KR102398085B1 - Method, device and system for automatic processing and creating company information based on artificial intelligence - Google Patents

Abstract

According to one embodiment, a method of automatically processing and generating enterprise information on the basis of artificial intelligence is performed by a control server and includes the steps of: extracting characteristic information of a first query by analyzing a usage pattern of the first query for a predetermined reference period on the basis of log data stored in a database; predicting a task category of the first query on the basis of an output of the artificial neural network by applying characteristic information of the first query to an artificial neural network; checking a task processing period set in a first category if a prediction result for the task category of the first query is identified as the first category; and if business processing through the first query is not requested during the task processing period, transmitting a task processing request through the first query to a first customer server, which is one of a plurality of customer servers, and making a control to generate corporate information.

Description

Method, device and system for automatic processing and creation of company information based on artificial intelligence {METHOD, DEVICE AND SYSTEM FOR AUTOMATIC PROCESSING AND CREATING COMPANY INFORMATION BASED ON ARTIFICIAL INTELLIGENCE}

The following embodiments relate to technology for automatically processing and generating corporate information based on artificial intelligence.

When directly changing information stored in a database, there is a problem in that it is difficult to identify a subject who extracts and edits information from the database, and there is a problem in that related log data cannot be obtained.

The existing DB access control solution has a problem of high construction cost because a proxy server must be provided for each server accessing the database.

Therefore, in order to solve the above problems, research on a method for recording and storing log data of a database is required.

In addition, research on a method for processing company information using log data is also required.

Korean Patent Registration No. 10-2037480 Korean Patent No. 10-1927578 Korean Patent No. 10-1671889 Korean Patent Registration No. 10-1241037

According to an embodiment, based on the log data stored in the database, the usage pattern of the first query is analyzed for a preset reference period, characteristic information of the first query is extracted, and the characteristic information of the first query is applied to the artificial neural network. By applying, based on the output of the artificial neural network, the business category of the first query is predicted, and when the prediction result for the business category of the first query is confirmed as the first category, the business processing period set in the first category is Check, and if the business processing through the first query is not requested during the business processing period, the business processing request through the first query is transmitted to the first customer server, which is one of the plurality of customer server servers, and the company An object of the present invention is to provide a method, apparatus, and system for automatically processing and generating company information based on artificial intelligence, which controls information to be generated.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned will be clearly understood from the description below.

According to an embodiment, in a method for automatically processing and generating company information based on artificial intelligence, performed by a control server, based on log data stored in a database, a usage pattern of a first query for a preset reference period analyzing and extracting characteristic information of the first query; predicting a business category of the first query by applying the characteristic information of the first query to an artificial neural network and based on an output of the artificial neural network; when the prediction result for the business category of the first query is confirmed as the first category, checking a business processing period set in the first category; And if the business processing through the first query is not requested during the business processing period, the business processing request through the first query is transmitted to the first customer server, which is one of the plurality of customer server servers, to the first query There is provided a method for automatically processing and generating company information based on artificial intelligence, including the step of controlling the company information to be generated by the company.

The artificial intelligence-based company information automatic processing and generation method, after the step of confirming the business processing period, if the business processing through the first query is not requested until the day before the last day of the business processing period, the log data based on the step of confirming that the company information has been generated by the first query transmitted from the first user terminal; checking the team to which the first user belongs in the company through the first user account logged into the first user terminal; and when the first user belongs to the first team and the first user and the second user form the first team, a notification message for requesting business processing through the first query is sent to the first The method may further include transmitting to the user terminal and the second user terminal.

The artificial intelligence-based company information automatic processing and generation method, after confirming the business processing period, in a state in which business processing through the first query is not requested during the business processing period, from a third user terminal 1 when a business process through a query is requested, through a third user account logged into the third user terminal, confirming a team to which the third user belongs in the company; when it is confirmed that the third user belongs to the second team, checking a business processing field set in the second team; when it is confirmed that the first category is included in the work processing field of the second team, controlling the company information to be generated by the first query; and when it is confirmed that the first category is not included in the work processing field of the second team, controlling so that the company information is not generated by the first query.

