KR102494034B1 - Method and apparatus for providing automatic of work manual - Google Patents

Abstract

The present invention relates to a method, device, and system for standardizing and automating corporate business manuals. An electronic device comprises a memory and a processor, wherein the processor may receive a user input and extract index words within the user input, determine whether a corresponding product or technology field corresponds to Korean standards or international standards, receive standard requirements from an external electronic device, store the received standard requirements and the user input in the memory, provide an interface for modifying a corresponding template that a user wishes to automate, create a customized script for a task that the user wishes to automate and store the customized script in the memory, design a performance model for improving a corresponding process, and recommend, as the corresponding process, a process having a score exceeding a specified level among a plurality of candidate processes, and intuitively providing an interface, which allows customized modifications to a selected template, and modifications. According to the present invention, it is possible to build a new classification model or improve the performance of an existing classification model.

Description

Enterprise work manual standardization automation method, device and system {METHOD AND APPARATUS FOR PROVIDING AUTOMATIC OF WORK MANUAL}

The present invention relates to the field of machine learning technology, and more particularly, to a method and apparatus for providing a business automation service in response to customer needs.

IS certification is a standard established to facilitate the exchange of materials or services between countries and to promote international cooperation in the fields of intellectual, scientific, technological, and economic activities, and may mean an internationally recognized standard. KS certification can be used to verify whether a company has the ability and conditions to continuously produce products that comply with KS standards for items regulated by KS.

Therefore, for this certification, users must check standards and certification targets, understand and confirm certification review criteria, introduce in-house standardization and quality management techniques, secure training and quality management personnel, manufacturing facilities, testing, inspection facilities, and samples. It may be necessary to secure and secure management performance for more than 3 months.

In general, among office workers' working hours, the time required for document preparation occupies a high proportion of the total work. Reduction of costs due to the time and manpower required to prepare these documents is an essential part in terms of corporate productivity. To this end, a system for integrating and automating work is being introduced [Korean Patent Registration No. 10-0968487].

However, companies in various industries that exist in Korea have different types of companies and may need a system tailored to their needs. However, the system that supports the preparation of examination documents for certification in response to individual products of each company has a problem in that the cost increases as the development period increases, and due to this cost aspect, it is difficult to supply to the current market. .

In order to solve this problem, a technology for constructing a business management system tailored to suit the business process handled by each company has been proposed [Korean Patent Registration No. 10-1782534]. The prior art is also divided into business classifications such as accounting, finance, taxation, accounting, etc., and classification details such as purchase and sales proof within accounting business, accounting settlement, etc., and the business process is defined and automated for each detailed business. However, the prior art defines and automates work processes for each detailed task based on a method that can be certified for KS certification or international standard certification in addition to standardized tasks, and provides the necessary documents to obtain KS certification or IS certification. There is a limitation that cannot disclose the method.

Korean Patent Registration Publication No. 10-1671889 is a Korean Standard Industrial Classification for extracting information of companies matching a standard industrial classification code to check for duplication in related industries in reporting and registering trademark rights of manufactured goods. Extracting code information. (The 3rd company information extraction module, the 5th company information extraction module) In this process, only the already classified standard industry classification code itself is used. It does not perform classification with its own methodology or presents a new method for classification.

Korean Patent Registration No. 10-0968487 (2010.07.07.) Korean Patent Registration No. 10-1782534 (2017.09.27.) Republic of Korea Patent Registration No. 10-1671889 (2016.10.27)

For KS authentication, the user can use the KS authentication support system. The KS certification support system has the following problems. First, users' accessibility is very low because web compatibility is impossible. Second, there is a high possibility of security problems related to international standard technical documents due to individual settings of security patches or security levels in PCs of users. Third, as a download-type program, frequent errors occur, which causes difficulties for users. Fourth, due to the lack of standardized forms and preparation guidelines, a considerable amount of time is consumed in preparing forms. Fourth, in the case of individual users, it is a reality that they are highly dependent on expensive consulting companies due to difficulties in writing technical document review requests.

