KR20230165997A - Method for Providing Time Series Data and Artificial Intelligence Optimized for Analysis/Prediction - Google Patents

Abstract

The present invention relates to a method of providing time series data and artificial intelligence modules optimized for analysis/prediction. The method of providing time series data and artificial intelligence modules optimized for analysis/prediction run through an operation server according to the present invention is applicable to industrial fields or S sensing data sensed in time series through S (S ≥ 1) sensors installed in agricultural fields and C images captured in time series through C (C ≥ 1) cameras installed in the field. By collecting and preprocessing D (1≤D≤(S+C)) designated data, it is possible to match within the allowable range T (T≥1) time series models related to the time series of processes or growth performed in the field. A first step of configuring N (1≤N≤D) time series data modeled in a similar manner, and a periodicity that can be matched with a specified periodicity related to at least one process or growth performed in the field based on the N time series data. A second step of confirming t (1≤t≤T) time series models and n (1≤n≤N) time series data with periodicity that can be matched within a specified allowable range, and the identified n time series data are A third step of processing into frequency domain-based time series data corresponding to frequency characteristics, and n' (1≤n'≤ While n) time series data are commonly included, i(1≤i≤(N-n')) time series data that can selectively affect the analysis or prediction among the (N-n') time series data are individually Constructing a plurality of learning data for each G time series data group containing (n'+i) time series data for each G time series data group included in G (G≥1) time series data groups in a specified structure, M artificial intelligence modules equipped with M (M≥2) different artificial intelligence algorithms using a plurality of learning data for each of the G time series data groups configured above (M+G) corresponding to the G time series data groups for each classification. The fourth step of learning the artificial intelligence modules, and after learning the (M+G) number of artificial intelligence modules, the data are collected and preprocessed through the processes corresponding to the first to third steps, and then processed into a designated frequency domain. Among the n time series data, each group of G time series data is composed of n' time series data that are essential for a specified analysis or prediction and individually containing i time series data that can selectively affect the analysis or prediction. (M+G) artificial intelligence for the specified analysis or prediction by substituting (n'+i) time series data for each of the G time series data groups specified in the G artificial intelligence modules for each of the learned M artificial intelligence module classifications. A fifth step of checking the result information for each module, a sixth step of checking the actual measurement result information measured for the result information of the (M+G) artificial intelligence modules, and the confirmed actual measurement result information and (M+ By matching and analyzing the result information for each G) number of artificial intelligence modules, at least one of the accuracy, precision and recall rate for each (M+G) number of artificial intelligence modules for the specified analysis or prediction was evaluated according to the specified evaluation rules (M+G). ) a seventh step of calculating evaluation information, and at least one f(1≤f≤(M+G)) artificial intelligence optimized for a specified analysis or prediction based on the calculated (M+G) evaluation information. It includes the eighth step of determining the intelligence module.

Description

Method for Providing Time Series Data and Artificial Intelligence Optimized for Analysis/Prediction}

The present invention relates to a method of providing time-series data and artificial intelligence modules optimized for analysis/prediction. The present invention relates to a method of providing time-series data and artificial intelligence modules that are optimized for analysis/prediction, by preprocessing data collected in time-series through various sensors or cameras provided in smart farms or smart factories to N (N ≥ 1 ) time series data are modeled, n (1 ≤ n ≤ N) time series data with a series of periodic characteristics are processed into the frequency domain, and any one or two or more of the r (r ≥ 1) known artificial intelligence algorithms are used. After preparing M (M≥1) artificial intelligence modules that are combined and applied to a specific purpose/use, among the n time series data processed into the frequency domain, n' (1≤n'≤n) are essential elements for the specific purpose/use. T containing time series data, each containing at least i(1≤i≤(N-n')) time series data selected as selection factors affecting a specific purpose/use among (N-n') time series data By setting (T≥1) time series data groups, T time series data models that combine one of the T time series data groups and n' time series data are learned by applying them to M artificial intelligence modules. Build (M*T) artificial intelligence modules, and assign T time series data models, for which the result information for specific purposes/uses are already known, to (M*T) artificial intelligence modules, respectively, to obtain the generated result information and already known results. Compare known result information to check at least one of accuracy, precision, and recall. Among (M*T) artificial intelligence modules, t(1≤t≤T) time series data models and m( This is about a method of determining the combination of 1≤m≤M) artificial intelligence modules as a combination of a time series data model and artificial intelligence modules optimized for specific purposes/uses.

In general, 1st and 2nd generation smart farms minimize the impact of various environmental changes outside the greenhouse and set user control settings for the greenhouse's facilities and equipment to provide an optimal cultivation and watering environment for crops inside the greenhouse. It is operated in this way.

However, the control of greenhouse facilities and equipment to provide an optimal cultivation and positive water environment for crops in the greenhouse is realistically difficult to systematize standardized cultivation knowledge due to the variety of greenhouse structures and equipment operation methods, and it is difficult to systematize standardized cultivation knowledge, and it is difficult to systematize the user's knowledge and the target cultivation environment. Because it largely relies on experience and ability, there may be significant differences between farms. In addition, in order to accurately respond to situations where crop damage is expected, such as pests and diseases, physiological disorders, and preparation for abnormal weather, it is necessary to rely on the judgment and decision-making of experts (consultants). You can't help but rely heavily on it.

Meanwhile, as prior art, Republic of Korea Patent Publication No. 10-2021-015853 (published on December 31, 2021) relates to a system and method for generating farmland cultivation maps for artificial intelligence-based agricultural robots, using aerial images. After performing polygon rendering, the boundaries between cultivated fields are identified, the actual cultivable space according to the type of crop is identified, a cultivation map is created, and then provided to the robot agricultural machinery, so that cultivation work is accurately performed even in the cultivable area near the border between cultivated fields. The goal is to make it happen.

However, the above prior art performs polygon rendering using aerial images, generates a cultivation map that accurately identifies the boundary between farmlands through the density difference between polygons, and then transmits it to a robotic agricultural machine to place crops at the exact location through the robotic agricultural machine. It is just cultivating, and various environments for actual cultivation management in smart farms (cultivation environment management, water management, crop growth and physiological management, pest and physiological disorder management, agricultural work management, production and quality management, energy management, etc. ) could not be processed.

Therefore, while overcoming the situation where existing farms strongly prefer face-to-face consulting methods and have relatively low participation or satisfaction with non-face-to-face and online consulting projects, non-face-to-face online consulting for domestic facility farmers is possible under the global pandemic situation. There is a need to find new ways to meet needs and demands.

The purpose of the present invention is to model N (N ≥ 1) time series data by pre-processing the collected data collected in time series through various sensors or cameras installed in smart farms or smart factories, and to model N (N ≥ 1) time series data with a series of n (1) with periodic characteristics. ≤n≤N) time series data are processed into the frequency domain, and M(M≥1) artificial intelligence algorithms are applied to a specific purpose/use by combining any one or two or more of the known r(r≥1) artificial intelligence algorithms. After preparing the intelligence module, among the n time series data processed into the frequency domain, n'(1≤n'≤n) time series data that are essential for specific purposes/uses are included, and among the (N-n') time series data, By setting up T(T≥1) time series data groups, each containing at least i(1≤i≤(N-n')) time series data selected as selection factors affecting a specific purpose/use, T time series T time series data models combining n' time series data with one of the data groups are applied to M artificial intelligence modules to construct (M*T) learned artificial intelligence modules, and construct specific purpose/ At least one of accuracy, precision, and recall rate is achieved by comparing the result information generated by substituting T time series data models for which the result information for the purpose is already known to (M*T) artificial intelligence modules and the already known result information. Confirmed. Among (M*T) artificial intelligence modules, t(1≤t≤T) time series data models and m( It provides a method of providing time series data and artificial intelligence modules optimized for analysis/prediction by determining a combination of 1≤m≤M artificial intelligence modules as a combination of a time series data model and artificial intelligence module optimized for a specific purpose/use. .

