JP7313769B2 - Knowledge base generation device, knowledge base generation method, and knowledge base generation program - Google Patents

Description

The present invention relates to a knowledge base generation device, a knowledge base generation method, and a knowledge base generation program. In particular, the present invention relates to a knowledge base generation device, a knowledge base generation method, and a knowledge base generation program for automatically generating a knowledge base regarding ship behavior.

Conventionally, there is no method for automatically generating a knowledge base on ship behavior. Thus, a knowledge base of vessel behavior was created by manual input.
Patent Literature 1 discloses a tactical support device that draws up operational guidelines for mobile devices in a short period of time based on the quantified total strength of deployed enemy and ally mobile devices.

JP 2015-197232 A

In the conventional knowledge base creation method, knowledge possessed by experts is manually input into the knowledge base to create a ship behavior knowledge base. In Japanese Unexamined Patent Application Publication No. 2002-100002 as well, a database used for drafting operating procedures for mobile devices, that is, a knowledge base is manually created.
It takes a lot of effort and time to build a large-scale knowledge base that covers effective behavior patterns in consideration of a wide variety of behavioral patterns for different types of ships or missions, as well as various aspects such as sea and weather conditions.
In addition, there are patterns in which the knowledge or experience differs depending on the inputter, and, for example, the correct answer cannot be determined uniquely for knowledge related to the behavior of warships. Therefore, there is a possibility that the knowledge base will be biased due to the input's arbitrary interpretation intervening in the knowledge base.
Furthermore, there is a risk that important knowledge that should be input may be omitted, or that useful knowledge that the inputter cannot recognize as knowledge may not be input.

An object of the present invention is to automatically generate an appropriate and effective knowledge base.

A knowledge base generation device according to the present invention includes:
In a knowledge base generation device for generating a knowledge base related to ship behavior,
a collection unit that collects a ship log including voyage information indicating the state of the voyage of the ship, wide-area information that indicates the situation around the ship, target specification information that indicates the specifications of targets detected by sensors provided on the ship, and operation information for an operation console mounted on the ship, and outputs time-series information that represents data for each type of information in the ship log in time series;
an extraction unit that extracts data patterns of each information type as a series from the time series information and outputs frequent series information in which the extracted series are arranged in descending order of frequency of appearance;
and a knowledge base recording unit for generating the knowledge base based on the series included in the frequent series information.

According to the knowledge base generating apparatus of the present invention, it is possible to automatically generate an appropriate and effective knowledge base by using ship logs collected from ships.

1 is a configuration diagram of a knowledge base generation system according to Embodiment 1; FIG. 1 is a configuration diagram of a knowledge base generation device according to Embodiment 1; FIG. 4 is a flowchart showing knowledge base generation processing of the knowledge base generation device according to the first embodiment; FIG. 4A and 4B are examples of time series information and frequent series information according to Embodiment 1; FIG. 2 is a configuration diagram of a knowledge base generation device according to a modification of Embodiment 1;

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. In each figure, the same reference numerals are given to the same or corresponding parts. In the description of the embodiments, the description of the same or corresponding parts will be omitted or simplified as appropriate.

Embodiment 1.
*** Configuration description ***
FIG. 1 is a configuration diagram of a knowledge base generation system 500 according to the first embodiment.
A knowledge base generation system 500 includes a knowledge base generation device 100 .
The knowledge base generation device 100 generates a knowledge base related to ship behavior. A ship is a mobile body that navigates on water. For example, the vessel is a water-going vehicle such as a naval vessel, cargo ship, tanker, or training vessel. Knowledge base generation device 100 includes collection unit 110 , extraction unit 120 , and knowledge base recording unit 130 .
The knowledge base generation device 100 is also called a ship behavior knowledge base automatic generation device. The collection unit 110 is also called a vessel log collection/threshold detection exclusion device. The extraction unit 120 is also called a frequent sequence extraction device. The knowledge base recording unit 130 is also called a ship behavior knowledge base recording device.

The knowledge base generation system 500 also includes a navigation information output device 1 , a wide area information output device 2 , a ship-mounted sensor 3 , a ship-mounted sensor 4 , a ship-mounted sensor 5 , an operation console 6 , an operation console 7 , and an operation console 8 .

The voyage information output device 1 periodically transmits voyage information 21 such as the ship's coordinates, speed, course, and wind speed and direction to the collection unit 110 . Let the voyage information at time T _m be N(T _m ).

The wide area information output device 2 periodically transmits wide area information 22 acquired from a ground base station via satellite communication to the collection unit 110 . Let C(T _m ) be the wide-area information at time T _m .