One object of the present invention is to apply a machine learning-based classification model to a rule base-based classification method and an index word search method using frequency/inverse frequency features, which were applied to the conventional Korean standard industrial/occupational automatic coding system of the National Statistical Office, and natural language Improve accuracy and performance by replacing text inference methods based on sentence similarity through processing technology, provide users with the necessary requirements for standard screening beyond simple industry classification, and document customized processes based on user input. .

The electronic device includes a memory and a processor, and the processor receives a user input including information on a product or technology field, extracts an index word from the user input using a learning model, and uses the extracted index word. to determine whether the corresponding product or technology field corresponds to Korean standards or international standards, receive standard requirements from an external electronic device based on whether the corresponding product or technology field corresponds to either Korean standards or international standards, Stores the received standard requirements and the user input in the memory, provides an interface for modifying the corresponding template to a task that the user wants to automate according to a selection input on the template, and provides a user input input on the interface Based on the modified and edited contents, a customized script for the task to be automated by the user is created, stored in the memory, and the components of each pre-generated template are divided to create mutually compatible scripts from a number of other templates for similar tasks. A performance model for the improvement of the corresponding process is designed by finding related components, and performance scores are calculated for a plurality of candidate processes inferred based on the performance model, and a process having a score exceeding a specified level is identified as the corresponding process. It is recommended as a process, and an interface capable of customizing a template selected from among the recommended templates and modifications may be intuitively provided. The template includes a basic configuration form and design form of a work process having sequence elements for automating a specific work area, and a script code generated therefrom, and the learning model receives information from a user and enters an application domain. Pre-processing of specialized raw corpus, learning syllable (letter) patterns frequently combined and used in given corpus to automatically learn the boundaries of compound words and individual names, and based on unsupervised learning by utilizing the frequency of occurrence of frequently repeated partial words. An index word is extracted, information on the index word extracted from the memory or database is retrieved, the searched information is transmitted to the processor, and a word and sentence embedding model for short sentence classification is again generated using the index word extracted from the user input. can learn

An electronic device according to an embodiment may be combined with hardware and controlled by a computer program stored in a medium to execute any one of the methods described above.

According to exemplary embodiments of the present invention, the present invention provides as a source technology of a method to compensate for the disadvantages and limitations of the conventional industry/occupation classification system. With the recent development of machine learning technology, it is possible to reduce the effort to build a system in many areas such as preprocessing or quality engineering. As it provides various classification information providing services such as classification, expenditure classification by destination, and special/general/international classification, there is a high possibility of service development through the application and application of the present invention.

The present invention not only simply classifies industry/occupation based on user input, but also provides the user with requirements for standard screening and can document a customized process based on user input.

The present invention applies a corresponding supervised learning-based classification model to minimize complicated preprocessing or knowledge building work and builds a classification model with existing classification result data, thereby improving the construction of a new classification model or the performance of an existing classification model. can be improved

1 is an exemplary diagram of a configuration of an electronic device according to an embodiment.
2 is a diagram for explaining a customer management program executed on an electronic device according to an exemplary embodiment.
3 is a diagram for explaining a customer management program executed on an electronic device according to an exemplary embodiment.
4 is a diagram showing the configuration of an artificial intelligence model according to an embodiment.
5 is a flowchart illustrating a method of providing a task automation service of an electronic device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be modified and implemented in various forms. Therefore, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

1 is an exemplary diagram of a configuration of an electronic device according to an embodiment.

An electronic device 101 according to an embodiment includes a processor 120 and a memory 130 . The electronic device 101 according to an embodiment may be a server or a terminal. According to an embodiment, the processor 120 is a component capable of performing calculations or data processing related to control and/or communication of each component of the electronic device 101, and may include one or more processors. The memory 130 may store information related to the above-described method or a program in which the above-described method is implemented. Memory 130 may be volatile memory or non-volatile memory.

According to one embodiment, the processor 120 may execute a program and control the device 101 . Program codes executed by the processor 120 may be stored in the memory 130 . Operations of the processor 120 may be performed by loading instructions stored in the memory 130 . The electronic device 101 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data.

According to an embodiment, there will be no limitations on calculation and data processing functions that the processor 120 can implement on the electronic device, but hereinafter, a data processing function for providing a method of providing a business automation service in response to customer needs will be described. It will be.