The method of providing time series data and artificial intelligence modules optimized for analysis/prediction executed through an operation server according to the present invention involves time-series sensing through S (S ≥ 1) sensors installed in industrial or agricultural fields. Among the S sensing data and C image data captured in time series through C (C≥1) cameras installed at the site, designated D (1≤D≤(S+C)) collected data are collected. A first step of preprocessing and configuring N (1≤N≤D) time series data modeled to enable matching within the allowable range with T (T≥1) time series models related to the time series of processes or growth performed in the field; , based on the N time series data, t (1 ≤ t ≤ T) time series models with a periodicity that can be matched with a specified periodicity related to at least one process or growth performed in the field and a periodicity that can be matched within a specified allowable range. A second step of checking n (1≤n≤N) time series data, and a third step of processing the confirmed n time series data into frequency domain-based time series data corresponding to specified frequency characteristics. And, among the n time series data processed into the frequency domain, the analysis among (N-n') time series data includes n'(1≤n'≤n) time series data essential for specified analysis or prediction. For each G time series data group included in G(G≥1) time series data groups, each individually containing i(1≤i≤(N-n')) time series data that can selectively affect the forecast. Construct a plurality of learning data for each G time series data group containing (n'+i) time series data in a specified structure, and use the plurality of learning data for each G time series data group to generate different M (M ≥ 2) A fourth step of learning (M+G) artificial intelligence modules corresponding to G time series data groups for each classification of M artificial intelligence modules equipped with artificial intelligence algorithms, and the (M+G) artificial intelligence After learning the module, n' time series data essential for specified analysis or prediction are commonly included among the n time series data collected and preprocessed through the process corresponding to the first to third steps and processed into the specified frequency domain. (n'+i) time series data for each G time series data group, individually including i time series data that can selectively affect the analysis or prediction. G for each learned M artificial intelligence module classification. A fifth step of verifying the result information for each (M+G) artificial intelligence module for the specified analysis or prediction by substituting each G time series data group specified in the (M+G) artificial intelligence modules, respectively, and the (M+G) artificial intelligence A sixth step of checking the actual measurement result information for each module, and matching, comparing and analyzing the confirmed actual measurement result information and the result information for each (M+G) artificial intelligence module to determine the specified analysis or prediction ( A seventh step of calculating (M+G) evaluation information in which at least one of M+G) accuracy, precision, and recall for each artificial intelligence module is evaluated according to a designated evaluation rule, and the calculated (M+G) pieces of evaluation information; Time series data and artificial intelligence optimized for analysis/prediction, including an 8th step of determining at least one f (1≤f≤(M+G)) artificial intelligence module optimized for specified analysis or prediction based on evaluation information. How to provide an intelligence module.

According to the present invention, the preprocessing may include an averaging procedure to reveal the representativeness of a periodic pattern or a certain time interval of the D collected data with a specified periodicity.

According to the present invention, the preprocessing may include a procedure for correcting temporal influence corresponding to bias weighted by data from a previous time on data corresponding to a designated independent variable among the D collected data.

According to the present invention, the T time series models include a time series model that can match the time series characteristics of processes performed through devices installed in industrial or agricultural fields, time series characteristics related to the growth of crops grown in agricultural fields, and It may include at least one time series model among the time series models that can be matched.

According to the present invention, the N pieces of time-series data may include time-domain-based time-series data based on time-series characteristics of collected data generated by time-series sensing or time-series photography.

According to the present invention, the periodicity is a periodicity corresponding to at least one process repeatedly performed at regular intervals through a device provided at an industrial or agricultural field, and at least one process performed through a device provided at an industrial or agricultural field. Periodicity corresponds to a schedule associated with a process, periodicity corresponds to a change in the daily interval (or the Earth's rotation interval), periodicity to a change in a trend over a specified period, periodicity to correspond to a seasonal change, and a yearly interval (or the Earth's revolution). It may include at least one periodicity among the periodicities corresponding to changes in the interval.

According to the present invention, the t time series models include the time series characteristics matched with the time series characteristics of the process or growth performed in the field, and the periodic characteristics or specified changes (or trends) of the process performed including a designated period. A periodic time series model containing multiple periodicities matching the periodic characteristics of growth affected by can be included.

According to the present invention, the second step analyzes the N time series data based on at least one periodicity time series model to generate n time series data with a periodicity that can match at least one specified periodicity time series model and a specified tolerance range. It may include a verification step.

According to the present invention, the second step is to apply a specified exponential smoothing method to the time series data in the case of time series data in which the data change according to time is slower than a specified reference value, and then at least one periodic time series model and within a specified tolerance range are performed. It may include the step of identifying n time series data with matchable periodicity.

According to the present invention, the second step analyzes the N time series data based on at least one periodic time series model, and corresponds to a random element or residual/remainer element included in the time series data. It may include the step of separately analyzing the data to identify at least one periodicity time series model and n time series data with a periodicity that can be matched within a specified allowable range.

According to the present invention, the frequency feature may include a model-based period (or frequency) feature corresponding to a time series model with periodicity.

According to the present invention, the frequency characteristic may include a data-based period (or frequency) confirmed by reading time series data with periodicity.

According to the present invention, the frequency feature is statistical processing of the feature of the model-based cycle (or frequency) corresponding to a time series model with periodicity and the feature of the data-based cycle (or frequency) confirmed by reading time series data with periodicity. Alternatively, it may include characteristics of the period (or frequency) confirmed through numerical analysis processing.

According to the present invention, the n time series data processed into the frequency domain are a cycle that matches the periodic characteristics of the process performed, including the cycle designated in the field, or the periodic characteristics of growth affected by a designated change (or trend). It may include time series data processed into the frequency domain corresponding to frequency characteristics that can be matched within the performance tolerance range.

According to the present invention, the n' time series data are within an acceptable range and periodicity matching the periodic characteristics of the process performed including the designated cycle in the field or the periodic characteristics of growth affected by a designated change (or trend). Among n time series data processed into the frequency domain corresponding to matchable frequency characteristics, at least one time series data essential for specified analysis or prediction may be included.

According to the present invention, the fourth step is to preprocess (n'+i) time series data for each of the G time series data groups so that they can be used as learning data for the G artificial intelligence modules for each M artificial intelligence module classification. Additional steps may be included.

According to the present invention, the preprocessing is a data change procedure for changing the character or category attribute value of at least one time series data included in (n'+i) time series data for each of the G time series data groups into numeric data. , It may include at least one of the data scaling procedures for adjusting the range difference between each time series data included in the (n'+i) time series data for each of the G time series data groups to within a specified range. .

According to the present invention, the preprocessing equalizes the periodicity of at least one time series data included in (n'+i) time series data for each of the G time series data groups to a certain time period in a specified time range, k (k ≥ 1 ) may include a process for deriving the result of the next data through the previous data.

According to the present invention, the preprocessing may include common preprocessing that is commonly applicable to time series data included in the learning data of the (M+G) artificial intelligence modules.

According to the present invention, the preprocessing may further include at least one individual preprocessing that can be individually applied to time series data included in the learning data of the (M+G) artificial intelligence modules.

According to the present invention, the learning data includes (n'+i) time series data for each of the G time series data groups as data corresponding to observation features or feature vectors for artificial intelligence learning, Among the (n'+i) time series data for each G time series data group, j(i≥1) data corresponding to an observation result or label related to the specified time series data may be included.

According to the present invention, the learning data is composed of an optimized structure for each of the M artificial intelligence module classifications specified for the learning data including (n'+i) time series data for each of the G time series data groups ( It can contain M+G) learning data.

According to the present invention, the learning data includes a structure that can be integrated and applied to the classification of M artificial intelligence modules designated for the learning data including (n'+i) time series data for each of the G time series data groups. It may contain training data.

According to the present invention, the fifth step is to divide (n'+i) time series data for each of the G time series data groups into each time series data group assigned to the G artificial intelligence modules for each of the learned M artificial intelligence module classifications. A preprocessing step to enable substitution may be further included.

According to the present invention, the result information for each (M+G) artificial intelligence module is result information corresponding to artificial intelligence-based analysis or prediction using frequency domain-based time series data, frequency domain-based time series data, and time domain-based time series data. It may include result information corresponding to artificial intelligence-based analysis or prediction using multiple methods.

According to the present invention, the f artificial intelligence module corresponds to a combination of the g (1 ≤ g ≤ G) time series data group optimized for specified analysis or prediction and the m (1 ≤ m ≤ M) artificial intelligence module classification. It may include at least one artificial intelligence module.

According to the present invention, after determining the f artificial intelligence module, it is essential for a specified analysis or prediction among the n time series data collected and preprocessed through the process corresponding to the first to third steps and then processed into a specified frequency domain. The specified analysis or A ninth step of checking the result information of the f artificial intelligence module for the prediction may be further included.

According to the present invention, future data such as facility preventive maintenance, marketing evidence, and environmental change predictions are generated using previous values in the form of past, present, and future through a method of providing time series data and artificial intelligence modules optimized for analysis/prediction. There are predictable benefits.

In addition, according to the present invention, there is an advantage of being able to predict abnormal cause values, such as predictive maintenance of equipment, prediction of crop growth/physiology, prediction of causes of pests and diseases, and maintenance of IoT environment by detecting patterns with repeated periodic characteristics.

