an analysis result that suggests a search solution C as a larger landing amount, and the reference information F is an analysis result that suggests a search solution D as a larger landing amount. Assume that there is After the setting with the reference information in this way, if the actually obtained information is the same as or similar to the reference information G, processing is performed to increase the weight of the search solution C as the landing amount. On the other hand, when the actually acquired information is the same as or similar to the reference information F, processing is performed to increase the weight of the search solution D as the landing amount. In other words, the degree of association itself leading to the amount of landed fish may be controlled based on the reference information FH. Alternatively, after the landing amount is determined only by the degree of association described above, the obtained search solution may be corrected based on the reference information F to H. In the latter case, how to correct the landing amount as the search solution based on the reference information F to H is to reflect what is designed on the system side each time.

The reference information is not limited to any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the discrimination pattern as a search solution obtained through the degree of association may be corrected to be higher for a case that leads to the landing amount suggested by the reference information.

Similarly, as shown in FIG. 12, even in the case of forming the degree of association with the landing amount for a combination of reference information that is the keynote and other reference information, the reference information that is the keynote is Any reference information described above (reference sea information, reference time information, reference fish school position information, reference image information, reference weather information, reference market information, reference external environment information, etc.) can be applied. . Other reference information includes any reference information other than the underlying reference information.

At this time, if the basic reference information is the reference time information, the other reference information includes any other reference information.

In such a case, it is possible to estimate the landing amount by searching for solutions in the same way. At this time, as shown in FIG. 11 described above, for the search solution obtained through the degree of association, further other reference information (reference information F, G, H, etc.) is used to correct the landing amount. can be Further, as shown in FIG. 10, the landing amount may be predicted through other reference information (reference information V) for the search solution obtained through the degree of association.

Note that the forms shown in FIGS. 10 and 12 may be configured in combination with any two or more of the other reference information described above. In addition to this reference information, the degree of relevance may be formed by adding other factors to this combination.

Further, as shown in FIG. 13, the degree of association may be formed between only the reference information that is the keynote and the landing amount. This basic reference information can be any reference information (reference sea information, reference time information, reference fish school position information, reference image information, reference weather information, reference market information, reference external environment information, etc.). etc. are also applicable.

FIG. 14 shows an example in which the degree of association is formed between the reference time information and the amount of landing, and FIG. 15 shows an example in which the degree of association is formed between the reference position information of the school of fish and the amount of landing. , and FIG. 16 is an example in which the degree of association is formed between the reference weather information and the landing amount. The method of deriving the amount of landing is omitted below by citing the explanation of FIGS. 3 and 5 mentioned above. Even when these reference time information, reference fish school position information, and reference weather information are used as basic reference information, as shown in FIGS. may be asked for.

In the above-mentioned degree of relevance, the degree of relevance is expressed by a 10-level evaluation, but it is not limited to this, and it may be expressed by a degree of relevance of 3 or more stages. For example, 100 steps or 1000 steps may be used. On the other hand, this degree of association does not include those expressed in two stages, that is, whether or not they are associated with each other, either 1 or 0.

According to the present invention configured as described above, anyone can easily search for a solution without special skills or experience. Further, according to the present invention, it is possible to judge the search solution with a higher degree of accuracy than a human being does. Furthermore, by configuring the degree of association described above with artificial intelligence (neural network, etc.) and making it learn, it is possible to further improve the discrimination accuracy.

Since the above-described input data and output data may not be exactly the same in many cases during the learning process, information obtained by classifying these input data and output data according to type may be used. That is, the information P01, P02, . . . P15, 16, . A data set may be created between the data and the output data for learning.

Moreover, according to the present invention, it is characterized in that the optimum solution search is performed through the degree of association set to three or more stages. The degree of association can be described by a numerical value of, for example, 0 to 100% in addition to the 10 stages described above, but is not limited to this, and can be described by a numerical value of 3 or more stages. may be configured.

By discerning the search solution with higher credibility and less misunderstanding based on the degree of association represented by numerical values of three or more levels, it is possible to consider multiple candidates for the possibility of the search solution. , it is also possible to search and display in descending order of the degree of association.

