KR102486491B1 - Information convergence-based response method recommendation method and device - Google Patents

Abstract

The present invention provides a countermeasure recommendation method, which collects a plurality of types of observation data, processes the collected plurality of types of observation data to generate fusion data, compares the fusion data generated in the past with the fusion data generated in the present, infers an intent for the plurality of types of observation data according to the comparison result using a predetermined rule model, and outputs at least one countermeasure corresponding to the inferred intent among a plurality of predefined countermeasures.

Description

Information convergence-based countermeasure recommendation method and device {INFORMATION CONVERGENCE-BASED RESPONSE METHOD RECOMMENDATION METHOD AND DEVICE}

The present invention relates to a method and apparatus for recommending a countermeasure based on information convergence, and more particularly, collects and fuses a plurality of pieces of information, infers the intention of the plurality of pieces of information using the converged information, and determines the inferred intention. It relates to a method and apparatus for recommending a countermeasure.

Each neighboring country surrounding the Korean Peninsula, such as North Korea, China, and Russia, possesses a variety of high-speed aircraft. To prepare for these threats, the ROK military possesses or is building various interception systems, detection systems, and command and control systems.

The command and control system judges the threat level of the high-speed aircraft detected by the radar and transmits the order to engage to the optimal interception system, and the interception system engages the high-speed aircraft. It also plays a role in disseminating alerts to related weapon systems of high-speed flight information, including launch and drop positions.

Domestic Patent Publication No. 10-2021-0099450 (2021.08.12.) Domestic Patent Publication No. 10-2008-0021017 (2008.03.06.)

The technical problem to be solved by the present invention is to collect and fuse a plurality of information through different paths, analyze the fused information, infer the intention of the collected information, and recommend a countermeasure for the inferred intention. It is to provide a method and apparatus for recommending a countermeasure based on information convergence.

One aspect of the present invention, collecting a plurality of observation data; Generating fusion data by processing a plurality of pre-collected observation data; Comparing fusion data generated in the past with fusion data currently generated; inferring intentions for the plurality of observation data according to the comparison result using a preset rule model; and outputting at least one response plan corresponding to the inferred intention among a plurality of predefined response plans.

In addition, the step of inputting a user input for the output at least one corresponding plan; and correcting each of a plurality of predefined countermeasures for the intention by using the user input.

In addition, the user input may include at least one of a satisfaction level and a corresponding command for each of the outputted at least one corresponding method.

The correcting of each of the plurality of predefined response methods may include determining a score for each of the output at least one corresponding method based on the user input; comparing the determined score with a score of a response plan other than the output at least one response plan among the plurality of response plans; and correcting each of the plurality of countermeasures according to the comparison result.

In addition, the step of determining the score may include, when the input corresponding command is different from the at least one output corresponding method, additional points are given to a score for a corresponding method corresponding to the input corresponding command, and the output A deduction may be given to the score for each of the at least one corresponding method.

In the determining of the score, when the input corresponding command is identical to at least one output corresponding method, additional points may be given to a score corresponding to the corresponding method corresponding to the input corresponding command.

In addition, the at least one countermeasure may be defined differently according to the environment of the region appearing in the observation data.

Also, when there are multiple inferred intentions, the at least one countermeasure method may be differently defined according to a combination of multiple different intentions.

Another aspect of the present invention is a memory in which a preset rule model is stored; And collecting a plurality of observation data, processing the collected plurality of observation data to generate fusion data, comparing the fusion data generated in the past with the fusion data currently generated, and using the preset rule model, A processor for inferring intentions for the plurality of observation data according to the comparison result and outputting a predefined countermeasure for the inferred intentions; may include.

In addition, when a user input for the at least one output countermeasure is input, the processor may correct each of a plurality of predefined countermeasures for the intention using the user input.

In addition, the processor determines a score for each of the at least one output response plan based on the user input, and determines a score different from the determined score and the at least one output response plan among the plurality of response plans. Scores of the countermeasures may be compared, and each of the plurality of countermeasures may be corrected according to the comparison result.