Figure 1 is a diagram showing the configuration of a system for providing time series data and artificial intelligence modules optimized for analysis/prediction according to the implementation method of the present invention.
Figure 2 is a flowchart showing a process of processing time series data confirmed to have a periodicity that can match a specified periodicity related to process or growth into frequency domain-based time series data according to the implementation method of the present invention.
Figure 3 shows (M+G) artificial intelligence learning time series data for each G time series data group that is essential or can selectively affect the analysis or prediction specified according to the implementation method of the present invention with M artificial intelligence algorithms. This is a flowchart showing the process of checking the result information for each (M+G) artificial intelligence module for the specified analysis or prediction by substituting it into the intelligence module.
Figure 4 is optimized for specified analysis or prediction based on (M+G) evaluation information calculated by matching, comparing and analyzing actual measurement result information and (M+G) result information for each artificial intelligence module according to the implementation method of the present invention. This is a flowchart showing the process of determining the artificial intelligence module.

Hereinafter, the operating principle of a preferred embodiment of the present invention will be described in detail with reference to the accompanying drawings and description. However, the drawings shown below and the description below are for preferred implementation methods among various methods for effectively explaining the characteristics of the present invention, and the present invention is not limited to the drawings and description below.

That is, the following examples correspond to preferred union examples among the numerous examples of the present invention, and in the following examples, specific configurations (or steps) are omitted, or specific configurations (or steps) are omitted. An embodiment of dividing an implemented function into a specific configuration (or step), or an embodiment of integrating a function implemented in two or more configurations (or steps) into one configuration (or step), of a specific configuration (or step) It is clearly stated that all embodiments that replace the operation sequence fall within the scope of the present invention, even if not specifically mentioned in the following embodiments. Therefore, based on the examples below, it is clearly stated that various embodiments corresponding to subsets or complements can be divided retroactively to the filing date of the present invention.

Additionally, in the following description of the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. The terms described below are terms defined in consideration of functions in the present invention, and may vary depending on the intention or custom of the user or operator. Therefore, the definition should be made based on the overall content of the present invention.

As a result, the technical idea of the present invention is determined by the claims, and the following examples are a means to efficiently explain the advanced technical idea of the present invention to those skilled in the art to which the present invention pertains. It's just that.

Figure 1 is a diagram showing the configuration of a system for providing time series data and artificial intelligence modules optimized for analysis/prediction according to the implementation method of the present invention.

In more detail, Figure 1 models N (N ≥ 1) time series data by pre-processing the collected data collected in time series through various sensors or cameras installed in smart farms or smart factories, and models n with a series of periodic characteristics. M(M≥1) where (1≤n≤N) time series data is processed into the frequency domain and any one or two or more of the known r(r≥1) artificial intelligence algorithms are combined and applied to a specific purpose/use. After preparing AI modules, among the n time series data processed into the frequency domain, (N-n') time series data are included, including n'(1≤n'≤n) time series data that are essential elements for specific purposes/uses. By setting up T(T≥1) time series data groups, each containing at least i(1≤i≤(N-n')) time series data selected as selection elements that affect a specific purpose/use of the data, T T time series data models, which combine one of the time series data groups and n' time series data, are applied to each of the M artificial intelligence modules to construct (M*T) learned artificial intelligence modules, and build a specific By substituting T time series data models, whose purpose/use result information is already known, into (M Confirmed one. Among (M*T) artificial intelligence modules, t(1≤t≤T) time series data models and m( It shows a system configuration that determines the combination of 1 ≤ m ≤ M artificial intelligence modules with a time series data model optimized for a specific purpose/use and artificial intelligence modules, and is based on common knowledge in the technical field to which the present invention belongs. Those skilled in the art will be able to infer various implementation methods for the above system (e.g., implementation methods in which some components are omitted, subdivided, or combined) by referring to and/or modifying Figure 1, but the present invention does not apply to the above. It includes all inferred implementation methods, and its technical features are not limited to only the implementation methods shown in Figure 1.

The system of the present invention processes time series data collected from one or more sensors or cameras installed in industrial or agricultural fields into frequency domain-based time series data, which can have an essential and selective effect on analysis or prediction. The artificial intelligence module is trained using multiple learning data for each time series data group that contains time series data in a designated structure, and each time series data group is substituted into the learned artificial intelligence module for each artificial intelligence module for specified analysis or prediction. After checking the result information, check the actual measurement result information for each artificial intelligence module, match, compare and analyze the confirmed actual measurement result information and the result information for each artificial intelligence module, and evaluate the evaluation information according to the designated evaluation rules. An operation server 100 that calculates and determines an artificial intelligence module optimized for analysis or prediction based on the calculated evaluation information, and a user terminal 140 that receives the result information from the operation server 100. Includes. Meanwhile, the operating server 100 may be implemented in the form of at least one or a combination of two or more of the following: an independent server, a combination of two or more servers, and a server program installed and run on an equipped server. The present invention is not limited by the method of implementation.

The user terminal 140 is a general term for computer devices used by users that are related to the site and check the result information provided through the operation server 100, and include wired terminals such as computers and laptops connected to a wired network, and wireless terminals such as computers and laptops connected to a wired network. It may include at least one of wireless terminals such as mobile phones, smartphones, tablet PCs, and laptops connected to the network.

Preferably, the user terminal 140 has an application or program installed and running that performs at least one procedure specified for the function of receiving result information for a specified analysis or prediction from the operation server 100. desirable.

Meanwhile, referring to Figure 1, the operation server 100 includes a data configuration unit 105 that configures time series data collected and modeled through sensors or cameras provided in industrial or agricultural fields, and the field a data confirmation unit 110 that verifies time series data with a periodicity that can match a specified periodicity related to at least one process or growth performed in the process, and a data processing unit 115 that processes the time series data into frequency domain-based time series data. Wow, among the time series data processed based on the frequency domain, a plurality of learning data for each time series data group that can be selectively influenced while necessary for a specified analysis or prediction are configured, and a plurality of learning data for each time series data group configured above are used. An artificial intelligence learning unit 120 that learns (M+G) artificial intelligence modules corresponding to series data groups for each artificial intelligence module classification with different artificial intelligence algorithms, and is essential and selectively influences designated analysis or prediction. Time-series data that can be provided are substituted for each time-series data group into the learned plurality of artificial intelligence modules to check the result information for each artificial intelligence module for the designated analysis or prediction, and to perform actual measurements on the result information for each artificial intelligence module. A result information confirmation unit 125 that checks result information, and an evaluation information calculation unit that matches, compares and analyzes the confirmed actual measurement result information and the result information for each artificial intelligence module to calculate evaluation information in which at least one is evaluated according to a designated evaluation rule. It may be configured to include a unit 130 and a module determination unit 135 that determines at least one artificial intelligence module optimized for a specified analysis or prediction.

According to Figure 1, the data configuration unit 105 includes S sensing data sensed in time series through S (S ≥ 1) sensors provided in industrial or agricultural fields and C provided in the field. Among C image data captured in time series through (C≥1) cameras, designated D (1≤D≤(S+C)) collected data are collected and preprocessed to create a time series of processes or growth performed at the site. It is possible to construct T(T≥1) time series models related to performance and N(1≤N≤D) time series data modeled to enable matching within the allowable range.

Typically, the preprocessing of the collected data involves any or a combination of two or more of data cleaning, data transformation, data filtering, data integration, and data reduction at least once. It may include performing

Here, the data purification includes a procedure for filling missing data with default values or replacing them with average/median values, a procedure for identifying and correcting or removing abnormal data corresponding to an abnormal state, and a procedure for smoothing noisy data. It may include any one or a combination of two or more.

In addition, the data conversion may include a procedure for converting data into a form that is easy to analyze through any one or a combination of two or more of normalization, aggregation, summarization, and hierarchy creation. You can.

Additionally, the data filtering may include any one or a combination of two or more of an error data discovery procedure, an error data correction procedure, an error data deletion procedure, a duplicate data confirmation procedure, a duplicate data correction procedure, and a duplicate data deletion procedure.

Additionally, the data integration may include a procedure for integrating similar data or linked data to facilitate data analysis.

Additionally, the data reduction may include a procedure for removing unused data from collected data.

Meanwhile, according to the implementation method of the present invention, the preprocessing of the collected data may include an averaging procedure to reveal the representativeness of a periodic pattern or a certain time interval of the collected data with a specified periodicity among the D collected data.

In addition, according to the implementation method of the present invention, the preprocessing of the collected data is a procedure of correcting the temporal influence corresponding to the bias weighted by data of the previous time with respect to the data corresponding to the designated independent variable among the D collected data. may include.