In addition to this, according to the present invention, it is possible to make a judgment without overlooking even a very low output discrimination result such as a correlation degree of 1%. Remind the user that even discrimination results with an extremely low degree of association are connected as slight signs, and that once in dozens or hundreds of times, the discrimination results may be useful. be able to.

Furthermore, according to the present invention, there is an advantage that a search policy can be determined by setting thresholds by performing a search based on three or more degrees of association. If the threshold value is lowered, even if the degree of association is 1%, it can be picked up without omission. be. On the other hand, if the threshold is set high, there is a high possibility that the optimal search solution can be detected with a high probability. Sometimes the solution is overlooked. It is possible to decide which one to place emphasis on based on the way of thinking of the user side and the system side, and it is possible to increase the degree of freedom in selecting such points to place emphasis on.

Furthermore, in the present invention, the degree of association described above may be updated. This update may reflect information provided via a public communication network such as the Internet, for example.

In other words, this update corresponds to learning in terms of artificial intelligence. Since new data is acquired and reflected in the learned data, it can be said that it is a learning act.

In addition to updating the degree of association based on information that can be obtained from the public communication network, the system side or the user side based on the contents of research data, papers, academic conference presentations, newspaper articles, books, etc. by experts It may be updated manually or automatically. Artificial intelligence may be used in these update processes.

Also, the process of initially building a trained model and the above-described updating may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of loading and learning datasets of input and output data, learning is performed by loading information corresponding to the input data, from which the degree of association related to the output data is self-formed. You can let it run.

Second Embodiment The present invention is not limited to the embodiments described above. For example, as shown in FIG. You may do so. In such a case, a solution search is performed based on three or more levels of association with the landing amount according to the newly acquired information. The basic reference information can be any reference information (reference sea information, reference time information, reference fish school position information, reference image information, reference weather information, reference market information, reference external environment information, etc.) ) is also applicable.

The quality of fish as used herein is a concept that indicates all qualities of fish in terms of appearance and taste. The quality of fish may be expressed in terms of freshness, or may be evaluated in terms of luster and taste. The quality of this fish may be expressed by a ranking of 5 or 10 levels set by the system side or the user side. Alternatively, it may simply be described as super delicious, delicious, so-so, or ordinary.

The quality of these fish may be determined based on previously learned feature values. At this time, artificial intelligence is used to learn the image data of the fish and the quality of the fish, and when actually acquiring the reference image information, the quality of the fish is compared with these learned image data You may make it discriminate|determine.

The quality of the fish may be determined based on previous experience by the evaluator, or may be determined by actually tasting the fish to determine its taste. In such a case, multiple inspectors who sample the quality of the fish evaluate the taste on multiple levels for each item such as texture, aroma, texture, bitterness, mellowness, etc., and statistically analyze them. It may be a quality evaluation value. Also, the quality of fish may be determined through a taste sensor capable of detecting taste, or may be determined through various instrumental analyses.

Also, the freshness of fish may be evaluated as the quality of the fish itself. Similarly, the freshness of fish may be evaluated by a plurality of inspectors with respect to the taste of each food item in a plurality of stages, and the results may be statistically analyzed to obtain a quality evaluation value.

The quality of these fish is stored in the database 3 after being associated with the landing position and time. After each quality has been evaluated, the landed fish can be stored in relation to the landed position and time. At this time, learning is performed through a data set including the reference information described above. As a result, it is possible to form association degrees as shown in FIG. 18 in advance.

In these cases, similarly, when information corresponding to reference information used as learning data is input, solution search is performed based on the above-described method.

The search solution obtained through the degree of association may be further modified or weighted based on other reference information.

The other reference information referred to here corresponds to any reference information other than the basic reference information when any of the reference information described above is used as the basic reference information.