Another aspect of the present invention is a computer readable recording medium storing a computer program, the computer program, when executed by a processor, comprising: collecting a plurality of observation data; generating fusion data by processing the collected plurality of observation data; Comparing fusion data generated in the past with fusion data currently generated; inferring intentions for the plurality of observation data according to the comparison result using a preset rule model; and outputting a predefined countermeasure for the inferred intention.

Another aspect of the present invention is a computer program stored on a computer-readable recording medium, wherein the computer program, when executed by a processor, includes: collecting a plurality of observation data; generating fusion data by processing the collected plurality of observation data; Comparing fusion data generated in the past with fusion data currently generated; inferring intentions for the plurality of observation data according to the comparison result using a preset rule model; and outputting a predefined countermeasure for the inferred intention.

According to one aspect of the present invention described above, by providing a method and apparatus for recommending a countermeasure based on information convergence, a plurality of information is collected and converged through different paths, the converged information is analyzed, and the intent for the collected information is provided. can be inferred, and a countermeasure for the inferred intention can be recommended.

1 is a block diagram of an apparatus for recommending a countermeasure method according to an embodiment of the present invention.
FIG. 2 is a block diagram conceptually illustrating an embodiment of a program for recommending a corresponding plan of FIG. 1 .
FIG. 3 is a diagram illustrating an embodiment of a process of inferring an intention in the reasoning unit of FIG. 2 .
4 is a flowchart of a method for recommending a countermeasure method according to an embodiment of the present invention.
FIG. 5 is a detailed flowchart of a step of generating fusion data of FIG. 4 .
6 is a detailed flowchart of the step of inferring the intent of FIG. 4 .

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only these embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs. It is provided to completely inform the person who has the scope of the invention, and the present invention is only defined by the scope of the claims.

In describing the embodiments of the present invention, if it is determined that a detailed description of a known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. In addition, terms to be described later are terms defined in consideration of functions in the embodiment of the present invention, which may vary according to the intention or custom of a user or operator. Therefore, the definition should be made based on the contents throughout this specification.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of an apparatus for recommending a countermeasure method according to an embodiment of the present invention.

Referring to FIG. 1 , the apparatus 100 for recommending countermeasures may include an input/output module 110 , a processor 120 and a memory 130 .

The processor 120 may collect a plurality of observation data through the input/output module 110 .

Here, the observation data may be generated in different types using a plurality of preset paths.

In one embodiment, observation data may be created in various types such as documents, images, and videos. In this case, the observation data may include information on at least one of aircraft, warheads, facilities, and troops deployed in a preset area.

In this regard, a plurality of paths preset to collect observation data may be a path connected to a server, a web page, etc. in which observation data is stored, and a path connected to a device or system that generates observation data.

In addition, the observation data may include an observation time point at which the observation data is generated and regional coordinates appearing in the observation data.

Accordingly, the processor 120 may generate fusion data by processing a plurality of collected observation data.

Here, the fusion data may be at least one keyword of observation data. In this case, at least one keyword may be extracted from the observation data or generated to be associated with the observation data.

For example, the keyword may be information on at least one of aircraft, warheads, facilities, and troops. In one embodiment, the keywords include specifications of the aircraft, location where the aircraft was observed, direction of the aircraft, direction of the warhead, specifications of the warhead, type of facility, operation of the facility, location where troops were observed, and progress of troops. Information such as direction may be included.

Also, the fusion data may be a pair of at least one keyword of observation data and an image pair of the at least one keyword. In this case, an image for at least one keyword may be created to be related to the at least one keyword. In one embodiment, an image for at least one keyword may be generated as a search result for at least one keyword through a web server or website, or may be matched and extracted with at least one keyword among a plurality of pre-prepared images. .

Accordingly, the processor 120 may compare fusion data generated in the past with fusion data currently generated, and use a preset rule model to deduce the intent of a plurality of observation data according to the comparison result.