Meanwhile, T (T ≥ 1) time series models related to the time series characteristics of processes or growth performed in the field are time series models that can match the time series characteristics of processes performed through devices installed in industrial or agricultural fields. It may include at least one time series model among time series models that can match time series characteristics related to the growth of crops grown in the field.

In addition, the N (1≤N≤D) time series data modeled to enable matching within the above allowable range is a time domain based on the time series characteristics of the collected data generated by time series sensing or time series shooting. Can include time series data based.

According to Figure 1, when N time series data is configured through the data configuration unit 105, the data confirmation unit 110 determines at least one process or growth performed in the field based on the N time series data. You can check t(1≤t≤T) time series models with periodicity that can be matched with the specified periodicity related to and n(1≤n≤N) time series data with periodicity that can be matched within the specified allowable range.

According to the method of carrying out the present invention, the periodicity is a periodicity corresponding to at least one process repeatedly performed at regular intervals through a device provided at an industrial or agricultural field, through a device provided at an industrial or agricultural field. A periodicity corresponding to a schedule associated with at least one process to be performed, a periodicity corresponding to a change in the daily interval (or the Earth's rotation interval), a periodicity corresponding to a change in a trend over a specified period, a periodicity corresponding to a seasonal change, a yearly interval ( or at least one periodicity corresponding to a change in the Earth's orbital interval).

Here, it is clear that the periodicity does not include periodicity related to simple vibration of the device sensed through a conventional vibration sensor and periodicity related to the frequency of electromagnetic waves sensed through an electromagnetic wave sensor.

According to the implementation method of the present invention, t (1≤t≤T) time series models with periodicities that can match the specified periodicity related to the at least one process or growth are the time series characteristics of the process or growth performed in the field. It can include a periodic time series model that includes multiple periodicities that match the periodic characteristics of the process performed, including a specified period, or the periodic characteristics of growth affected by a specified change (or trend), while including time series matched to the specified period. .

In addition, the n (1≤n≤N) time series data with the periodicity may include time series data with a specified periodicity related to at least one process or growth performed in the field and a periodicity matched within a specified tolerance range. there is.

In addition, the n time series data may include a periodicity time series model that can match a specified periodicity related to at least one process or growth performed in the field and time series data with a periodicity that matches within a specified allowable range.

Meanwhile, according to the implementation method of the present invention, the data confirmation unit 110 analyzes the N time series data based on at least one periodic time series model and can match at least one specified periodic time series model within a specified allowable range. You can check n time series data with periodicity.

In addition, according to the implementation method of the present invention, in the case of time series data where the data change due to time change is slower than a specified reference value, the data confirmation unit 110 applies a specified exponential smoothing method to the time series data and then performs at least one You can check n time series data with periodicity that can match the periodic time series model and within the specified tolerance range.

In addition, according to the implementation method of the present invention, the data confirmation unit 110 analyzes the N time series data based on at least one periodic time series model, and random elements or residuals included in the time series data (Residual/Remainder) By separating and analyzing the data corresponding to the element, it is possible to identify at least one periodicity time series model and n time series data with a periodicity that can be matched within the specified allowable range.

According to Figure 1, when n (1≤n≤N) time series data with the periodicity are confirmed through the data confirmation unit 110, the data processing unit 115 selects the confirmed n time series data. It can be processed into frequency domain-based time series data corresponding to specified frequency characteristics.

According to the implementation method of the present invention, the frequency feature may include a model-based period (or frequency) feature corresponding to a time series model with periodicity.

Additionally, according to the implementation method of the present invention, the frequency characteristic may include a data-based period (or frequency) confirmed by reading time series data with periodicity.

In addition, according to the implementation method of the present invention, the frequency feature is the characteristic of a model-based period (or frequency) corresponding to a time series model with periodicity and a data-based period (or frequency) confirmed by reading time series data with periodicity. The characteristics of may be statistically processed (e.g., average, correction, etc.) or numerical analysis process (e.g., average, correction, interpolation, etc.) may be performed to include the identified period (or frequency) characteristics.

Meanwhile, according to the implementation method of the present invention, the n time series data processed into the frequency domain are the periodic characteristics of the process performed including the specified cycle in the field or the periodic characteristics of growth affected by the specified change (or trend). It may include time series data processed into a frequency domain corresponding to periodicity matching the characteristics and frequency characteristics that can be matched within an allowable range.

Additionally, the n pieces of time series data processed into the frequency domain do not include time series data related to simple vibration of the device sensed through a vibration sensor or time series data related to the frequency of electromagnetic waves sensed through an electromagnetic wave sensor.

Here, time series data related to the simple vibration of the device sensed through the vibration sensor or time series data related to the frequency of electromagnetic waves sensed through the electromagnetic wave sensor are the periodic characteristics or specified changes of the process performed including the specified period at the site. It is not included in the n time series data processed into the frequency domain corresponding to the periodicity that matches the periodic characteristics of growth affected by (or trend) and the frequency characteristic that matches within the allowable range.

In addition, time series data related to the simple vibration of the device sensed through the vibration sensor or time series data related to the frequency of electromagnetic waves sensed through the electromagnetic wave sensor are the periodic characteristics or specified changes of the process performed including the specified cycle at the site. Identified as time series data corresponding to a separate frequency domain that is distinguished from n time series data processed into a frequency domain corresponding to a periodicity that matches the periodic characteristics of growth affected by (or trend) and a frequency characteristic that matches within an acceptable range. Or it can be managed.

According to Figure 1, when the time series data is processed into frequency domain-based time series data through the data processing unit 115, the artificial intelligence learning unit 120 performs a specified analysis among the n time series data processed into the frequency domain. However, it commonly includes n'(1≤n'≤n) time series data essential for prediction and i(1≤i) that can selectively affect the analysis or prediction among (N-n') time series data. G time series data included in G(G≥1) time series data groups that individually contain ≤(N-n')) time series data, each group containing (n'+i) time series data in a specified structure. Construct a plurality of learning data for each G time series data group, and classify M artificial intelligence modules equipped with M (M ≥ 2) different artificial intelligence algorithms using the plurality of learning data for each G time series data group. Each (M+G) number of artificial intelligence modules corresponding to G time series data groups can be learned.

According to the implementation method of the present invention, the n' time series data is a periodicity that matches the periodic characteristics of the process performed including the designated cycle in the field or the periodic characteristic of growth affected by the designated change (or trend). Among the n time series data processed into the frequency domain corresponding to frequency features that can be matched within the allowable range, at least one time series data essential for specified analysis or prediction may be included.

Meanwhile, the (N-n) pieces of time series data may include time domain-based time series data.

Additionally, according to the implementation method of the present invention, the (N-n) pieces of time series data may include (n-n') pieces of time series data processed into the frequency domain.

Meanwhile, according to the implementation method of the present invention, the artificial intelligence learning unit 120 converts (n'+i) time series data for each G time series data group into G artificial intelligence modules for each M artificial intelligence module classification. It can be preprocessed so that it can be used as learning data.

The preprocessing includes any or a combination of two or more of data purification, data conversion, data filtering, data integration, and data reduction for at least one time series data included in (n'+i) time series data for each of the G time series data groups. Can be performed at least once.

According to the implementation method of the present invention, the preprocessing includes changing the character or category attribute value of at least one time series data included in (n'+i) time series data for each of the G time series data groups into numeric data. A data change procedure, including at least one of the data scaling procedures for adjusting the range difference between each time series data included in the (n'+i) time series data for each of the G time series data groups to within a specified certain range. can do.

Here, the preprocessing is performed by equalizing the periodicity of at least one time series data included in the (n'+i) time series data for each of the G time series data groups to a certain time period in a specified time range, and k (k≥1) previous It may include a process for processing the data so that the result of the next data can be derived.

Meanwhile, according to the implementation method of the present invention, the preprocessing may include common preprocessing that is commonly applicable to time series data included in the learning data of the (M+G) artificial intelligence modules.

In addition, according to the implementation method of the present invention, the preprocessing may further include at least one individual preprocessing that can be individually applied to time series data included in the learning data of the (M+G) artificial intelligence modules.

Meanwhile, according to the implementation method of the present invention, the learning data is data corresponding to (n'+i) time series data for each of the G time series data groups as observed features or feature vectors for artificial intelligence learning. and may include j(i≥1) pieces of data corresponding to observation results or labels related to (n'+i) time series data for each of the G time series data groups.

Here, the learning data includes (M+G ) pieces of learning data, or G pieces composed of a structure that can be integrated and applied to the classification of M artificial intelligence modules designated for learning data including (n'+i) pieces of time series data for each of the G time series data groups. May include learning data.