In one embodiment, the processor 120 receives a user input including information on any one of product or technology fields, extracts an index word from the user input using a learning model (not shown), and extracts the extracted index word. Determines whether the corresponding product or technology field corresponds to Korean standard or international standard by using, and receives standard requirements from external electronic devices based on whether the corresponding product or technology field corresponds to either Korean standard or international standard. can do. The processor 120 may store the received standard requirements and the user input in the memory 130, and provide an interface for modifying the corresponding template to a task the user wants to automate according to a selection input on the template. . The processor 120 may create a customized script for a task that the user wants to automate based on the user's correction and editing contents input on the interface, and store it in the memory 130 . The processor 120 divides the components of each pre-generated template, finds components that are correlated with each other from a plurality of other templates for similar tasks, designs a performance model for improvement of the corresponding process, and based on the performance model Performance scores are calculated for a plurality of inferred candidate processes, and a process having a score exceeding a specified level may be recommended as the corresponding process. The processor 120 may intuitively provide an interface capable of customizing a template selected from among the recommended templates and modifications.

In one embodiment, the template may include a basic construction form and design form of a work process having sequence elements for automating a specific work area, and script codes generated therefrom.

In one embodiment, a learning model (not shown) receives information from a user, preprocesses a raw corpus specific to an application domain, and learns syllable (letter) patterns frequently combined and used in a given corpus to determine the boundary between compound words and object names. Automatic learning, extracting an index word based on unsupervised learning by utilizing the frequency of occurrence of frequently repeated partial words, searching for information on the index word extracted in the memory or database, and transmitting the retrieved information to the processor , word and sentence embedding models for short sentence classification can be learned again using index words extracted from user input.

In one embodiment, the processor 120 extracts a first sequence element of a pre-created template, stores it in correspondence with the template, and extracts a second sequence element from an action input for a task to be automated through a user terminal. It determines the similarity with the stored template, recommends a preset number of templates according to the order of high similarity, and intuitively provides an interface and modifications that can be customized for the template selected from the recommended templates. there is. The processor 120 divides the components of each pre-generated template, finds components that are correlated with each other from a plurality of other templates for similar tasks, designs a performance model for improvement of the corresponding process, and based on the performance model A performance score may be calculated for a plurality of inferred candidate processes, and a process having the highest score may be recommended as the corresponding process. The processor 120 extracts the name and type of a module in a textual manner based on user input, and selectively extracts a value corresponding to an input value from a dependency list database to generate a new task management program. .

In one embodiment, the processor 120 may receive the customized script corresponding to the product or technology field from the memory 130 based on receiving a new user input regarding whether the product or technology field passes standard certification. there is. The processor 120 assigns a score exceeding a specified level to the corresponding customized script based on whether the product or technical field standard certification has passed, and based on the failure of the standard certification of the product or technical field, the user It is possible to request input of information on an element that caused a failure in the customized script, and give the customized script a score lower than a specified level.

When the processor 120 receives another user input corresponding to the same or similar product or technology field, if the score of the customized script corresponding to the product or technology field exceeds a certain level, the customized script is provided to the user as it is, and the customized script is provided to the user as it is. If the score of the script is less than a certain level, the element causing the failure in the customized script may be modified and provided, or information instructing the user to modify may be displayed and provided together.

In one embodiment, the requirements of the standard include tasks that representatives of the body that is the subject of the standard must perform, tasks that the body that is the subject of the standard must monitor, definitions of emergencies for the body that is the subject of the standard, It may include at least one of emergency response and measures, requirements to be met by organizations subject to standards, safety rules, security rules, and health hygiene rules of organizations subject to standards.

In one embodiment, the security rules are network robustness, service continuity and identification authentication, access control, transmission and storage data that must provide essential services such as command, control, reporting, and monitoring even when abnormal or excessive amounts of communication data flow in. It may include providing security functions to secure security such as protection.

In one embodiment, responses and measures for emergencies may be classified according to disasters and response processes according to user levels, and may be provided to users in an order assigned within each category according to situations input in case of disaster.

In one embodiment, the requirements to be met by the organization subject to the standard are self-determination and self-declaration, conformity confirmation by stakeholders in the organization such as customers, self-declaration by external parties of the organization, and safety and health management by external organizations. May include system authentication and registration.