Here, the intention is a regional intention for at least one observation data collected within a preset regional range among a plurality of observation data and a wide area according to a plurality of regional intentions inferred for a wide area range including a plurality of different regional ranges. may contain intent.

Accordingly, the processor 120 may infer regional intent for multiple different regional scopes and further infer wide-area intent using the multiple regional intents.

Meanwhile, the intention may be inferred from changes in behavior estimated through changes in a plurality of observation data. In one embodiment, intent may be an inference of at least one of destroy, damage, threaten, reconnaissance, support, deception, and induce negotiations.

Accordingly, the preset rule model may be set to infer an intention for a comparison result between fusion data generated in the past and fusion data currently generated. In one embodiment, the preset rule model may be a kind of artificial neural network trained to output learning intention according to the learning fusion data and correct answer intention, which is label data, as input.

Accordingly, the processor 120 may output the inferred intention through the input/output module 110 .

In this way, the countermeasure recommendation device 100 predicts the enemy's intention to enable effective operation against the enemy, and through this, it is possible to select an appropriate countermeasure to minimize damage to the friendly side.

Moreover, the countermeasure recommendation device 100 can quickly identify an aircraft and a warhead and more accurately calculate the degree of threat accordingly. For example, it may be possible to respond by issuing an evacuation order to an expected damage area in preparation for warheads with high threat levels such as nuclear and biochemical, or calculating and intercepting an interception point capable of minimizing damage.

Meanwhile, the countermeasure recommendation program 200 and information necessary for executing the countermeasure recommendation program 200 may be stored in the memory 130 .

In this specification, the countermeasure recommendation program 200 may refer to software including instructions programmed to collect observation data, generate fusion data, and infer an intention by performing comparison between fusion data.

Accordingly, in order to execute the countermeasure recommendation program 200, the processor 120 may load the countermeasure recommendation program 200 and information necessary for execution of the countermeasure recommendation program 200 from the memory 130.

Meanwhile, the function and/or operation of the countermeasure recommendation program 200 will be described in detail with reference to FIG. 2 .

FIG. 2 is a block diagram conceptually illustrating an embodiment of a program for recommending a corresponding plan of FIG. 1 .

Referring to FIG. 2 , the countermeasure recommendation program 200 includes a collection unit 210, a convergence unit 220, a comparison unit 230, an inference unit 240, a recommendation unit 250, and a feedback unit 260. can include

Meanwhile, the collection unit 210, the convergence unit 220, the comparison unit 230, the inference unit 240, the recommendation unit 250, and the feedback unit 260 shown in FIG. In order to easily explain the function of, the function of the countermeasure recommendation program 200 is conceptually divided, but is not limited thereto. According to embodiments, the functions of the collection unit 210, the fusion unit 220, the comparison unit 230, the reasoning unit 240, the recommendation unit 250, and the feedback unit 260 can be merged/separated, It may be implemented as a series of instructions included in one program.

The collection unit 210 may collect a plurality of observation data. At this time, the collection unit 210 may convert the type of collected observation data. For example, the collecting unit 210 may convert observation data such that the type of collected observation data is at least one of text and image.

In one embodiment, the collection unit 210, when the type of the collected observation data is any one of a Hangul file (hwp), a word file (doc), a presentation file (ppt), and a pdf file, the text (txt) type is Observation data can be transformed.

In another embodiment, when the type of collected observation data is an image file (avi, mkv, mp4, etc.), the collection unit 210 may convert the observation data to be an image (img) type.

Accordingly, the fusion unit 220 may generate fusion data by processing a plurality of observation data. To this end, the fusion unit 220 may extract at least one keyword for each of a plurality of observation data. In this case, the convergence unit 220 may extract at least one keyword from observation data converted into text or image type.

In one embodiment, when the observation data is a text type, the fusion unit 220 may extract keywords for the observation data through techniques such as removing stopwords, morpheme analysis, and syntactic analysis.

In another embodiment, when the observation data is an image type, the fusion unit 220 may output keywords for the observation data by inputting the observation data to a pre-learned keyword extraction model.