According to an embodiment, based on the log data stored in the database, the usage pattern of the first query is analyzed for a preset reference period, characteristic information of the first query is extracted, and the characteristic information of the first query is applied to the artificial neural network. By applying, based on the output of the artificial neural network, the business category of the first query is predicted, and when the prediction result for the business category of the first query is confirmed as the first category, the business processing period set in the first category is Check, and if the business processing through the first query is not requested during the business processing period, the business processing request through the first query is transmitted to the first customer server, which is one of the plurality of customer server servers, and the company By controlling the information to be generated, there is an effect that company information can be automatically processed using log data.

On the other hand, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those of ordinary skill in the art from the following description.

1 is a diagram schematically showing the configuration of a system according to an embodiment.
2 is a flowchart illustrating a process of managing and processing log data of a corporate server according to an exemplary embodiment.
3 is a diagram for explaining a process of decoding a packet and storing a result of parsing according to an embodiment.
4 is a diagram for explaining a process of capturing and storing a packet according to an embodiment.
5 is a flowchart illustrating a process of distributing work according to the number of jobs according to an exemplary embodiment.
6 is a flowchart illustrating a process of automatically processing and generating company information based on artificial intelligence according to an embodiment.
7 is a flowchart illustrating a process of transmitting a notification message for requesting a business process to a business processing person in charge according to an exemplary embodiment.
8 is a flowchart illustrating a process of processing a task through confirmation of a person in charge according to an embodiment.
9 is a diagram for explaining learning of an artificial neural network according to an embodiment.
10 is an exemplary diagram of a configuration of a control server according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes may 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 modifications, equivalents and substitutes for the embodiments are included in the scope of the rights.

Specific structural or functional descriptions of the embodiments are disclosed for purposes of illustration only, and may be changed and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosure 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 elements, these terms should be interpreted only for the purpose of distinguishing one element from another. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected or connected to the other component, but it should be understood that another component may exist in between.

The terms used in the examples are used for the purpose of description only, and should not be construed as limiting. The singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate that a feature, number, step, operation, component, part, or a combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one 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 should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present application. does not

In addition, in the description with reference to the accompanying drawings, the same components are given the same reference numerals regardless of the reference numerals, and the overlapping description 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 thereof 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 cars, kiosks, wearable devices, and the like.

1 is a diagram schematically showing the configuration of a system according to an embodiment.

Referring to FIG. 1 , a system according to an embodiment may include a plurality of customer servers 100 , cloud storage 200 , a control server 300 , a plurality of servers 400 , and a database 500 .

The plurality of customer server 100 may include a first customer server 110 , a second customer server 120 , and the like.

The plurality of customer server 100 may be implemented as a plurality of corporate servers used by one customer, and the plurality of servers may be classified for each field of business work to be processed. For example, the first customer server 110 may be a corporate server that processes accounting-related tasks, and the second customer server 120 may be a corporate server that processes personnel-related tasks, and may be provided in various forms according to the characteristics of the customer. can be implemented.

A log bot is installed in each of the plurality of customer server 100 . That is, the first log bot 111 is installed in the first customer server 110 , and the second log bot 121 is installed in the second customer server 120 .

Each of the plurality of customer server 100 includes a database. That is, the first customer server 110 includes the database 112 , and the second customer server 120 includes the database 122 .

The multiple log bot is a bot that manages logs of the customer server database. It accesses the customer server database through a database access control solution (database access tool, program, etc.) and monitors the process of changing the information stored in the database. When information is changed, log data can be created and recorded. Here, the log data may include information about a query used to change information, an IP address that requested information change, and the like.

For example, when the first customer server 110 and the first user terminal are connected, and a database access program is installed in the first user terminal, the database 112 by the first query transmitted from the first user terminal ) is changed, the first log bot 111 may generate and record log data for the database change based on the first query and the IP address of the first user terminal.

According to an embodiment, the database log server may be configured to include a cloud storage 200 , a control server 300 , a plurality of servers 400 , and a database 500 .