The ship-mounted sensors 3 , 4 , 5 periodically transmit target specification information 23 such as the position, speed, acceleration, and feature quantity of detected targets to the collecting unit 110 . The target dimension information from the ship-mounted sensors 3, 4, 5 at time _Tm is assumed to be _S3 ( _Tm ), _S4 ( _Tm ), _S5 ( _Tm ).

The operation consoles 6, 7, and 8 transmit the operator's operation information 24 to the collection unit 110 when an operator's operation occurs. Let the operation information of the operation consoles 6, 7, 8 at time _Tm be _A6 ( _Tm ), _A7 ( _Tm ), and _A8 ( _Tm ).

The voyage information N (T _m ), wide area information C (T _m ), target specification information S ₃ (T _m ), S ₄ (T _m ), S ₅ (T _m ), and operation information A ₆ (T _m ), A ₇ (T _m ), A ₈ (T _m ) are referred to as ship log 20 .

The configuration of the knowledge base generation device 100 according to this embodiment will be described with reference to FIG.
Knowledge base generation device 100 is a computer. The knowledge base generation device 100 includes a processor 910 and other hardware such as a memory 921 , an auxiliary storage device 922 , an input interface 930 , an output interface 940 and a communication device 950 . The processor 910 is connected to other hardware via signal lines and controls these other hardware.

The knowledge base generation device 100 includes a collection unit 110, an extraction unit 120, a knowledge base recording unit 130, and a storage unit 140 as functional elements. The storage unit 140 stores exclusion conditions 141 and a knowledge base 142 .

The functions of the collecting unit 110, the extracting unit 120, and the knowledge base recording unit 130 are realized by software. Storage unit 140 is provided in memory 921 .

Processor 910 is a device that executes a knowledge base generation program. The knowledge base generation program is a program that implements the functions of the collection unit 110 , the extraction unit 120 and the knowledge base recording unit 130 .
The processor 910 is an IC (Integrated Circuit) that performs arithmetic processing. Specific examples of the processor 910 are a CPU, a DSP (Digital Signal Processor), and a GPU (Graphics Processing Unit).

The memory 921 is a storage device that temporarily stores data. A specific example of the memory 921 is SRAM (Static Random Access Memory) or DRAM (Dynamic Random Access Memory).
Auxiliary storage device 922 is a storage device that stores data. A specific example of the auxiliary storage device 922 is an HDD. The auxiliary storage device 922 may be a portable storage medium such as an SD (registered trademark) memory card, CF, NAND flash, flexible disk, optical disk, compact disk, Blu-ray (registered trademark) disk, or DVD. Note that HDD is an abbreviation for Hard Disk Drive. SD® is an abbreviation for Secure Digital. CF is an abbreviation for CompactFlash®. DVD is an abbreviation for Digital Versatile Disk.

The input interface 930 is a port connected to an input device such as a mouse, keyboard, or touch panel. The input interface 930 is specifically a USB (Universal Serial Bus) terminal. The input interface 930 may be a port connected to a LAN (Local Area Network). The knowledge base generation device 100 acquires the exclusion condition 141 from the user via the input interface 930 .
The output interface 940 is a port to which a cable of an output device such as a display is connected. The output interface 940 is specifically a USB terminal or an HDMI (registered trademark) (High Definition Multimedia Interface) terminal. The display is specifically an LCD (Liquid Crystal Display). Knowledge base generation device 100 may display knowledge base 142 on a display via output interface 940 .

Communication device 950 has a receiver and a transmitter. The communication device 950 is wirelessly connected to a communication network such as a LAN, the Internet, or a telephone line. The communication device 950 is specifically a communication chip or a NIC (Network Interface Card). Knowledge base generation device 100 acquires ship log 20 via communication device 950 . The knowledge base generation device 100 may acquire the exclusion condition 141 via the communication device 950 . Alternatively, knowledge base generation device 100 may display knowledge base 142 on an external display device via communication device 950 .

The knowledge base generation program is loaded into processor 910 and executed by processor 910 . The memory 921 stores not only the knowledge base generation program but also an OS (Operating System). The processor 910 executes the knowledge base generation program while executing the OS. The knowledge base generation program and OS may be stored in the auxiliary storage device 922 . The knowledge base generation program and OS stored in auxiliary storage device 922 are loaded into memory 921 and executed by processor 910 . Note that part or all of the knowledge base generation program may be incorporated into the OS.

The knowledge base generation device 100 may include multiple processors in place of the processor 910 . These multiple processors share the execution of the knowledge base generation program. Each processor, like processor 910, is a device that executes a knowledge base generation program.