Meanwhile, according to the implementation method of the present invention, the artificial intelligence module may include an LSTM (Long Short-Term Memory) series algorithm optimized for time series analysis.

According to Figure 1, the result information confirmation unit 125 selects (M+G) artificial intelligence modules corresponding to G time series data groups for each M artificial intelligence module classification through the artificial intelligence learning unit 120. After learning, among the n time series data collected and pre-processed through the process corresponding to the first to third steps and processed into the specified frequency domain, n' time series data essential for the specified analysis or prediction are commonly included. (n'+i) time series data for each G time series data group, which individually includes i time series data that can selectively affect the analysis or prediction, and G time series data for each of the learned M artificial intelligence module classifications. Each of the G time series data groups specified in the artificial intelligence module is individually substituted to check the result information for each (M+G) number of artificial intelligence modules for the specified analysis or prediction, and the result information for each (M+G) number of artificial intelligence modules is checked. You can check the actual measurement result information.

Here, the n' time series data is a periodicity that matches the periodic characteristics of the process performed including the designated cycle in the field or the periodic characteristics of growth affected by a designated change (or trend), and a frequency that can be matched within an acceptable range. Among n time series data processed into the frequency domain corresponding to the feature, at least one time series data essential for specified analysis or prediction may be included.

Meanwhile, according to the implementation method of the present invention, the result information confirmation unit 125 converts (n'+i) time series data for each of the G time series data groups into G artificial intelligence modules for each of the learned M artificial intelligence module classifications. Each time series data group specified in the intelligence module can be preprocessed to enable substitution.

Here, the preprocessing includes one or two of data purification, data conversion, data filtering, data integration, and data reduction for at least one time series data included in (n'+i) time series data for each of the G time series data groups. The above combination can be performed at least once.

In addition, the preprocessing includes a data change procedure for changing a character or category attribute value for at least one time series data included in (n'+i) time series data for each of the G time series data groups into numeric data, the G It may include at least one of the data scaling procedures for adjusting the range difference between each time series data included in (n'+i) time series data for each time series data group to within a specified range.

In addition, the preprocessing equalizes the periodicity of at least one time series data included in the (n'+i) time series data for each of the G time series data groups to a constant time period in a specified time range, so that the k (k≥1) previous It may include a processing procedure so that the result of the next data can be derived through the previous data.

In addition, the preprocessing may include common preprocessing that is commonly applicable to time series data to be applied to the designated (M+G) number of artificial intelligence modules.

In addition, the preprocessing may further include at least one individual preprocessing that can be individually applied to the time series data to be applied to the (M+G) number of artificial intelligence modules.

In addition, the result information confirmation unit 125 converts (n'+i) time series data for each of the G preprocessed time series data groups into time series data designated for the G artificial intelligence modules for each of the learned M artificial intelligence module classifications. You can check the result information for each (M+G) artificial intelligence module for the specified analysis or prediction by substituting each group.

Meanwhile, the result information for each of the (M+G) artificial intelligence modules is result information corresponding to artificial intelligence-based analysis or prediction using frequency domain-based time series data, and result information using multiple frequency domain-based time series data and time domain-based time series data. It may include result information corresponding to artificial intelligence-based analysis or prediction.

Here, the result information for each (M+G) number of artificial intelligence modules may not include result information corresponding to artificial intelligence-based analysis or prediction using only time domain-based time series data.

Meanwhile, according to the implementation method of the present invention, the result information confirmation unit 125 stores the result information for each of the (M+G) artificial intelligence modules in a designated storage medium, and a designated user terminal 140 related to the site. ) can provide result information for each of the above (M+G) artificial intelligence modules.

Here, the result information for each of the (M+G) artificial intelligence modules includes result information of analyzing the occurrence of an abnormality, result information of predicting the occurrence of an abnormality, result information of predicting the future state, and at least some of the processes performed at the site. It may include at least one result information among result information that feeds back control or adjustment.

According to the implementation method of the present invention, the result information confirmation unit 125 receives actual measurement result information corresponding to the result information for each of the (M+G) artificial intelligence modules from the user terminal 140 corresponding to the field. can do.

In addition, according to the implementation method of the present invention, the result information confirmation unit 125 generates/manages data corresponding to actual measurement result information corresponding to the result information for each (M+G) artificial intelligence module, or The data may be received from a server (not separately shown) that generates/manages data to be used to derive result information, and the actual measurement result information may be confirmed based on the received data.

In addition, according to the implementation method of the present invention, the result information confirmation unit 125 senses data corresponding to the actual measurement result information among sensors provided in the field or selects data to be used to derive the actual measurement result information. Sensing data sensed through a sensing sensor can be received, and the actual measurement result information can be confirmed based on the received sensing data.

According to Figure 1, when the evaluation information calculation unit 130 confirms the actual measurement result information for the (M+G) number of artificial intelligence modules through the result information confirmation unit 125, the Match, compare and analyze the confirmed actual measurement result information and the result information for each (M+G) artificial intelligence module to evaluate at least one of the accuracy, precision and recall rate for each (M+G) artificial intelligence module for the specified analysis or prediction. (M+G) pieces of evaluation information evaluated according to the rules can be calculated.

Here, the accuracy may include the ratio of accurately predicted actual 'true' and actual 'false', and the precision may include the ratio of actual 'true' among those predicted as 'true', , the recall rate may include the ratio of what is predicted to be ‘true’ among what is actually ‘true’.

In addition, the evaluation rule is a rule for scoring at least one of accuracy, precision, and recall for each (M+G) number of artificial intelligence modules, and at least one of accuracy, precision, and recall rate for each (M+G) number of artificial intelligence modules. It may include at least one of a rule for quantifying into a number within a specified range, and a rule for grading at least one of accuracy, precision, and recall for each (M+G) number of artificial intelligence modules.

In addition, the evaluation rule may further include a rule for assigning a predetermined weight related to the object to be analyzed or predicted through the artificial intelligence module to a designated item among accuracy, precision, and recall.

According to Figure 1, when the module determination unit 135 calculates (M+G) pieces of evaluation information evaluated according to the evaluation rule specified through the evaluation information calculation unit 130, the calculated (M+G) Based on ) evaluation information, at least one f(1≤f≤(M+G)) artificial intelligence module optimized for the specified analysis or prediction can be determined.

According to the implementation method of the present invention, the module determination unit 135 compares the (M+G) pieces of evaluation information and analyzes the artificial intelligence module corresponding to the highest evaluated (or highest ranked) evaluation information. Or, you can decide on any one of the f artificial intelligence modules optimized for prediction.

In addition, according to the implementation method of the present invention, the module determination unit 135 compares the (M+G) pieces of evaluation information and selects at least one artificial intelligence module corresponding to the evaluation information within the specified ranking through a designated analysis or The decision can be made with at least one f artificial intelligence module optimized for prediction.

Meanwhile, according to the implementation method of the present invention, the f artificial intelligence module includes the g (1≤g≤G) time series data group and the m (1≤m≤M) artificial intelligence module optimized for specified analysis or prediction. It may include at least one artificial intelligence module corresponding to a combination of classifications.

Here, the f artificial intelligence module is the g (1 ≤ g ≤ G) time series data group optimized for specified analysis or prediction among the M artificial intelligence module classifications corresponding to the G time series data groups and M artificial intelligence algorithms. It may include at least one artificial intelligence module corresponding to a combination of the mth (1≤m≤M) artificial intelligence module classification.

Meanwhile, when the f-th artificial intelligence module is determined, the result information confirmation unit 125 performs a specified analysis or prediction among the n time series data collected and preprocessed through the process of Figure 2 and then processed into a designated frequency domain. Designated analysis by substituting (n'+i) time series data, including the essential n' time series data and i time series data corresponding to the time series data group of the f artificial intelligence module, into the f artificial intelligence module. You can check the result information of the f artificial intelligence module for or prediction.

Here, the n' time series data is a periodicity that matches the periodic characteristics of the process performed including the designated cycle in the field or the periodic characteristics of growth affected by a designated change (or trend), and a frequency that can be matched within an acceptable range. Among n time series data processed into the frequency domain corresponding to the feature, at least one time series data required for specified analysis or prediction may be included.

In addition, the result information confirmation unit 125 converts (n'+i) time series data corresponding to the time series data group of the f artificial intelligence module into G artificial intelligence modules for each of the learned M artificial intelligence module classifications. Each group of time series data specified in can be preprocessed to enable substitution.

Here, the preprocessing includes data purification, data conversion, data filtering, and data integration for at least one time series data included in (n'+i) time series data corresponding to the time series data group of the f artificial intelligence module. It may include performing any one or a combination of two or more of data reduction at least once.