The cloud storage 200 may be implemented as an object storage built to store and retrieve a desired amount of data anywhere. The cloud storage 200 may provide a Simple Storage Service (S3), and S3 may refer to an object storage service that provides industry-leading scalability, data availability, security, and performance. This means that customers of all sizes and industries can use this service to acquire as much data as they want across a variety of use cases such as data lakes, websites, mobile applications, backup and restore, archives, enterprise applications, IoT devices, and big data analytics. can be stored and protected. S3 provides easy-to-use management features so you can organize your data and configure fine-grained access controls according to your specific business, organizational and compliance requirements.

The control server 300 may be a self-server owned by a person or organization that provides services using the control server 300, may be a cloud server, and may be peer-to-peer (p2p) of distributed nodes. It may be a set. The control server 300 may be configured to perform all or part of an arithmetic function, a storage/referencing function, an input/output function, and a control function of a typical computer.

The control server 300 controls the operation of each of the plurality of log bots, the cloud storage 200, the plurality of servers 400 and the database 500 installed in the plurality of customer servers 100, thereby controlling the overall operation of the system. can do.

The plurality of servers 400 is a plurality of servers constituting an auto scaling group, and may include a first server 410 , a second server 420 , and the like.

An auto-scaling policy may be set in the plurality of servers 400 through auto-scaling. The auto-scaling policy is connected to the Auto Scaling Group, which is a bundle of servers, so that the number of servers is kept to a minimum when the service is idle, and the number of servers is increased to the maximum when a load occurs to implement a stable and flexible service. A detailed description related thereto will be described later with reference to FIG. 5 .

The database 500 is a database for storing log data and may perform a database function of a database log server.

According to an embodiment, the control server 300 may control the company information to be generated using log data stored in the database 500 . Here, the corporate information is information necessary for corporate activities, and may include information related to finance, human resources, purchase, and the like.

2 is a flowchart illustrating a process of managing and processing log data of a corporate server according to an exemplary embodiment.

Referring to FIG. 2 , first, in step S201 , a plurality of log bots installed in the plurality of customer server 100 can extract log data for each of the plurality of customer server 100 under the control of the control server 300 . there is. Here, the log data may include information on queries and IP addresses.

That is, the control server 300 may process log data to be extracted for each of the plurality of customer server 100 through a plurality of log bots installed in each of the plurality of customer server 100 .

For example, the first log bot 111 installed in the first customer server 110 extracts log data generated in the first customer server 110 by changing information stored in the database 112, and the second customer server The second log bot 121 installed in 120 may extract log data generated by the second customer server 120 by changing information stored in the database 122 .

The first log bot 111 and the second log bot 121 may be operated under the control of the control server 300, and log data can be extracted whenever log data is newly recorded due to a change in information stored in the database. Alternatively, log data may be collectively extracted every preset period.

In step S202 , the plurality of log bots installed in the plurality of customer servers 100 may copy the extracted log data into packets under the control of the control server 300 .

That is, the control server 300 may process the extracted log data to be copied into packets through a plurality of log bots installed in each of the plurality of customer server 100 .

For example, the first log bot 111 installed in the first customer server 110 copies log data extracted from the first customer server 110 into packets, and the second log bot 111 installed in the second customer server 120 The log bot 121 may replicate log data extracted from the second customer server 120 into packets.

The first log bot 111 and the second log bot 121 may be operated under the control of the control server 300, and whenever log data is extracted, the extracted log data may be copied into packets, and Log data extracted in batches can be copied in packets every set period.

In step S203 , the plurality of log bots installed in the plurality of customer servers 100 may transmit the replicated log data to the control server 300 .

Specifically, a plurality of log bots installed in a plurality of customer server 100 may deliver replicated log data to the cloud storage 200 , and when the replicated log data is delivered from the plurality of log bots to the cloud storage 200 , , the delivered log data may be stored in the cloud storage 200 . Thereafter, the control server 300 may acquire log data stored in the cloud storage 200 .

In step S204 , when the replicated log data is delivered, the control server 300 may process decryption of the delivered log data in parallel. In this case, the control server 300 may parallelly process the decryption of the obtained log data through an auto scaling group connected to the control server 300 .