Data, information, signal values and variable values that are used, processed or output by the knowledge base generation program are stored in memory 921, auxiliary storage 922, or registers or cache memory within processor 910. FIG.

The "part" of each part of the collecting part 110, the extracting part 120, and the knowledge base recording part 130 may be read as "processing", "procedure", or "process". Also, the "processing" of the collecting process, the extracting process, the knowledge base recording process, and the recording process may be read as "program", "program product", or "computer-readable storage medium recording the program".

The knowledge base generation program causes a computer to execute each process, each procedure, or each process, where the above "part" is read as "process,""procedure," or "step." Also, the knowledge base generation method corresponds to each procedure in which the above-mentioned "part" is read as "procedure".
The knowledge base generation program may be stored in a computer-readable recording medium and provided. Also, the knowledge base generation program may be provided as a program product.

***Description of operation***
FIG. 3 is a flowchart showing knowledge base generation processing S100 of knowledge base generation apparatus 100 according to the present embodiment.
The exclusion condition 141 is set by the user via the input interface 930 . The storage unit 140 stores, as exclusion conditions 141, conditions for information to be excluded from the knowledge base generation process. The exclusion condition 141 is a threshold for selecting information from the ship log 20 to be excluded from the knowledge base generation process.

In step S<b>101 , the collection unit 110 collects the ship log 20 . The vessel log 20 includes voyage information 21 indicating the voyage status of the vessel, wide-area information 22 indicating the surroundings of the vessel, target specification information 23 indicating the specifications of targets detected by sensors provided on the vessel, and operation information 24 for an operation console mounted on the vessel.

In step S102, the collection unit 110 outputs the time-series information 31 representing the data for each information type in the ship log 20 in time series. The collection unit 110 outputs the time-series information 31 obtained by excluding information that matches the exclusion condition 141 from the vessel log 20 . The collection unit 110 outputs the time-series information 31 as time-series data for each information type.
Specifically, the collection unit 110 uses the exclusion condition 141 to exclude from the ship log 20 those that meet the exclusion condition. The collection unit 110 matrixes the data after the exclusion process as time-series data for each information type. Time-series information 31 is the matrix-formed data after the exclusion process. The collection unit 110 transmits the time series information 31 to the extraction unit 120 .

FIG. 4 is a diagram showing an example of time series information 31, frequent series information 32, and knowledge base 142 according to the present embodiment.
The time-series information 31 is information in which the data of each information type in the ship log 20 are expressed in time series and arranged in a matrix. In FIG. 4, as information types, navigation information, wide area information, sensor information A, B, target information A, B, C, and consoles A, B, C, D . E operation is set. In the time series information 31, data are set in time series for each of these information types.

In step S103, the extraction unit 120 extracts data patterns of each information type for each time as a series from the time series information 31, and outputs the frequent series information 32 in which the extracted series are arranged in descending order of frequency of appearance.

Specifically, it is as follows.
The extraction unit 120 uses the Prefix-projected sequential pattern mining algorithm for the time-series information 31 received from the collection unit 110 to list the sequences S _n at each time T _m .

A series is a pattern of data of each information type for each time. The sequence _Sn at time _Tm means all sequences at time _Tm . That is, if the time is on the horizontal axis and the series is on the vertical axis, the series _Sn at each time _Tm means all series for all time. As a specific example in FIG. 4, "h, 1, x, Y, X" at time 1, time 6, and time 7 are treated as an example of a series. In addition, at time 1, there are sequences such as "A, j", "1, x, y," and "a, A, X". In this way, information representing all series of all times is listed.

Then, the extraction unit 120 outputs the sequences Sn in descending order of frequency of appearance.
Let m and n be natural numbers. An arbitrary number of vessel logs at times _Tm are stored in each series _Sn . That is, if the series is "h, 1, x, Y, X", five ship logs are stored. This number can be changed from "one" to "the number of all types of elements that can be acquired".

When outputting the sequences Sn in descending order of appearance frequency, the extracting unit 120 does not output the same sequence repeatedly, and outputs each sequence once. The extracting unit 120 stores the output series in an ordered set, and makes the series ordered set P in the order of appearance frequency. P becomes (S _t1 , S _t2 , S _t3 , . . . S _tk ). Let k be a natural number. The extraction unit 120 outputs the series ordered set P as the frequent series information 32 to the knowledge base recording unit 130 . For example, the sequential order set P=(“h, 1, X, Y, X”, “c, h, x”, “d, D, 3, 3, z”, . . . ).