For example, it is assumed that in the reference fish school position information P14, which is one of the other reference information, B has often been determined as the fish quality in the past. When tone information corresponding to such reference tone information P14 is newly acquired, the search solution B as the quality of the fish is weighted, in other words, the search solution B as the quality of the fish is obtained. It is set in advance so as to perform a process to

For example, the other reference information G is an analysis result that suggests the search solution C as the quality of the fish, and the reference information F is the analysis result that suggests the search solution D as the quality of the fish. Assume that there is After the setting with the reference information in this way, when the actually obtained information is the same as or similar to the reference information G, processing is performed to increase the weight of the search solution C as the quality of the fish. On the other hand, when the actually acquired information is the same as or similar to the reference information F, processing is performed to increase the weight of the search solution D as the quality of the fish. In other words, the degree of association itself leading to the quality of the fish may be controlled based on the reference information FH. Alternatively, after the quality of the fish is determined only by the degree of association described above, the obtained search solution may be corrected based on the reference information FH. In the latter case, how and with what weight the quality of the fish as the search solution is modified based on the reference information F to H is to reflect what is designed on the system side each time.

The reference information is not limited to any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the discriminant pattern as a search solution obtained through the degree of association may be corrected to a higher value for a case that leads to the quality of the fish suggested by the reference information.

Similarly, as shown in FIG. 19, even in the case of forming the degree of association with the quality of fish for a combination of reference information that is the keynote and other reference information, the reference information that is the keynote is Any reference information described above (reference sea information, reference time information, reference fish school position information, reference image information, reference weather information, reference market information, reference external environment information, etc.) can be applied. . Other reference information includes any reference information other than the underlying reference information.

At this time, if the basic reference information is the reference time information, the other reference information includes any other reference information.

In such a case as well, the quality of the fish can be estimated by searching for solutions in the same way. At this time, as shown in FIG. 19 described above, for the search solution obtained through the degree of association, further other reference information (reference information F, G, H, etc.) is used to correct the quality of the fish. can be Further, as shown in FIG. 10, the fish quality may be predicted through other reference information (reference information V) for the search solution obtained through the degree of association.

Note that the forms shown in FIGS. 10 and 19 may be configured by combining two or more of the other reference information described above. In addition to this reference information, the degree of relevance may be formed by adding other factors to this combination.

Further, as shown in FIG. 20, the degree of association may be formed between only the reference information that is the keynote and the quality of the fish. This basic reference information can be any reference information (reference sea information, reference time information, reference fish school position information, reference image information, reference weather information, reference market information, reference external environment information, etc.). etc.) are also applicable.

Similarly, in the second embodiment, the optimum fishing ground may be proposed based on the predicted fish quality. In such a case, weighting is set in advance so that the position where the quality of the fish is higher is the most suitable fishing ground, and based on the actually obtained quality of the fish, the weighting is referred to and the fishing ground is proposed. good too. Since the quality of the fish is actually associated with the position and time of landing as described above, it is possible to propose a fishing ground according to the position. Further, when proposing this fishing ground, the current position information of the fishing boat may be acquired, and the fishing ground may be proposed based on the acquired position information. Weighting may be set in advance so that a position closer to the current position of the fishing boat is the most suitable fishing ground, and a fishing ground may be proposed by referring to the weighting based on the actually acquired position information. At this time, the optimum fishing season may also be proposed by referring to the chronological trend.

Furthermore, in the present invention, desired quality information for fish quality reflecting consumer needs may be obtained. This desired quality information is information that indicates what kind of fish quality is demanded by consumers, and by extension, retail stores and wholesale markets that reflect consumer demand. This desired quality information is composed of the quality of the fish that the fish wants to receive, which is collected from retail stores and wholesale markets. The desired quality information may indicate the quantity for each fish species. A fishing ground may be proposed based on such desired quality information. In such a case, the quality of the landed fish shown on the two-dimensional map, which is obtained through the degree of association described above, is compared, and fishing grounds that are likely to catch fish of a quality matching the desired quality information are proposed.

At the stage when the desired quality information is uploaded, weighting is applied to the quality of the fish for each fishing ground shown on the two-dimensional map obtained through the above-mentioned degree of association, and the position where the fish of the quality close to the desired quality information can be landed. You may make it weight heavily. Then, a fishing ground may be selected based on the weighting.