In addition, the preprocessing involves changing the character or category attribute value of at least one time series data included in (n'+i) time series data corresponding to the time series data group of the f artificial intelligence module into numeric data. Data change procedure, a data scaling procedure that adjusts the range difference between each time series data included in (n'+i) time series data corresponding to the time series data group of the f artificial intelligence module to within a specified range. It may contain at least one procedure.

In addition, the preprocessing equalizes the periodicity of at least one time series data in the (n'+i) time series data corresponding to the time series data group of the f artificial intelligence module to a certain time period in a specified time range to k (k ≥ 1) It may include a process for deriving the result of the next data through the previous data.

Meanwhile, the result information confirmation unit 125 substitutes the preprocessed (n'+i) time series data into the f artificial intelligence module to check the result information of the f artificial intelligence module for the specified analysis or prediction. You can.

Here, the result information of the f artificial intelligence module is result information corresponding to artificial intelligence-based analysis or prediction using frequency domain-based time series data, and artificial intelligence-based analysis using multiple frequency domain-based time series data and time domain-based time series data. It may also include result information corresponding to the prediction.

Additionally, the result information of the f artificial intelligence module may not include result information corresponding to artificial intelligence-based analysis or prediction using only time domain-based time series data.

The result information confirmation unit 125 may store the result information of the fth artificial intelligence module in a designated storage medium and provide the result information of the fth artificial intelligence module to a designated user terminal related to the site.

In addition, the result information of the f artificial intelligence module includes result information of analyzing the occurrence of an abnormality, result information of predicting the occurrence of an abnormality, result information of predicting the future state, and control or adjustment of at least some processes performed in the field. At least one result information may be included among the result information being fed back.

Figure 2 is a flowchart showing the process of processing time series data confirmed to have a periodicity that can match the specified periodicity related to process or growth into frequency domain-based time series data according to the implementation method of the present invention.

In more detail, Figure 2 constitutes time series data collected and modeled by the operation server 100 through sensors or cameras provided in industrial or agricultural fields, and includes at least one process or growth and This diagram shows the process of confirming time series data with a periodicity that can match the relevant specified periodicity and processing the time series data into frequency domain-based time series data. Those skilled in the art will understand this drawing. By referring to and/or modifying 2, various implementation methods for the above process (e.g., implementation methods in which some steps are omitted or the order is changed) may be inferred, but the present invention includes all implementation methods inferred above. The technical features are not limited to the implementation method shown in Figure 2.

Referring to Figure 2, the operation server 100 stores S sensing data sensed in time series through S (S ≥ 1) sensors provided in industrial or agricultural fields and C (C) provided in the field. Among C pieces of image data captured in time series through ≥1) cameras, designated D (1≤D≤(S+C)) pieces of collected data are collected (200).

Here, the preprocessing may include an averaging procedure to reveal periodic patterns or representativeness of a certain time interval of the D collected data with a specified periodicity.

In addition, the preprocessing may include a procedure for correcting the temporal influence corresponding to the bias weighted by data of the previous time with respect to the data corresponding to the designated independent variable among the D collected data.

When the D pieces of collected data are collected, the operation server 100 preprocesses the collected D pieces of data to create T (T≥1) time series models related to the time series of the process or growth performed in the field and within the allowable range. Construct N (1≤N≤D) time series data modeled to enable matching (205).

Here, the T time series models are a time series model that can match the time series characteristics of processes performed through devices installed in industrial or agricultural fields, and a time series that can match the time series characteristics related to the growth of crops grown in agricultural fields. At least one time series model may be included among the models.

Additionally, the N pieces of time series data may include time domain-based time series data based on the time series characteristics of collected data generated by time series sensing or time series photography.

When the N time series data are configured, the operation server 100 sets t (1 ≤ t Confirm ≤T) time series models and n (1≤n≤N) time series data with periodicity that can be matched within the specified allowable range (210).

Here, the periodicity corresponds to at least one process repeatedly performed at regular intervals through a device installed in an industrial or agricultural field, and at least one process to be performed through a device provided in an industrial or agricultural field. periodicity corresponding to a schedule related to a periodicity, a periodicity corresponding to a change in a daily interval (or the Earth's rotation interval), a periodicity corresponding to a change in a trend in a specified period, a periodicity corresponding to a seasonal change, and a periodicity corresponding to a yearly interval (or the Earth's rotation interval). It may include at least one periodicity among the periodicities corresponding to change.

In addition, the t time series models include time series characteristics matched with the time series characteristics of the process or growth performed in the field and do not affect the periodic characteristics or specified changes (or trends) of the process performed including the specified period. It is possible to include a periodic time series model that includes multiple periodicities that match the periodic characteristics of the receiving growth.

According to the implementation method of the present invention, the operation server 100 analyzes the N time series data based on at least one periodic time series model and n with a periodicity that can match at least one specified periodic time series model within a specified allowable range. You can check time series data.

In addition, according to the implementation method of the present invention, in the case of time series data in which the data change according to time is slower than a specified reference value, the operation server 100 applies a specified exponential smoothing method to the time series data and then generates at least one periodic time series. You can check n time series data with periodicity that can match the model and within the specified tolerance range.

When the n time series data are confirmed, the operation server 100 processes the confirmed n time series data into frequency domain-based time series data corresponding to the specified frequency characteristic (215).

Here, the frequency feature includes a feature of a model-based period (or frequency) corresponding to a time series model with periodicity, or a data-based period (or frequency) confirmed by reading time series data with periodicity, Or, the characteristics of the model-based cycle (or frequency) corresponding to a time series model with periodicity and the characteristics of the data-based cycle (or frequency) confirmed by reading the time series data with periodicity ( or frequency) characteristics.

In addition, the n time series data processed into the frequency domain have a periodicity and allowable range that match the periodic characteristics of the process performed in the field, including the designated cycle, or the periodic characteristics of growth affected by the designated change (or trend). It can include time series data processed into the frequency domain corresponding to the frequency features that can be matched.

Figure 3 shows (M+G) time series data for each G time series data group, which are essential for or can selectively affect a specified analysis or prediction according to the implementation method of the present invention, learned with M artificial intelligence algorithms. This is a flowchart showing the process of checking the result information for each (M+G) artificial intelligence module for the specified analysis or prediction by substituting it into the intelligence module.

In more detail, Figure 3 shows a plurality of learning methods for each time series data group that are necessary for a specified analysis or prediction and can selectively affect the time series data processed based on the frequency domain in the operation server 100 after the process of Figure 2. After constructing the data and using a plurality of learning data for each configured time series data group, (M+G) artificial intelligence modules corresponding to the series data group are trained for each classification of artificial intelligence modules with different artificial intelligence algorithms. , The process of checking the result information for each artificial intelligence module for the specified analysis or prediction by substituting time series data that is essential and can selectively affect the specified analysis or prediction into the learned plurality of artificial intelligence modules for each time series data group. As shown, those of ordinary skill in the art to which the present invention pertains can refer to and/or modify Figure 3 to determine various implementation methods for the above process (e.g., some steps are omitted or the order is changed). Implementation method) can be inferred, but the present invention includes all of the above-described implementation methods, and its technical features are not limited to only the implementation method shown in Figure 3.

Referring to Figure 3, the operation server 100 processes time series data into frequency domain-based time series data corresponding to a specified frequency characteristic through the process of Figure 2, and then processes n into the frequency domain. Among the time series data, n'(1≤n'≤n) time series data that are essential for the specified analysis or prediction are commonly included, and among the (N-n') time series data, the analysis or prediction can be selectively affected. G time series data included in G(G≥1) time series data groups that individually contain i(1≤i≤(N-n')) time series data (n'+i) time series data for each group is preprocessed so that it can be used as learning data of (M+G) artificial intelligence modules to which M (M≥2) different artificial intelligence algorithms are applied (300).

Here, the n' time series data is a periodicity that matches the periodic characteristics of the process performed including the designated cycle in the field or the periodic characteristics of growth affected by a designated change (or trend), and a frequency that can be matched within an acceptable range. Among n time series data processed into the frequency domain corresponding to the feature, at least one time series data essential for specified analysis or prediction may be included.

In addition, the preprocessing includes a data change procedure for changing a character or category attribute value for at least one time series data included in (n'+i) time series data for each of the G time series data groups into numeric data, the G It may include at least one of the data scaling procedures for adjusting the range difference between each time series data included in (n'+i) time series data for each time series data group to within a specified range.

In addition, the preprocessing equalizes the periodicity of at least one time series data included in the (n'+i) time series data for each of the G time series data groups to a constant time period in a specified time range, so that the k (k≥1) previous It may include a process for processing the data so that the result of the next data can be derived.