In step S<b>104 , the knowledge base recording unit 130 generates the knowledge base 142 based on the series included in the frequent series information 32 . The knowledge base recording unit 130 converts the sequences included in the frequent sequence information 32 into if-then sentences and stores them in the knowledge base 142 .
The knowledge base recording unit 130 converts the series included in the frequent series information 32 into a set of if-then sentences "If ◯◯, then XX". The knowledge base recording unit 130 applies a conversion formula to a series in which the sensor information, the voyage information, the wide area information, and the operation information are paired, and converts them into if-then sentences.

Specifically, it is as follows.
First, the example in FIG. 1 will be described.
The knowledge base recording unit 130 determines that the frequent sequence information 32 input from the extracting unit 120, that is, each _Stk stored in the sequence order set P includes at least one of A ₆ (T _m ), A ₇ (T _m ), and A ₈ (T _m ), and N(T _m ), C(T _m ), S ₃ (T _m ), S ₄ (T _m ), and S ₅ . A sequence containing at least one of (T _m ) is converted into an if-then statement and stored in the knowledge base 142 . Specifically, the knowledge base recording unit 130 converts it into an if-then sentence stating “If {N(T _m ), C(T _m ), S ₃ (T _m ), S ₄ (T _m ), S ₅ (T _m )} is {A ₆ (T _m ), A ₇ (T _m ), A ₈ (T _m )}” and stores it in the knowledge base 142.

Further, an example of FIG. 4 will be described.
The sequence "h, 1, x, Y, X" shown in FIG. 4 is converted to an if-then statement that "If sensor information A=h and target information=1, then console A operation=x, console C operation=Y, and console E operation=X."

***Other Configurations***
<Modification 1>
In this embodiment, the functions of the collecting unit 110, the extracting unit 120, and the knowledge base recording unit 130 are realized by software. As a modification, the functions of the collecting unit 110, the extracting unit 120, and the knowledge base recording unit 130 may be realized by hardware.

FIG. 5 is a diagram showing the configuration of knowledge base generation device 100 according to a modification of the present embodiment.
Knowledge base generation device 100 comprises electronic circuitry 909 , memory 921 , auxiliary storage device 922 , input interface 930 and output interface 940 .

The electronic circuit 909 is a dedicated electronic circuit that implements the functions of the collection unit 110 , the extraction unit 120 and the knowledge base recording unit 130 .
Electronic circuit 909 is specifically a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, GA, ASIC, or FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array.
The functions of the collecting unit 110, the extracting unit 120, and the knowledge base recording unit 130 may be implemented by one electronic circuit, or may be implemented by being distributed among a plurality of electronic circuits.
As another modification, part of the functions of the collecting unit 110, the extracting unit 120, and the knowledge base recording unit 130 may be implemented by electronic circuits, and the remaining functions may be implemented by software.

Each of the processor and electronic circuitry is also called processing circuitry. That is, in the knowledge base generation device 100, the functions of the collection unit 110, the extraction unit 120, and the knowledge base recording unit 130 are realized by processing circuitry.

***Description of the effects of the present embodiment***
The knowledge base generating apparatus 100 according to the present embodiment can automatically generate a knowledge base by using ship logs such as sensor information or system log information that already exist in the ship. Therefore, according to the knowledge base generation device 100 according to the present embodiment, it is possible to automatically generate a knowledge base of ship behavior without manual preparation, and it is possible to improve the efficiency of the work related to building the knowledge base.

Further, according to the knowledge base generation device 100 according to the present embodiment, since the knowledge base is cross-extracted from each ship log, the knowledge base can be generated without arbitrary bias.

In addition, in the knowledge base generation apparatus 100 according to the present embodiment, when constructing a large-scale knowledge base by automation, actual data is used to avoid bias in the knowledge base due to differences in knowledge or experience of each inputter due to manual input. Furthermore, by searching all data, it is possible to avoid omission of knowledge input and to discover useful knowledge that the input person has not recognized as knowledge.

In the above first embodiment, each part of the knowledge base generation device has been described as an independent functional block. However, the configuration of the knowledge base generation device does not have to be the configuration of the embodiment described above. The functional blocks of the knowledge base generation device may have any configuration as long as they can implement the functions described in the above embodiments. Also, the knowledge base generation device may be a system composed of a plurality of devices instead of a single device.
Moreover, it is also possible to combine a plurality of portions of the first embodiment. Alternatively, one portion of this embodiment may be implemented. In addition, this embodiment may be implemented as a whole or partially in any combination.
That is, in Embodiment 1, it is possible to freely combine each embodiment, modify any component of each embodiment, or omit any component from each embodiment.

The above-described embodiments are essentially preferable examples, and are not intended to limit the scope of the invention, the scope of applications of the invention, or the scope of applications of the invention. Various modifications can be made to the above-described embodiments as required.