2 is a diagram for explaining a customer management program executed on an electronic device according to an exemplary embodiment.

An electronic device (eg, the electronic device 101 of FIG. 1 ) may execute the customer management program 200 . The customer management program 200 may provide a task automation service in response to customer needs. The customer management program 200 may include items for inputting product information 210 and information on possession certification 220 .

In one embodiment, the product information 210 may include an item for at least one of a product type, a product type, and a product price. A processor (eg, the processor 120 of FIG. 1 ) may store information corresponding to the product information 210 in a memory (eg, the memory 130 of FIG. 1 ) based on a user input.

In one embodiment, the held certification 220 may include at least one item of a review certification review, standard name, standard number, certification details, certification authority, acquisition date, effective date, or certification period. The processor 120 may store information corresponding to the holding certification 220 in the memory 130 based on the user input.

In one embodiment, the processor 120 may extract an index word based on information input on the product information 210 . An index word may refer to a product or product included in the Korean standard (KS) or the international standard (IS). The processor 120 may determine whether a corresponding product or technical field corresponds to a Korean standard or an international standard by using the extracted index word.

The processor 120 may receive a standard requirement from an external electronic device based on whether a corresponding product or technology field corresponds to either a Korean standard or an international standard. The external electronic device may include, for example, an application server. The processor 120 may provide information about standard requirements received from an external electronic device to a user. Standard requirements include, for example, the tasks that representatives of the body that is the subject of the standard must perform, the tasks that the body that is the subject of the standard must monitor, the definition of emergencies in the body that is the subject of the standard, the emergency It may include at least one of response and measures for situations, requirements to be met by organizations subject to standards, safety rules, security rules, and health hygiene rules of organizations subject to standards.

In one embodiment, the security rules are network robustness, service continuity and identification authentication, access control, transmission and storage data that must provide essential services such as command, control, reporting, and monitoring even when abnormal or excessive amounts of communication data flow in. It may include providing security functions to secure security such as protection.

In one embodiment, responses and measures for emergencies may be classified according to disasters and response processes according to user levels, and may be provided to users in an order assigned within each category according to situations input in case of disaster.

In one embodiment, the requirements to be met by the organization subject to the standard are self-determination and self-declaration, conformity confirmation by stakeholders in the organization such as customers, self-declaration by external parties of the organization, and safety and health management by external organizations. May include system authentication and registration.

3 is a diagram for explaining a customer management program executed on an electronic device according to an exemplary embodiment.

An electronic device (eg, the electronic device 101 of FIG. 1 ) may execute the customer management program 300 . The customer management program 300 may provide a task automation service corresponding to customer needs. The customer management program 300 may include items capable of inputting data for contract information 310 , authentication information 320 , and consulting information 330 .

In one embodiment, the contract information 310 may include items related to at least one of a certification type, examination category, contract information, contract date, contract end date, or review plan.

In one embodiment, the certification information 320 may include at least one item of an examination certification name, standard name, standard number, certification authority, acquisition date, effective date, or certification due date.

In one embodiment, the consulting information 330 may include items about any one of a screening date, judges, results, a satisfaction survey, a review completion report, down payment, or review writing.

A processor (eg, the processor 120 of FIG. 1 ) may provide a standard document suitable for a user based on a user input on the customer management program 300 . A standard document suitable for the user may contain specific processes that the user must implement or manage.

4 is a diagram showing the configuration of an artificial intelligence model according to an embodiment.

An artificial intelligence model according to an embodiment may include an input layer, a hidden layer, and an output layer.

An input layer is a layer related to input values input to an artificial intelligence model. Information input from a user may be input to the input layer, for example. Information input from the user may include information in any one of product or technology fields. The learning model can extract index words from user input using a hidden layer and an output layer.

In the hidden layer, a feature map may be output by performing a multiply-accumulate (MAC) operation and an activation operation on an input value.

The MAC operation may be an operation of multiplying an input value by a corresponding weight and summing the multiplied values.

The activation operation may be an operation of inputting a result of the MAC operation to an activation function and outputting a resultant value. Activation functions can be of various types. For example, the activation function may include, but is not limited to, a sigmoid function, a tangent function, a relu function, a ricky relu function, a maxout function, and/or an elu function.