For example, if the Auto Scaling Group consists of 5 servers and the number of tasks to be processed to decrypt log data is 10,000, the control server 300 performs 2,000 tasks to be processed. By distributing the distributed work to five servers for processing, decryption of log data can be processed in parallel through a plurality of servers 400 .

In step S205 , the control server 300 may control the operations of the plurality of servers 400 and the database 500 to store the decrypted log data in the database 500 connected to the control server 300 .

For example, when decryption of log data is processed in parallel through the first server 410 and the second server 420 , the control server 300 may 2 The log data decrypted through the server 420 may be combined and processed to be stored in the database 500 .

That is, as described above, when a packet of log data is copied and transmitted to the control server 300 , the control server 300 may obtain the transmitted log data and extract a query therefrom. In this case, the control server 300 may control the decryption required for extracting the query to be distributed through the plurality of servers 400 to distribute the decryption and process the decryption in parallel.

3 is a diagram for explaining a process of decoding a packet and storing a result of parsing according to an embodiment.

Referring to FIG. 3 , first, in step S301 , the control server 300 may obtain a file list of log data to be processed among log data files stored in the cloud storage 200 . That is, it is possible to obtain a list of files to be processed among the files stored in the cloud storage 200 .

For example, when files for the first log data, the second log data, and the third log data are stored in the cloud storage 200 , the control server 300 controls the first log data, the second log data, and the third log data. 3 It is possible to obtain a file list including log data.

The control server 300 may obtain a file list of log data that needs to process all log data files stored in the cloud storage 200, and log data that only needs to process log data files stored within a preset period. It can also be obtained as a file list of

When it is confirmed that the storage capacity of the cloud storage 200 remains below the reference capacity, the control server 300 may obtain a file list of log data to be processed from the cloud storage 200, A file list of log data to be processed may be obtained from the storage 200 .

In step S302, the control server 300 may generate a list of tasks to be processed using the obtained file list. That is, the control server 300 may generate a list of tasks to be processed through the plurality of servers 400 .

For example, if 10,000 log data is included in the file list, the control server 300 needs to decrypt 10,000 log data, so a list of 10,000 days corresponding to 10,000 log data can be generated. can

In step S303 , the control server 300 distributes tasks included in the list of created tasks, and transmits processing requests for the distributed tasks to the plurality of servers 400 constituting the auto scaling group, respectively. In this case, the instance of the auto scaling group may request a list of tasks to be processed from the control server 300 . A list of files to be processed and a key file required for decrypting the files are stored in the list of tasks, so the control server 300 distributes the list of files to be processed and the key file to be transmitted to the plurality of servers 400 . can

For example, when a list of jobs numbered from 1 to 6,000 is generated, the control server 300 distributes jobs from 1 to 2,000 as the first job, and assigns jobs from 2001 to 4,000. You can divide it into 2 jobs, and you can divide the jobs 4,001 through 6,000 into 3 jobs. Thereafter, the control server 300 transmits a processing request for the first job to the first server 410 , transmits a processing request for the second job to the second server 420 , and processes the third job The request may be sent to a third server.

In step S304, the control server 300 processes such that the log data file and key file necessary for processing the distributed work are transmitted from the cloud storage 200 to the plurality of servers 400, respectively, and the plurality of servers 400 Based on the log data file and key file delivered to , it is possible to process log data decryption and packet analysis in progress. That is, the instance of the auto scaling group downloads the file specified in the list and the key file required for processing from the cloud storage 200 , and the plurality of servers 400 may perform decryption and packet analysis. In this case, packet analysis can be performed using Tshark, which is the Terminal version of Wireshark.

For example, tasks 1 through 2,000 are distributed as a first task, tasks 2001 through 4,000 are distributed as a second task, tasks 4001 through 6,000 are distributed as a third task, and so on, When the processing for the first job is requested to the first server 410, the processing for the second job is requested to the second server 420, and the processing for the third job is requested to the third server, the first The server 410 obtains log data files and key files from Nos. 1 to 2,000 from the cloud storage 200 to process the first task, and decrypts and packets for log data from Nos. 1 to 2,000. In order to proceed with the analysis, the second server 420 acquires log data and key files from 2001 to 4,000 from the cloud storage 200 to process the second job, and from 2001 to 4,000 log Decryption and packet analysis of the data are performed, and the third server obtains log data and key files from 4,001 to 6,000 from the cloud storage 200 to process the third task, and from 4,001 to 6,000 Decryption and packet analysis of log data up to .