In another embodiment, the fusion unit 220 inputs at least one observation data to a pre-learned keyword extraction model for each of at least one observation data that is an image or video among a plurality of observation data, such as an aircraft or a warhead. Keywords for at least one of , facilities, and troops may be output respectively.

On the other hand, the pre-trained keyword extraction model is trained to output learning keywords when learning observation data and answer keywords, which are label data of the learning observation data, are input, and learning observation data and learning observation data are input using the learning observation data and correct answer keywords. can

At this time, the observation data for learning is an image in which at least one of the aircraft, warhead, facility, and military force is observed from various angles, an image in which a partial shape of at least one of the aircraft, warhead, facility, and military force is occluded, and the aircraft, warhead, and facility in different environments. and at least one of an image in which at least one of troops is observed, and an image in which at least one of aircraft, warheads, facilities, and troops with different noises is observed.

In this regard, in one embodiment, observation data for learning may be collected through various websites.

In addition, the correct answer keywords include the specifications of the aircraft, the location where the aircraft was observed, the direction of the aircraft, the direction of the warhead, the specifications of the warhead, the type of facility, whether the facility is operating, the location where the troops were observed, the direction the troops are moving, etc. It may include information of, and may further include information such as specifications of components mounted on the aircraft and specifications of equipment possessed by troops.

Accordingly, the fusion unit 220 may compare at least one keyword extracted from at least two or more of a plurality of observation data.

In one embodiment, the fusion unit 220 may compare keywords using a pre-prepared thesaurus (eg, Thesaurus).

Meanwhile, in another embodiment, the convergence unit 220 may search for images using keywords in a website or server on a preset path, and compare the searched images with each other. In this case, each image may be scored according to the degree of similarity between the images.

The fusion unit 220 may generate fusion data according to a comparison result for each of at least one keyword.

In this case, the fusion unit 220 may generate fusion data by integrating keywords determined to be similar according to the comparison result and listing keywords determined to be dissimilar.

As such, the fusion unit 220 provides information on enemy units and facilities provided through various sources and routes (eg, location, type of deployed aircraft, number of launch pads, etc.), information on ships or submarines capable of launching aircraft, By converging various information analyzed by each information analysis department, it is possible to continuously update aircraft and warhead information held by region or unit.

The comparator 230 may compare fusion data generated in the past with fusion data currently generated. In this case, the comparator 230 may perform comparison between fusion data for each preset time period.

In this regard, the comparator 230 may compare fusion data generated from observation data collected within the same regional range.

Accordingly, the comparison unit 230 may extract a currently changed keyword from among past keywords and extract a newly added keyword as a comparison result. In this case, the comparison unit 230 may further extract a keyword representing a subject of the comparison result.

For example, the changed or added keywords include 'additional arrangement', 'direction', 'forward', 'additional movement', 'construction', and 'operation', and keywords representing the subject include 'high-speed aircraft', It may include 'troops' and 'nuclear test facilities'.

Accordingly, the reasoning unit 240 may infer the intention according to the comparison result. In this regard, the inference unit 240 may output a probability of each of a plurality of different intentions as a result of the inferred intention. For example, the inference unit 240 may infer an intention such that a probability of at least one of destruction, damage, threat, reconnaissance, assistance, deception, and negotiation inducement appears according to the comparison result.

In this regard, in one embodiment, the inference unit 240 may infer threats, local provocations, and test launches as intentions when the comparison result is 'high-speed aircraft, additional deployment' or 'high-speed aircraft, direction'. . At this time, the inference unit 240 may infer a threat at 67%, a local provocation at 21%, and a test launch at 11%.

In another embodiment, the inference unit 240 may infer threats and local provocations as intentions when the comparison result is 'troops, front, additional movement'. At this time, the inference unit 240 may infer the threat as 67% and the local provocation as 21%.