1 voyage information output device 2 wide area information output device 3, 4, 5 ship-mounted sensors 6, 7, 8 operation console 20 ship log 21 voyage information 22 wide area information 23 target specification information 24 operation information 31 time series information 32 frequent series information 100 knowledge base generation device 110 collection unit 120 extraction unit 130 knowledge base recording unit 140 storage unit 14 1 Exclusion condition 142 Knowledge base 500 Knowledge base generation system 909 Electronic circuit 910 Processor 921 Memory 922 Auxiliary storage device 930 Input interface 940 Output interface 950 Communication device S100 Knowledge base generation processing.

Claims (3)

In a knowledge base generation device for generating a knowledge base related to ship behavior,
前記船舶の航海の状態を示す航海情報と、前記船舶の周囲の状況を表す広域情報と、前記船舶に備えられた複数のセンサの各センサ情報と、前記各センサにより探知された目標の位置、速度、加速度、および特徴量を含む諸元を表す目標諸元情報と、前記船舶に搭載されオペレータの操作が発生した際にオペレータの操作情報を送信する複数の操作コンソールの各操作コンソールからの各オペレータの操作情報とを含む船舶ログを収集し、前記船舶ログにおける情報種別ごとのデータを時系列に表した時系列情報であって、前記船舶ログから除外する情報を選択するための閾値である除外条件に適合する情報を除外した時系列情報を出力する収集部と、
an extraction unit that extracts data patterns of each information type as a series from the time series information for each output time, and outputs frequent series information in which the extracted series are arranged in descending order of frequency of appearance;
a knowledge base generating unit for converting data other than the operation information of each operator from each operation console into an if-then statement in which data other than the operation information of each operator from each operation console is an if statement and data of operation information of each operator from each of the operation consoles is an if-then statement based on the series including the sensor information, the target specification information, and the data of operation information of each operator from each operation console among the series included in the frequent series information, and generating the knowledge base as a knowledge base of the operation information of each operator for each of the operation consoles . In a knowledge base generation method for a knowledge base generation device that generates a knowledge base related to ship behavior,
コンピュータが、前記船舶の航海の状態を示す航海情報と、前記船舶の周囲の状況を表す広域情報と、前記船舶に備えられた複数のセンサの各センサ情報と、前記各センサにより探知された目標の位置、速度、加速度、および特徴量を含む諸元を表す目標諸元情報と、前記船舶に搭載されオペレータの操作が発生した際にオペレータの操作情報を送信する複数の操作コンソールの各操作コンソールからの各オペレータの操作情報とを含む船舶ログを収集し、前記船舶ログにおける情報種別ごとのデータを時系列に表した時系列情報であって、前記船舶ログから除外する情報を選択するための閾値である除外条件に適合する情報を除外した時系列情報を出力し、
A computer extracts data patterns of each information type as a series from the time series information for each output time, and outputs frequent series information in which the extracted series are arranged in descending order of appearance frequency,
A knowledge base generation method in which a computer converts data other than operation information of each operator from each operation console into an if-then statement in which data other than operation information of each operator from each operation console is an if statement and data of operation information of each operator from each operation console is an if-then statement based on a series including the data of the operation information of each operator from each of the operation consoles, and the knowledge base is generated as a knowledge base of the operation information of each operator for each of the operation consoles . In a knowledge base generation program for a knowledge base generation device that generates a knowledge base related to ship behavior,
前記船舶の航海の状態を示す航海情報と、前記船舶の周囲の状況を表す広域情報と、前記船舶に備えられた複数のセンサの各センサ情報と、前記各センサにより探知された目標の位置、速度、加速度、および特徴量を含む諸元を表す目標諸元情報と、前記船舶に搭載されオペレータの操作が発生した際にオペレータの操作情報を送信する複数の操作コンソールの各操作コンソールからの各オペレータの操作情報とを含む船舶ログを収集し、前記船舶ログにおける情報種別ごとのデータを時系列に表した時系列情報であって、前記船舶ログから除外する情報を選択するための閾値である除外条件に適合する情報を除外した時系列情報を出力する収集処理と、
Extraction processing for extracting data patterns of each information type as a series from the time-series information for each output time, and outputting frequent series information in which the extracted series are arranged in descending order of frequency of appearance;
a knowledge base recording process for generating the knowledge base as a knowledge base of the operation information of each operator for each of the operation consoles by converting into an if-then statement in which the data other than the operation information of each operator from each of the operation consoles is an if statement and the data of the operation information of each operator from each of the operation consoles is a then statement, based on the series including the sensor information, the target specification information, and the data of operation information of each operator from each operation console among the series included in the frequently occurring series information; knowledge base generator.

Images