In step S305, the control server 300 may store the analysis result extracted through the decryption and packet analysis of the log data in the database 500 when the log data is decoded and the packet analysis is performed through the plurality of servers 400. there is. That is, the analysis result may be stored in the database 500 .

In step S306 , the control server 300 may check the processed file through the analysis result stored in the database 500 , and process the processed file to be deleted from the cloud storage 200 . That is, the processed file may be deleted from the cloud storage 200 .

For example, when decryption and packet analysis of log data from Nos. 1 to 6,000 are completed, and the analysis results for log data from Nos. 1 to 6,000 are stored in the database 500, the cloud storage 200 The log data files from No. 1 to No. 6,000 stored in .

4 is a diagram for explaining a process of capturing and storing a packet according to an embodiment.

Referring to FIG. 4 , first, in step S401 , the access program installed in the external terminal connected to the first customer server 110 , which is any one of the plurality of customer server 100 , is the access program installed in the database of the first customer server 110 . A DB change request may be transmitted to (112). In other words, various access programs such as ERP, Toad program, and DB Log Manager can send requests to the customer server.

In step S402, when the access program transmits a DB change request to the first customer server 110, the control server 300 through the first log bot 111 installed in the first customer server 110, the first By filtering only the change requests sent to the port, log data can be captured as packets and saved to a file. In other words, when various access programs such as ERP, Toad program, DB Log Manager, etc. send a request to the customer server, the DB log bot watches all packets coming to the customer server in a sniffing method and uses the database dedicated communication port (e.g. For example, you can filter and store only requests coming to 3306). At this time, the DB log bot can capture and store packets by using Gopacket, and can store the captured packets in the form of a pcap file by 10,000.

In step S403 , the control server 300 may process log data captured as packets and stored as files to be transferred from the first log bot 111 to the cloud storage 200 . That is, the pcap file stored by the DB log bot may be transmitted to the cloud storage 200 .

According to one embodiment, the database 112 of the first customer server 110 must set the protocol according to the method used in the DB Log in advance for the security protocol (TLS) to be used in the communication process with the outside.

Since the DB log requires an external decryption process using the private key of the database server, an encryption protocol using the Diffie-Hellman key exchange method cannot be used.

The Diffie-Hellman method is a method that cannot be decrypted from the outside because the key is dynamically generated during the communication process. Therefore, a process of setting only Cipher Suites to be used except for the method containing “ECDHE” or “DHE” is required.

5 is a flowchart illustrating a process of distributing work according to the number of jobs according to an exemplary embodiment.

Referring to FIG. 5 , first, in step S501 , when a list of work is generated, the control server 300 may check a first quantity that is the number of days included in the list of work.

For example, when a list of days numbered from 1 to 6,000 is generated, the control server 300 may check 6,000 as the first quantity.

In step S502 , the control server 300 may determine whether the first quantity is smaller than the first reference value. Here, the first reference value may be set differently according to embodiments.

If it is confirmed in step S502 that the first quantity is smaller than the first reference value, in step S503, the control server 300 sends a processing request for a job included in the list of jobs to the first one of the plurality of servers 400 may be transmitted to the server 410 .

For example, when the first quantity is 1,500 and the first reference value is set to 2,000, the control server 300 does not distribute a list of tasks and sends a processing request for 1,500 days to the first server 410 . can be sent to

If it is determined in step S502 that the first quantity is greater than the first reference value, in operation S504 , the control server 300 may determine whether the first quantity is less than the second reference value. Here, the second reference value may be set to a value greater than the first reference value.

If it is confirmed in step S504 that the first quantity is smaller than the second reference value, in step S505, the control server 300 may distribute the work included in the list of work to the list 1-1 and the list 1-2. .