If (n'+i) time series data for each of the G time series data groups are preprocessed so that they can be used as learning data for (M+G) artificial intelligence modules to which the M (M≥2) different artificial intelligence algorithms are applied. , the operation server 100 configures a plurality of learning data for each G time series data group, including (n'+i) time series data for each of the preprocessed GG time series data groups in a designated structure (305).

Here, the learning data includes (n'+i) time series data for each of the G time series data groups as data corresponding to observation features or feature vectors for artificial intelligence learning, and the G time series It may include j(i≥1) data corresponding to observation results or labels related to (n'+i) time series data for each data group.

In addition, the learning data includes (M+G ) learning data may be included.

In addition, the learning data is G learning data composed of a structure that can be integrated and applied to the classification of M artificial intelligence modules designated for the learning data including (n'+i) time series data for each of the G time series data groups. may include.

When a plurality of learning data for each of the G time series data groups is configured, the operation server 100 operates M (M ≥ 2) different artificial intelligence algorithms using the plurality of learning data for each of the G time series data groups. For each M artificial intelligence module classification, (M+G) artificial intelligence modules corresponding to G time series data groups are learned (310).

Thereafter, the operation server 100 commonly includes n' time series data essential for the specified analysis or prediction among the n time series data collected and preprocessed through the process of Figure 2 and processed into the specified frequency domain. (n'+i) time series data for each G time series data group, which individually includes i time series data that can selectively affect analysis or prediction, and G artificial intelligence for each learned M artificial intelligence module classification. Each G time series data group specified in the intelligence module is individually substituted to check the result information for each (M+G) artificial intelligence module for the specified analysis or prediction (315).

Here, the result information for each of the (M+G) artificial intelligence modules is result information corresponding to artificial intelligence-based analysis or prediction using frequency domain-based time series data, and result information using multiple frequency domain-based time series data and time domain-based time series data. It may include result information corresponding to artificial intelligence-based analysis or prediction.

Thereafter, the operation server 100 stores the result information for each (M+G) number of artificial intelligence modules in a designated storage medium (320), and sends the (M+G) information to a designated user terminal 140 related to the site. Provides result information for each artificial intelligence module (325).

In addition, the result information for each of the (M+G) artificial intelligence modules includes result information of analyzing the occurrence of an abnormality, result information of predicting the occurrence of an abnormality, result information of predicting the future state, and at least some of the processes performed at the site. It may include at least one result information among result information that feeds back control or adjustment.

Figure 4 is optimized for specified analysis or prediction based on (M+G) evaluation information calculated by matching, comparing and analyzing actual measurement result information and (M+G) result information for each artificial intelligence module according to the implementation method of the present invention. This is a flowchart showing the process of determining the artificial intelligence module.

In more detail, Figure 4 shows that after the process of Figure 3, the operation server 100 checks the actual measurement result information for each (M+G) artificial intelligence module, and the confirmed actual measurement result information By matching and analyzing the result information for each (M+G) artificial intelligence module, at least one of the accuracy, precision, and recall rate for each (M+G) artificial intelligence module for the specified analysis or prediction was evaluated according to the specified evaluation rule ( At least one f(1≤f≤(M+G)) artificial intelligence module that calculates M+G) pieces of evaluation information and is optimized for analysis or prediction specified based on the calculated (M+G) pieces of evaluation information. This illustrates the process of determining , and those skilled in the art will refer to and/or modify Figure 4 to determine various implementation methods for the process (e.g., some steps may be omitted, Or an implementation method with a changed order) may be inferred, but the present invention includes all of the above inferred implementation methods, and its technical features are not limited to only the implementation method shown in Figure 4.

Referring to Figure 4, when the operation server 100 confirms the result information for each (M+G) artificial intelligence module for the analysis or prediction specified through the process of Figure 3, the user terminal 140 corresponding to the field ) receives actual measurement result information corresponding to the result information for each of the (M+G) artificial intelligence modules (400).

According to the implementation method of the present invention, the operation server 100 generates/manages data corresponding to actual measurement result information corresponding to the result information for each (M+G) artificial intelligence module or derives the actual measurement result information. The data can be received from a server that generates/manages data to be used.

In addition, according to the implementation method of the present invention, the operation server 100 is a sensor that senses data corresponding to the actual measurement result information among sensors provided in the field or senses data to be used to derive the actual measurement result information. You can receive sensing data sensed through .

When actual measurement result information corresponding to the result information for each (M+G) number of artificial intelligence modules is received, the operation server 100 confirms the actual measurement result information based on the received data (405).

When the actual measurement result information is confirmed, the operation server 100 matches, compares and analyzes the confirmed actual measurement result information and the result information for each (M+G) artificial intelligence module (410), and (410) for the specified analysis or prediction. (M+G) evaluation information is calculated by evaluating at least one of accuracy, precision, and recall for each M+G time series data group according to a specified evaluation rule (415).

Thereafter, the operation server 100 determines at least one f(1≤f≤(M+G)) artificial intelligence module optimized for the specified analysis or prediction based on the calculated (M+G) evaluation information. Do (420).

According to the implementation method of the present invention, the operation server 100 compares the (M+G) pieces of evaluation information and performs a designated analysis or prediction of an artificial intelligence module corresponding to the highest evaluated (or highest ranked) evaluation information. It can be decided on any one f artificial intelligence module optimized for .

In addition, according to the implementation method of the present invention, the operation server 100 compares the (M+G) pieces of evaluation information and uses at least one artificial intelligence module corresponding to the evaluation information within the specified ranking to perform the specified analysis or prediction. The decision can be made with at least one optimized artificial intelligence module.

According to the implementation method of the present invention, the f artificial intelligence module is a classification of the g (1≤g≤G) time series data group and the m (1≤m≤M) artificial intelligence module optimized for specified analysis or prediction. It may include at least one artificial intelligence module corresponding to the combination.

When the f-th artificial intelligence module is determined, the operation server 100 selects n' essential for the specified analysis or prediction among the n time series data collected and pre-processed through the process of Figure 2 and then processed into the specified frequency domain. (n'+i) time series data, including time series data and i time series data corresponding to the time series data group of the f artificial intelligence module, are substituted into the f artificial intelligence module to provide a solution for the specified analysis or prediction. f Check the result information of the artificial intelligence module (425).

In addition, the operation server 100 stores the result information of the fth artificial intelligence module in a designated storage medium and provides the result information of the fth artificial intelligence module to the designated user terminal 140 related to the site ( 430).

Here, the result information of the f artificial intelligence module includes result information of analyzing the occurrence of an abnormality, result information of predicting the occurrence of an abnormality, result information of predicting the future state, and control or adjustment of at least some processes performed in the field. At least one result information may be included among the result information being fed back.

100: Operation server 105: Data configuration unit
110: data confirmation unit 115: data opening unit
120: Artificial intelligence learning unit 125: Result information confirmation unit
130: Evaluation information calculation unit 135: Module decision unit
140: user terminal

Claims (27)