The hidden layer may consist of at least one layer. For example, when the hidden layer is composed of a first hidden layer and a second hidden layer, the first hidden layer outputs a feature map by performing a MAC operation and an activation operation based on the input value of the input system, and A feature map, which is a result value of the layer, may be an input value of the second hidden layer. The second hidden layer may perform a MAC operation and an activation operation based on the feature map resulting from the first hidden layer. In the hidden layer, the original corpus specialized for the application domain is preprocessed, and the frequently combined and used syllable (letter) patterns in the given corpus can be learned to automatically learn the boundaries of compound words and entity names.

An output layer may be a layer related to a result value of an operation performed in a hidden layer. The learning model extracts an index word based on unsupervised learning by using the frequency of occurrence of frequently repeated partial words using an output layer, searches information on the index word extracted from the memory or database, and sends the retrieved information to the processor. can be sent to The learning model may learn a word and sentence embedding model for short sentence classification again using the index word extracted from the user input.

In one embodiment, the learning model automatically learns the boundaries of compound words and object names by learning syllable (letter) patterns that are frequently combined and used in a given corpus, and object information of the first UI source and object information rendered by the browser Integrating to create an object information file for learning, generating learning data for learning a deep learning network using the object information file for learning, receiving data from various domains of the support system, and corresponding to each of the various domains Based on at least one standardization method, standardizes the data of the various domains in an integrated format, learns and infers data of a specific domain, determines information to be transmitted for the standardization in the data of the specific domain, Post processing may be performed on data from the various domains. The first UI source includes an XML file, and the object information file for learning includes an input JSON file for learning features and an output JSON file that is label data during learning, and the output JSON file is a web standard. and the various domains include at least one of RAN (radio access network), transport, or core, and the post-processing is (correlation) function can be included.

5 is a flowchart illustrating a method of providing a task automation service of an electronic device according to an embodiment.

Operations described with reference to FIG. 5 may be implemented based on instructions that may be stored in a computer recording medium or memory (eg, the memory 130 of FIG. 1 ). The illustrated method may be executed by the electronic device (eg, the electronic device 101 of FIG. 1 ) previously described with reference to FIGS. 1 to 4 , and technical features described above will be omitted below. The order of each operation in FIG. 5 may be changed, some operations may be omitted, or some operations may be performed simultaneously.

In operation 510, a processor (eg, the processor 120 of FIG. 1 ) may receive a user input including information on any one of product or technology fields, and extract an index word from the user input using a learning model. there is.

In operation 520, the processor 120 may use the extracted index word to determine whether a corresponding product or technical field corresponds to a Korean standard or an international standard.

In operation 530, the processor 120 may receive standard requirements from an external electronic device based on whether a corresponding product or technology field corresponds to either a Korean standard or an international standard.

At operation 540, processor 120 may store the received standard requirements and the user input in memory 130.

In operation 550, the processor 120 may provide an interface for modifying the corresponding template to a task that the user wants to automate according to a selection input on the template.

In operation 560, the processor 120 may create a customized script for a task to be automated by the user based on the user's correction and editing contents input on the interface, and store it in the memory 130.

In operation 570, the processor 120 divides the components of each pre-generated template, finds components that are correlated with each other from a plurality of other templates for similar tasks, and designs a performance model for improvement of the corresponding process. .

In operation 580, the processor 120 calculates performance scores for a plurality of candidate processes inferred based on the performance model, recommends a process having a score exceeding a specified level as the corresponding process, and selects the recommended templates. It can intuitively provide an interface and modifications that can be customized for the selected template.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (3)