Also, when learning the degree of association, the degree of association with the quality of the fish landed in chronological order may be learned. By giving priority to those with a higher degree of association, the chronological quality of the fish to be landed in the new sea area to be landed may be predicted on the two-dimensional map. In such a case, in addition to or in place of the chronological trend of changes in the amount of landings from t1 to t4 in FIG. You may make it learn.

Third Embodiment The present invention can be applied not only to deep-sea fishery and inshore fishery, but also to coastal fishery using seine nets and set nets. In coastal fisheries, fishing spots are mostly specified. For this reason, the two-dimensional map used in the first and second embodiments does not predict the amount of landed fish at each point, but predicts the amount of landed land at a fixed point where coastal fishing is performed. Therefore, it is not essential to use a two-dimensional map in this third embodiment. However, even when using a two-dimensional map, if the position for coastal fishing that appears on the map appears on the map, the first embodiment and the second embodiment using the two-dimensional map It is also possible to search for solutions using

In such a coastal fishery, the two-dimensional map is not used in the first embodiment and the second embodiment, except for making predictions focusing on one sea area where fixed coastal fishing is performed. 2 embodiment.

For example, when using the reference sea information, the reference sea information is used based on the physical data actually measured or calculated for the coastal sea areas where fish have been landed in the past. Then, referencing three or more levels of correlation between this reference sea information and the amount of landings in the sea area, and based on the reference sea information corresponding to the sea information of the coastal sea area newly acquired, the correlation is determined. Landings are projected for the coastal waters with priority given to those with higher degrees. The same applies to other reference information.

1 Landing amount prediction system 2 Search device 21 Internal bus 23 Display unit 24 Control unit 25 Operation unit 26 Communication unit 27 Estimation unit 28 Storage unit 61 Node

Claims (17)