In another embodiment, the reasoning unit 240 infers plutonium extraction and nuclear weapon production, threat and power generation as intention when the comparison result is 'nuclear test facility, construction' or 'nuclear test facility, operation'. can do. At this time, the inference unit 240 may infer plutonium extraction and nuclear weapon production as 66 percent, threat as 30 percent, and power generation as 4 percent.

In another embodiment, the inference unit 240 may infer a threat as an intention when the comparison result is 'high-speed flight vehicle, additional deployment' and 'nuclear test facility, construction'. At this time, the reasoning unit 240 may infer the threat to 97%.

Meanwhile, the inference unit 240 may infer a regional intention based on a comparison result of at least one observation data collected within a preset regional range among a plurality of observation data.

Accordingly, the inference unit 240 may infer a wide-area intention by using a plurality of regional intentions inferred for a wide-area range including a plurality of different regional ranges.

The recommendation unit 250 may output at least one response method corresponding to the inferred intention among a plurality of predefined response methods. To this end, a countermeasure for each of a plurality of different intentions may be defined in advance in the recommendation unit 250 .

In this case, when there are multiple inferred intents, the countermeasures may be defined differently according to a combination of multiple different intents.

In addition, different countermeasures for different environments may be defined in the recommendation unit 250 . That is, countermeasures may be defined differently depending on the environment of the region appearing in the observation data. For example, environment may include temperature, weather, humidity, terrain, latitude, longitude, and altitude.

To this end, the recommender 250 may determine an environment for the corresponding observation data according to the observation time point and regional coordinates included in the observation data. Alternatively, when the fusion data includes a keyword indicating an environment for observation data, the recommendation unit 250 may determine an environment for observation data by using the keyword.

Meanwhile, the feedback unit 260 may receive a user input for at least one response method output from the recommendation unit 250 . In this case, the user input may include at least one of a satisfaction level and a corresponding command for each of the outputted at least one corresponding method. Here, the satisfaction level is a score for each of the output at least one response method, and the response command may be any one of a plurality of predefined response methods.

Accordingly, the feedback unit 260 may correct each of a plurality of predefined countermeasures for the intention using the user input. Through this, the feedback unit 260 may generate an effect of adapting the recommendation unit 250 so that a response plan suitable for the user is output.

In detail, the feedback unit 260 may determine a score for each of the at least one corresponding method output from the recommendation unit 250 based on the user input.

For example, if satisfaction is input as a user input, the feedback unit 260 may increase or decrease the score for the corresponding plan according to the value of satisfaction. In this case, each of the multiple countermeasures may be scored separately. Accordingly, the feedback unit 260 may adjust scores assigned to each of the plurality of response methods based on the satisfaction level.

Meanwhile, when a corresponding command is input as a user input, the feedback unit 260 may determine a score by comparing the input corresponding command with at least one output corresponding method.

For example, the feedback unit 260 may increase the score of the same response method when the input response command and the output at least one response method are the same. In addition, the feedback unit 260 increases the score of the corresponding method corresponding to the input corresponding command when the input corresponding command and the output at least one corresponding method are different from each other, and for each of the at least one output corresponding method score can be lowered.

Accordingly, the feedback unit 260 compares the score determined for each of the output at least one countermeasure with the score of a countermeasure different from the at least one outputted countermeasure, and determines a plurality of responses for the intention according to the comparison result. Each of the countermeasures can be calibrated.

For example, if the score of the output countermeasure plan is higher than the score of other countermeasure plans, the feedback unit 260 maintains the previously determined countermeasure plan for the corresponding intention. A countermeasure for the corresponding intention may be changed to another determined countermeasure.

FIG. 3 is a diagram illustrating an embodiment of a process of inferring an intention in the reasoning unit of FIG. 2 .

Referring to FIG. 3, 'troop movement' and 'additional deployment of high-speed aircraft' are generated as fusion data (10a, 10b), 'threat' and 'provocation' are inferred as regional intentions (30a, 30b), and wide-area It can be confirmed that 'negotiation inducement' is inferred as the intention 50a.