For example, when the first quantity is 3,000 pieces, the first reference value is 2,000 pieces, and the second reference value is set to 4,000 pieces, the control server 300 distributes tasks 1 to 1,500 in the first-first list And, you can distribute tasks 1,501 to 3,000 in the list 1-2.

In step S506, the control server 300 transmits a processing request for the work included in the 1-1 list to the first server 410, and transmits the processing request for the work included in the 1-2 list to the second may be transmitted to the server 420 .

On the other hand, if it is confirmed in step S504 that the first quantity is greater than the second reference value, in step S507, the control server 300 selects the tasks included in the list of tasks 2-1, 2-2, and the second list. -3 can be distributed in a list.

For example, if the first quantity is 4,500, the first reference value is 2,000 pieces, and the second reference value is set to 4,000 pieces, the control server 300 distributes tasks 1 to 1,500 in the 2-1 list And, the tasks 1,501 to 3,000 can be distributed in the 2-2 list, and the tasks 3,001 to 4,500 can be distributed in the 2-3 list.

In step S508, the control server 300 transmits a processing request for the work included in the 2-1 list to the first server 410, and transmits the processing request for the job included in the 2-2 list to the second It may be transmitted to the server 420, and a request for processing the work included in the 2-3 list may be transmitted to the third server.

As described above, the larger the number of jobs, the more jobs can be distributed to more servers. Through this, the number of servers that can be processed is increased to provide stable and flexible services while keeping the number of servers that can be processed to a minimum. can provide

6 is a flowchart illustrating a process of automatically processing and generating company information based on artificial intelligence according to an embodiment.

Referring to FIG. 6 , first, in step S601 , the control server 300 may analyze a usage pattern of the first query during a reference period based on log data stored in the database 500 . Here, the reference period may be set differently according to embodiments. Here, the log data includes information about a query used when information is changed, an IP address that requested information change, and information about a time when the information is changed for each item. Through this, the control server 300 may analyze the usage pattern of the first query by identifying how often and at what point in time the first query is used based on the log data.

For example, the first customer server 110 is a corporate server that processes accounting-related tasks, the first customer server 110 and the first user terminal are connected, and a database access program is installed in the first user terminal. If there is, when company information is generated in the database 112 by the first query transmitted from the first user terminal, the first log bot 111 generates the first query, the IP address of the first user terminal, and company information Based on time, it is possible to create and record log data for changes in the database 112 . In this case, the query may be classified for each category of the corporate business, and when the first query is a query used in the accounting business, the corporate information may be accounting information extracted through the first query.

That is, when information is extracted from the database 112 through the first query, the first log bot 111 may generate company information using the extracted information, and the generated company information is stored in the database 112 . Also, log data for database changes may be created and recorded due to the generation of company information. Thereafter, when the log data is stored in the database 500, the control server 300 determines that the first query is used based on the log data stored in the database 500, 1), the usage pattern of the first query can be analyzed.

In step S602 , the control server 300 may extract characteristic information of the first query by using the analysis result of the usage pattern of the first query. Here, the characteristic information of the first query may include information indicating in which period the first query is regularly used.

For example, when the control server 300 analyzes the usage pattern of the first query and analyzes that the first query is used from the 1st to the 3rd of every month, it is used at the beginning of every month, and the characteristics of the first query information can be extracted.

In step S603, the control server 300 may apply the characteristic information of the first query to the artificial neural network. Here, the artificial neural network may be an algorithm that receives the characteristic information of a query and then predicts and outputs the business category of the query. The artificial neural network may be learned through a method described later with reference to FIG. 9 .

In step S604 , the control server 300 may predict the business category of the first query based on the output of the artificial neural network. Here, the business category may be divided according to the business of the company, for example, may be divided into accounting, human resources, finance, and the like.

According to an embodiment, the artificial neural network may be trained to predict the business category of the query through characteristic information of the query. Through this, the artificial neural network may predict and output the business category of the query in consideration of the characteristics of the query.

In step S605 , the control server 300 may check the prediction result for the business category of the first query as the first category. Here, the first category is a business category of a company, and may be any one of business categories such as accounting, human resources, and finance.