In a landing prediction program that predicts the amount of fish landing in offshore fishing grounds,
an information acquisition step of acquiring sea information based on physical data actually measured or calculated for a sea area where new fish are to be landed;
Reference sea information based on physical data actually measured or calculated for the sea areas where fish have been landed in the past, and the amount of landed fish displayed on the two-dimensional map of the above sea areas. Based on the reference sea information corresponding to the sea information acquired in the acquisition step, prioritizing the one with the higher degree of correlation, predicting the amount of landed fish on the two-dimensional map for the sea area where the new fish are to be landed. A landing amount prediction program characterized by causing a computer to execute the steps of; In the information acquisition step, the physical data includes any one or more of seawater temperature, salinity, current velocity and direction, tide, sea surface altitude, occurrence of red tide, and amount of carbon dioxide in the sea area,
2. The prediction step refers to reference sea information based on physical data of the same type as the physical data acquired in the information acquisition step, and three or more degrees of association with the landing amount. Landing forecast program. In the prediction step, the above-mentioned degree of association between the amount of landing and the fish species that has been landed is referred to, and priority is given to those with the higher degree of association. The landing amount prediction program according to claim 1 or 2, wherein the prediction is made on the two-dimensional map. The landing amount prediction according to any one of claims 1 to 3, further comprising a proposing step of proposing a fishing ground based on at least the landing amount predicted on the two-dimensional map in the prediction step. program. In the prediction step, the degree of correlation with the time-series landing amount is referred to, and priority is given to those with a higher degree of correlation, and the time-series landing amount is calculated for the sea area where the new fish are to be landed. The landing amount prediction program according to claim 1 or 2, wherein the prediction is made on a two-dimensional map. 6. The landing according to claim 5, wherein the prediction step further comprises a proposal step of proposing a fishing ground and fishing season based on at least the chronological landing amount predicted on the two-dimensional map. quantity forecasting program. In the information acquisition step, time information regarding the scheduled time for landing a new fish is acquired,
The prediction step refers to a combination of the reference sea information and the reference time information related to the time of landing in the past, and the degree of association with the amount of landing in three or more stages, and further, in the information acquisition step, Based on the reference time information corresponding to the acquired time information, prioritizing those with a higher degree of correlation, the amount of landed fish is predicted on the above two-dimensional map for the sea area where the new fish will be landed. The landing amount prediction program according to claim 1 or 2. In the information obtaining step, fish school position information about the position on the two-dimensional map of the fish school detected in the sea area where the new fish are to be landed is obtained,
In the prediction step, a combination having the reference sea information and the reference fish school position information related to the position on the two-dimensional map of the fish school detected in the past landed sea area, and the landing amount in three stages or more. By referring to the degree of association and further based on the reference fish school position information corresponding to the fish school position information acquired in the information acquisition step, the one with the higher degree of association is prioritized, and the new fish are landed in the sea area. 3. The landing amount prediction program according to claim 1, wherein the amount is predicted on the two-dimensional map. In the information acquisition step, image information captured on the sea or underwater is acquired for a sea area where a new fish is to be landed,
In the prediction step, a combination of the reference sea information and the reference image information captured on the sea or in the water about the sea area where the fish were landed in the past, and the degree of association with the landed amount in three or more stages are referred to, Furthermore, based on the reference image information corresponding to the image information acquired in the information acquisition step, the amount of landing for the sea area where the new fish are to be landed is displayed on the two-dimensional map, giving priority to the one with the higher degree of association. 3. The landing amount prediction program according to claim 1 or 2, characterized in that it predicts. In the above information acquisition step, weather information on the weather of the sea area where the new fish are to be landed is acquired,
In the prediction step, a combination of the reference sea information and the reference weather information relating to the weather in the sea area where the fish were landed in the past, and the degree of association with the landed amount in three or more stages are referred to, and further the information acquisition step is performed. Based on the reference weather information corresponding to the weather information acquired in , prioritizing those with a higher degree of correlation, predicting the amount of landing of the new fish on the two-dimensional map. The landing amount prediction program according to claim 1 or 2. In the above information acquisition step, the position information of the fishing ground at the present time is acquired,
5. The landing amount prediction program according to claim 4, wherein the proposing step proposes the fishing ground based on the position information acquired in the information acquiring step. In the above information acquisition step, the desired landing volume information is acquired for the landing volume reflecting the needs from the consumer side,
The landing amount prediction program according to any one of claims 1 to 11, wherein the proposing step proposes the fishing ground based on the desired landing amount information acquired in the information acquiring step. In the above information acquisition step, market information on market conditions at the time of new fish landing is acquired,
In the prediction step, referring to three or more levels of association between the combination of the reference sea information and the reference market condition information related to the market condition in the past when the fish were landed, and the sales data linked to the landed quantity, Furthermore, based on the reference market condition information corresponding to the market condition information acquired in the information acquisition step, prioritizing data with a higher degree of correlation, searching for sales data linked to the amount of landing. 3. The landing amount prediction program according to 1 or 2. The information acquisition step acquires external environment information related to the external environment at the time when a new fish is to be landed,
In the prediction step, a combination of the reference sea information and the reference external environment information related to the external environment in the past when the fish were landed, and the sales data linked to the landed amount are referred to at least three levels of association. Further, based on the external environment information for reference corresponding to the external environment information acquired in the information acquisition step, the sales data linked to the amount of landing is searched for, prioritizing those with a higher degree of correlation. The landing amount prediction program according to claim 1 or 2. In the information acquisition step, time information regarding the scheduled time for landing a new fish is acquired,
In the prediction step, priority is given to items with a higher degree of correlation, and based on the acquired time information, the amount of landed fish is predicted on the two-dimensional map for the sea area where the new fish will be landed. A landing amount prediction program according to claim 1 or 2. The landing amount prediction program according to any one of claims 1 to 15, wherein the prediction step uses the degree of association corresponding to a weighting coefficient of each output of a neural network node in artificial intelligence. In a landing prediction program that predicts the amount of fish landing in coastal fishing grounds,
an information acquisition step of acquiring sea information based on physical data actually measured or calculated for a coastal sea area where new fish are to be landed;
Reference sea information based on physical data actually measured or calculated for coastal sea areas where fish have been landed in the past, and sea information acquired in the above information acquisition step by referring to three or more levels of correlation with the amount of fish landed in the above sea areas. A landing amount prediction program characterized by causing a computer to execute a prediction step of predicting the landing amount for the coastal sea area with priority given to the reference sea information according to the above-mentioned high degree of correlation.

Images