In this regard, the global intent may be determined based on a combination of local intents and a probability of each local intent. For example, when 'threat' and 'provocation' are inferred as regional intentions for different regional scopes, the reasoning unit 240 may infer 'negotiation inducement' as the wide-area intention.

In this regard, in one embodiment, the reasoning unit 240 infers regional intentions for each village using at least one observation data collected for each of a plurality of villages belonging to one country, and Based on the regional intentions inferred for each of the plurality of villages to which it belongs, the wide-area intention of the corresponding country can be inferred.

4 is a flowchart of a method for recommending a countermeasure method according to an embodiment of the present invention.

Referring to FIG. 4 , the processor 120 may collect a plurality of observation data (S100).

In this case, the processor 120 may process a plurality of collected observation data to generate fusion data (S200), and compare the fusion data generated in the past with the fusion data currently generated (S300).

Accordingly, the processor 120 may infer the intention of a plurality of observation data according to the comparison result using a preset rule model (S400).

In addition, the processor 120 may output at least one response plan corresponding to the intention inferred from among a plurality of predefined response plans (S500).

FIG. 5 is a detailed flowchart of a step of generating fusion data of FIG. 4 .

Referring to FIG. 5 , the processor 120 may extract at least one keyword from each of a plurality of observation data (S210) and compare at least one keyword extracted from at least two or more of the plurality of observation data (S220). ).

Accordingly, the processor 120 may generate fusion data according to a comparison result for each of the at least one keyword (S230).

6 is a detailed flowchart of the step of inferring the intent of FIG. 4 .

Referring to FIG. 6 , the processor 120 may infer a regional intention based on a comparison result of at least one observation data collected within a preset regional range among a plurality of observation data (S410).

Accordingly, the processor 120 may infer a wide-area intention using a plurality of regional intentions inferred for a wide-area range including a plurality of different regional ranges (S420).

Various embodiments of the present document are software (eg, machine-readable storage media) (eg, memory (internal memory or external memory)) including instructions stored in a storage medium readable by a machine (eg, a computer). : program). A device is a device capable of calling a stored command from a storage medium and operating according to the called command, and may include an electronic device (eg, a device) according to the disclosed embodiments. When the command is executed by a processor (eg, a processor), the processor may perform a function corresponding to the command directly or by using other components under the control of the processor. An instruction may include code generated or executed by a compiler or interpreter. The device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' only means that the storage medium does not contain a signal and is tangible, but does not distinguish whether data is stored semi-permanently or temporarily in the storage medium.

According to one embodiment, the method according to various embodiments disclosed in this document may be provided by being included in a computer program product.

The above description is merely an example of the technical idea of the present invention, and various modifications and variations can be made to those skilled in the art without departing from the essential qualities of the present invention. Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed according to the claims below, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

100: Countermeasure recommendation device
10a, 10b: fusion data
30a, 30b: local intent
50b: wide intent

Claims (13)