In the method executed through the operating server,
S sensing data sensed in time series through S (S ≥ 1) sensors installed in industrial or agricultural fields and captured in time series through C (C ≥ 1) cameras installed in the field. Among C image data, designated D (1≤D≤(S+C)) collected data are collected and preprocessed to create T(T≥1) time series models and allowable ranges related to the time series of the process or growth performed in the field. A first step of configuring N (1≤N≤D) time series data modeled to allow for my matching;
Based on the N time series data, t (1≤t≤T) time series models with a periodicity that can be matched with a specified periodicity related to at least one process or growth performed in the field and a periodicity that can be matched within a specified allowable range. A second step of checking n (1≤n≤N) time series data;
A third step of processing the confirmed n time series data into frequency domain-based time series data corresponding to specified frequency characteristics;
Among the n time series data processed into the frequency domain, n'(1≤n'≤n) time series data essential for the specified analysis or prediction are commonly included, and among the (N-n') time series data, the analysis or prediction is made. For each G time series data group (n Construct a plurality of learning data for each G time series data group containing '+i) time series data in a specified structure, and use the plurality of learning data for each G time series data group to obtain different M (M≥2) A fourth step of learning (M+G) artificial intelligence modules corresponding to G time series data groups for each classification of M artificial intelligence modules equipped with artificial intelligence algorithms;
After learning the (M+G) number of artificial intelligence modules, the n time series data collected and preprocessed through the process corresponding to the first to third steps and processed into the specified frequency domain are essential for the specified analysis or prediction. The learning is performed on (n'+i) time series data for each G time series data group, which includes the necessary n' time series data in common and individually includes i time series data that can selectively affect the analysis or prediction. A fifth step of confirming the result information for each (M+G) number of artificial intelligence modules for the specified analysis or prediction by substituting each group of G time series data specified in the G number of artificial intelligence modules for each classification of the M number of artificial intelligence modules;
A sixth step of checking actual measurement result information for the (M+G) number of artificial intelligence modules;
By matching and analyzing the confirmed actual measurement result information and the result information for each (M+G) number of artificial intelligence modules, at least one of the accuracy, precision, and recall rate for each (M+G) number of artificial intelligence modules for the specified analysis or prediction is determined. A seventh step of calculating (M+G) evaluation information evaluated according to evaluation rules; and
An eighth step of determining at least one f(1≤f≤(M+G)) artificial intelligence module optimized for the specified analysis or prediction based on the calculated (M+G) evaluation information. How to provide time series data and artificial intelligence modules optimized for analysis/prediction.
The method of claim 1, wherein the pretreatment is,
A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, comprising an averaging procedure to reveal the representativeness of periodic patterns or regular time intervals of the collected data with a specified periodicity among the D collected data.
The method of claim 1, wherein the pretreatment is,
Time series data optimized for analysis/prediction and artificial intelligence, comprising a procedure for correcting temporal effects corresponding to biases weighted by data from previous times with respect to data corresponding to designated independent variables among the D collected data. How to provide an intelligence module.
The method of claim 1, wherein the T time series models are:
A time series model that can match the time series characteristics of processes performed through devices installed in industrial or agricultural fields,
A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, comprising at least one time series model among time series models that can be matched with time series characteristics related to the growth of crops grown in agricultural fields.
The method of claim 1, wherein the N time series data are:
Provides time series data and artificial intelligence module optimized for analysis/prediction, characterized by including time series data based on the time domain based on the time series characteristics of collected data generated by time series sensing or time series shooting. method.
The method of claim 1, wherein the periodicity is:
Periodicity corresponding to at least one process that is repeatedly performed at regular intervals through a device installed in an industrial or agricultural field,
Periodicity corresponding to a schedule related to at least one process to be performed through a device provided in an industrial or agricultural field,
Periodicity, corresponding to changes in the daily interval (or Earth's rotation interval);
Periodicity, corresponding to changes in trends over a specified period of time;
periodicity in response to seasonal changes;
A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, characterized by including at least one periodicity among the periodicities corresponding to changes in one-year intervals (or Earth orbital intervals).
The method of claim 1, wherein the t time series models are:
Periodicity that matches the periodic characteristics of the process performed at the site or the time-series characteristics of growth, including a specified period, or growth that is affected by a specified change (or trend). A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, characterized by including a periodic time series model that includes multiple.
The method of claim 1, wherein the second step is:
Analysis comprising the step of analyzing the N time series data based on at least one periodicity time series model to identify n time series data with a periodicity that can be matched with at least one specified periodicity time series model and within a specified tolerance range. /How to provide time series data and artificial intelligence modules optimized for prediction.
The method of claim 1 or 8, wherein the second step is,
In the case of time series data where the data change over time is slower than a specified reference value,
Time series data optimized for analysis/prediction, comprising the step of applying a specified exponential smoothing method to the time series data and then identifying n time series data with a periodicity that can be matched with at least one periodicity time series model within a specified tolerance range. and how to provide artificial intelligence modules.
The method of claim 1 or 8, wherein the second step is,
Analyze the N time series data based on at least one periodic time series model, and separate and analyze data corresponding to random elements or residual/remainder elements included in the time series data to determine at least one periodic time series. A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, comprising the step of checking n time series data with periodicity that can be matched to the model and within a specified allowable range.
The method of claim 1, wherein the frequency characteristic is:
A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, characterized by including features of model-based period (or frequency) corresponding to a time series model with periodicity.
The method of claim 1, wherein the frequency characteristic is:
A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, characterized by including a data-based period (or frequency) confirmed by reading time series data with periodicity.
The method of claim 1, wherein the frequency characteristic is:
The characteristics of the model-based cycle (or frequency) corresponding to the time series model with periodicity and the characteristics of the data-based cycle (or frequency) identified by reading the time series data with periodicity are statistically processed or numerical analysis is performed to determine the cycle (or A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, characterized by including the characteristics of frequency.
The method of claim 1, wherein the n time series data processed into the frequency domain are:
A time series processed into the frequency domain corresponding to a frequency characteristic that can be matched within an acceptable range and a periodicity that matches the periodic characteristics of the process performed at the site, including the specified cycle, or the periodic characteristics of growth affected by the specified change (or trend). A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, characterized by including data.
The method of claim 1, wherein the n' time series data are:
n processed into a frequency domain corresponding to a frequency characteristic that can be matched within an acceptable range and a periodicity that matches the periodic characteristics of the process performed including the specified cycle in the field or the periodic characteristic of growth affected by a specified change (or trend) A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, comprising at least one time series data essential for specified analysis or prediction among the time series data.
The method of claim 1, wherein the fourth step is:
Analysis / characterized by further comprising the step of preprocessing (n'+i) time series data for each of the G time series data groups so that they can be used as learning data for G artificial intelligence modules for each M artificial intelligence module classification. How to provide time series data and artificial intelligence modules optimized for prediction.
The method of claim 16, wherein the pretreatment is,
A data change procedure for changing a character or category attribute value for at least one time series data included in (n'+i) time series data for each of the G time series data groups into numeric data,
Characterized by comprising at least one of the data scaling procedures for adjusting the range difference between each time series data included in the (n'+i) time series data for each of the G time series data groups to within a specified range. A method of providing time series data and artificial intelligence modules optimized for analysis/prediction.
The method of claim 16, wherein the pretreatment is,
The periodicity of at least one time series data included in the (n'+i) time series data for each of the G time series data groups is equalized to a certain time period in a specified time range, and the next data is generated through k (k≥1) previous data. A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, characterized by including a process for processing the result so that the result can be derived.
The method of claim 16, wherein the pretreatment is,
A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, comprising common preprocessing commonly applicable to time series data included in the learning data of the (M+G) artificial intelligence modules.
The method of claim 19, wherein the pretreatment is,
A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, further comprising at least one individual preprocessing that can be individually applied to time series data included in the learning data of the (M+G) artificial intelligence modules. .
The method of claim 1, wherein the learning data is:
Includes (n'+i) time series data for each of the G time series data groups as data corresponding to observation features or feature vectors for artificial intelligence learning,
Analysis/prediction, characterized in that it includes j (i≥1) data corresponding to an observation result or label related to the specified time series data among (n'+i) time series data for each of the G time series data groups. A method of providing optimized time series data and artificial intelligence modules.
The method of claim 21, wherein the learning data is:
Containing (M+G) learning data composed of optimized structures for each of the M artificial intelligence module classifications specified for the learning data including (n'+i) time series data for each of the G time series data groups. A method of providing time series data and artificial intelligence modules optimized for analysis/prediction.
The method of claim 21, wherein the learning data is:
Characterized in that it includes G learning data composed of a structure that can be integrated and applied to the M artificial intelligence module classifications specified for the learning data including (n'+i) time series data for each of the G time series data groups. How to provide time series data and artificial intelligence modules optimized for analysis/prediction.
The method of claim 1, wherein the fifth step is:
Further comprising the step of preprocessing (n'+i) time series data for each of the G time series data groups so that each time series data group assigned to the G artificial intelligence modules for each of the learned M artificial intelligence module classifications can be individually assigned. A method of providing time series data and artificial intelligence modules optimized for analysis/prediction.
According to claim 1, the result information for each of the (M+G) artificial intelligence modules is:
Result information corresponding to artificial intelligence-based analysis or prediction using frequency domain-based time series data,
A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, which includes result information corresponding to artificial intelligence-based analysis or prediction using multiple frequency domain-based time series data and time domain-based time series data.
The method of claim 1, wherein the f artificial intelligence module is:
Characterized by comprising at least one artificial intelligence module corresponding to a combination of the g (1 ≤ g ≤ G) time series data group and the m (1 ≤ m ≤ M) artificial intelligence module classification optimized for specified analysis or prediction. A method of providing time series data and artificial intelligence modules optimized for analysis/prediction.
According to clause 1,
After determining the f artificial intelligence module,
Among the n time series data collected and preprocessed through the process corresponding to the first to third steps and then processed into the designated frequency domain, the n' time series data essential for the specified analysis or prediction and the f artificial intelligence module A system that checks the result information of the f artificial intelligence module for a specified analysis or prediction by substituting (n'+i) time series data, including i time series data corresponding to the time series data group, into the f artificial intelligence module. A method of providing time series data and artificial intelligence modules optimized for analysis/prediction, characterized by further including 9 steps.