In electronic devices,
memory; and
contains a processor;
The processor
Product information including items on at least one of product type, product form, or product amount, and items on at least one of the following: product information, standard name, standard number, certification details, certification authority, acquisition date, effective date, or certification deadline Receives user input for holding certification including, and extracts an index word meaning a word that refers to a product or product included in the Korean Standard (KS) or International Standard (IS) within the user input using a learning model. do,
Using the extracted index words, determine whether the corresponding product or technology field corresponds to Korean standards or international standards,
Receive standard requirements from external electronic devices based on whether the corresponding product or technology field corresponds to either Korean standards or international standards,
storing the received standard requirements and the user input on the memory;
According to the selection input on the template, an interface for modifying the corresponding template to a task that the user wants to automate is provided,
Based on the user's correction and editing contents input on the interface, a customized script for the task to be automated by the user is created and stored in the memory;
The template includes a basic configuration form and design form of a work process having sequence elements for automating a specific work area, and script codes generated therefrom,
Receiving the customized script corresponding to the product or technology field from the memory based on receiving a new user input regarding whether the product or technology field passed standard certification;
Giving a score exceeding a specified level to the corresponding customized script based on the passing of the standard certification in the product or technical field;
Based on the failure of the standard certification of the product or technical field, requesting the user to input information on the element that caused the failure in the custom script, and giving the custom script a score below a specified level,
When receiving another user input corresponding to the same or similar product or technology field, if the score of the customized script corresponding to the product or technology field exceeds a certain level, the customized script is provided to the user as it is,
If the score of the customized script is below a certain level, the element that caused the failure in the customized script is modified and provided, or information instructing the user to modify is displayed and provided together,
The learning model is
An input layer that receives an input value input to the artificial intelligence model;
A hidden layer that performs an operation of multiplying input values and corresponding weights and summing the multiplied values; And
Including an output layer that outputs the result value of the operation performed in the hidden layer,
Receives information from the user through the input layer, preprocesses the original corpus specific to the application domain using the hidden layer, and learns syllable (letter) patterns frequently combined and used in the given corpus to automatically delineate compound words and object names. learn with,
Using the output layer, an index word is extracted based on unsupervised learning by utilizing the frequency of occurrence of frequently repeated partial words, and information on the index word extracted from the memory or database is retrieved, and the retrieved information is transmitted to the processor. and
Using the index word extracted from the user input, learning for short sentence classification is performed again,
Automatically learns the boundaries of compound words and object names by learning syllable (letter) patterns that are frequently combined and used in a given corpus,
Creating an object information file for learning by integrating object information of the first UI source and object information rendered in the browser;
Creating learning data for learning using the learning object information file,
receive data from the various domains of the support system;
Based on at least one standardization method corresponding to each of the various domains, standardizing the data of the various domains in an integrated format;
Learning and inferring data of a specific domain, determining information to be delivered for the standardization in the data of the specific domain,
performing post processing on data from the various domains;
The first UI source is
Include an XML file,
The learning object information file is
It includes an input JSON file for learning features and an output JSON file that is label data during learning,
The output JSON file is
Includes a file containing HTML DOM Tree information implemented in compliance with web standards
The various domains include at least one of a radio access network (RAN), a transport, or a core,
The post-processing includes a correlation function,
The above standard requirements are
Tasks to be performed by representatives of organizations subject to standards, tasks to be monitored by organizations subject to standards, definitions of emergencies in organizations subject to standards, responses and actions to the above-mentioned emergencies, standards It includes at least one of the requirements to be met by organizations subject to standards, safety rules, security rules, and health and sanitation rules of organizations subject to standards,
The security rule
Network robustness, service continuity and identification authentication, access control, transmission and storage data protection that must provide essential services, including at least one of command, control, reporting or monitoring, even when abnormal or excessive amounts of communication data flow in. Including the provision of security functions to ensure security, including
Responses and actions for the above emergencies are
It is divided by disaster and response process according to user level, and is provided to users in the order given within each category according to the input situation in case of disaster.
The requirements to be met by organizations subject to the above standards are
Electronic devices, including self-determination and self-declaration, confirmation of conformity by stakeholders within the organization, such as customers, self-declaration by parties external to the organization, and certification and registration of OH&S management systems by external organizations.
According to claim 1,
The processor
A first sequence element of a pre-created template is extracted and stored corresponding to the template, and a second sequence element is extracted from an action input for a task to be automated through a user terminal to determine similarity with a pre-stored template. recommends a preset number of templates in the order of high, and intuitively provides an interface and modifications that can be customized for a template selected from among the recommended templates;
An electronic device that creates a new task management program by extracting a module name and type in a textual way based on a user input and selectively extracting a value corresponding to an input value from a dependency list database.



delete

Images