In the countermeasure recommendation method performed by the countermeasure recommendation device,
Collecting multiple observation data;
extracting one or more keywords for each of the plurality of observation data collected, and generating convergence data by integrating similar keywords and enumerating dissimilar keywords through comparison of extracted keywords between two or more observation data;
Comparing previously generated fusion data with currently generated fusion data, extracting a changed keyword, an added keyword, and a keyword representing a subject from the currently generated fusion data, and outputting the result as a comparison result;
inferring an intention including a probability based on a keyword of the comparison result for the plurality of observation data using a preset rule model; and
outputting at least one response plan corresponding to an intention including an inferred probability among a plurality of predefined response plans;
The at least one corresponding method is defined differently according to the environment of the region indicated in the observation data, which is determined according to at least one of an observation point included in the observation data, regional coordinates, and a keyword representing the environment. . According to claim 1,
inputting a user input for the outputted at least one countermeasure; and
Correcting each of the plurality of predefined countermeasures by using the user input;
The method of claim 2, wherein the user input,
A method of recommending a response method comprising at least one of a satisfaction level and a response command for each of the at least one response method.
4. The method of claim 3, wherein the step of correcting each of the plurality of predefined countermeasures comprises:
determining a score for each of the at least one countermeasure based on the user input;
comparing a score determined for each of the at least one countermeasure with scores of the at least one countermeasure and other countermeasures among the plurality of countermeasures; and
Compensating for each of the plurality of predefined countermeasures according to a comparison result; including, a countermeasure recommendation method.
The method of claim 4, wherein determining the score comprises:
If the response command is different from the at least one response method, adding points to a score for the response method corresponding to the response command and subtracting points from the score for each of the at least one response method, How to recommend.
The method of claim 4, wherein determining the score comprises:
Wherein when the corresponding command is identical to the at least one corresponding method, an additional point is given to a score for a corresponding method corresponding to the corresponding command.
delete The method of claim 1, wherein the at least one countermeasure,
If the inferred intent is multiple, it is differently defined according to a combination of different multiple intents.
a memory in which a preset rule model is stored; and
Collecting a plurality of observation data, extracting one or more keywords for each of the collected plurality of observation data, integrating similar keywords through comparison of keywords between two or more observation data, listing dissimilar keywords to generate fusion data, , Compare the fusion data generated in the past with the fusion data currently generated, extract changed keywords, added keywords, and keywords representing subjects from the currently generated fusion data, output them as comparison results, and use the preset rule model. Thus, for the plurality of observation data, the intention including the probability based on the keyword of the comparison result is inferred, and the observation included in the observation data corresponds to the intention including the inferred probability among a plurality of predefined correspondence methods A processor outputting at least one corresponding method differently defined according to the environment of the region indicated in the observation data determined according to at least one of a viewpoint, regional coordinates, and a keyword representing the environment;
The method of claim 9, wherein the processor,
and correcting each of the plurality of predefined countermeasures by using the user input when a user input for the output at least one countermeasure is input.
11. The method of claim 10, wherein the processor,
A score for each of the at least one response plan is determined based on the user input, and a response different from the at least one response plan from the score determined for each of the at least one response plan and the plurality of predefined response plans is determined. A countermeasure recommendation device that compares scores of the countermeasures and corrects each of the plurality of predefined countermeasures according to the comparison result.
A computer-readable recording medium storing a computer program,
When the computer program is executed by a processor,
Collecting multiple observation data;
extracting one or more keywords for each of the plurality of observation data collected, and generating convergence data by integrating similar keywords and enumerating dissimilar keywords through comparison of extracted keywords between two or more observation data;
Comparing previously generated fusion data with currently generated fusion data, extracting a changed keyword, an added keyword, and a keyword representing a subject from the currently generated fusion data, and outputting the result as a comparison result;
inferring an intention including a probability based on a keyword of the comparison result for the plurality of observation data using a preset rule model; and
According to the environment of the region indicated in the observation data, which is determined according to at least one of the observation time point included in the observation data, regional coordinates, and keywords representing the environment in correspondence with the intent including the inferred probability among a plurality of previously stored response methods. A computer-readable recording medium comprising instructions for causing the processor to perform a method comprising: outputting at least one differently defined corresponding scheme.
As a computer program stored on a computer-readable recording medium,
When the computer program is executed by a processor,
Collecting multiple observation data;
extracting one or more keywords for each of the plurality of observation data collected, and generating convergence data by integrating similar keywords and enumerating dissimilar keywords through comparison of extracted keywords between two or more observation data;
Comparing previously generated fusion data with currently generated fusion data, extracting a changed keyword, an added keyword, and a keyword representing a subject from the currently generated fusion data, and outputting the result as a comparison result;
inferring an intention including a probability based on a keyword of the comparison result for the plurality of observation data using a preset rule model; and
According to the environment of the region indicated in the observation data, which is determined according to at least one of the observation time point included in the observation data, regional coordinates, and keywords representing the environment in correspondence with the intent including the inferred probability among a plurality of previously stored response methods. A computer program comprising instructions for causing the processor to perform a method comprising outputting at least one differently defined corresponding scheme.

Images