For example, after the artificial neural network receives the characteristic information of the first query, if the characteristic of the first query (period in which the first query is frequently used) is analyzed as suitable for the first category, the business category suitable for the first query may predict and output the first category, and the control server 300 may check the prediction result for the business category of the first query as the first category through the output of the artificial neural network.

In step S606 , when the prediction result for the business category of the first query is confirmed as the first category, the control server 300 may check the business processing period set in the first category.

For example, in the Accounting category, the processing period is set from 1 to 5 days, in the Human Resources category, the business processing period is set from 11 to 15 days, and in the Finance category, the processing period is set from 21 days. If set to 25 days, the control server 300 checks the business processing period of the first category as 1 to 5 days when the first category is the accounting category, and when the first category is the personnel category, The business processing period of the first category may be identified as 11 to 15 days, and when the first category is the financial category, the business processing period of the first category may be confirmed as 21 to 25 days.

In step S607 , the control server 300 may check whether the business processing through the first query is requested during the business processing period of the first category.

Specifically, the log data stored in the database 500 may be updated every preset period, and the control server 300 performs a first query based on the log data whenever the log data stored in the database 500 is updated. By checking whether it is used, it is possible to check whether the business processing through the first query is requested during the business processing period of the first category.

If it is confirmed in step S607 that the business processing through the first query is requested during the business processing period of the first category, in step S609, the control server 300 responds to the first query according to the business processing request through the first query You can control the creation of company information by In this case, the first log bot 111 may extract information from the database 112 through the first query as a business processing request through the first query, and generate company information using the extracted information.

For example, when a business processing request through the first query is received from the first user terminal during the business processing period of the first category, the control server 300 responds to the first query according to the business processing request through the first query. The operation of the first log bot 111 may be controlled so that the company information is generated by the user.

If, in step S607, the business processing through the first query is not requested during the business processing period of the first category and it is confirmed that the business processing period of the first category has passed, in step S608, the control server 300 performs the first query through The business processing request may be transmitted to the first customer company server 110 .

After step S608, in step S609, the control server 300 may control the company information to be generated by the first query according to the business processing request through the first query. That is, the control server 300 transmits a business processing request through the first query to the first customer server 110 and controls the operation of the first log bot 111 so that company information is generated by the first query. can do.

7 is a flowchart illustrating a process of transmitting a notification message for requesting a job processing to a person in charge of processing the job according to an exemplary embodiment.

Referring to Figure 7, first, in step S701, the control server 300, if the business processing through the first query is not requested until the day before the last day of the first category business processing period, the log stored in the database 500 Based on the data, it may be confirmed that the company information has been generated by the first query transmitted from the first user terminal.

For example, if the business processing period of the first category is from 1 to 5 days, if business processing through the first query is not requested by the 4th of this month, the control server 300 stores the log stored in the database 500 Based on the data, it may be confirmed that the company information has been generated by the first query transmitted from the first user terminal. That is, the control server 300 may determine from which user terminal the first query is transmitted in order to find a user who has previously requested business processing through the first query.

In step S702, if the control server 300 confirms that the company information has been generated by the first query transmitted from the first user terminal, it checks the first user account logged in the first user terminal, Through the 1 user account, the first user may check the team to which the company belongs. At this time, the first user account registers the first user's identity, job title, and information on the team to which the first user belongs, and the control server 300 uses the first user account to register the first user's team. can confirm.

In step S703 , the control server 300 may identify the team to which the first user belongs as the first team through the first user account. Here, the team may be divided into categories of corporate work, for example, a first team may be divided into an accounting team, a second team may be divided into a human resources team, and a third team may be divided into a finance team, and the like.

In step S704 , the control server 300 may identify the first user and the second user constituting the first team. That is, when the first user and the second user are registered as team members of the first team, the control server 300 may identify the first user and the second user constituting the first team.

In step S705 , when the first user belongs to the first team and the first user and the second user form the first team, the control server 300 provides a notification for requesting business processing through the first query. The message may be transmitted to the first user terminal and the second user terminal. Here, the notification message is a message for informing that the task through the first query has not yet been processed this month, and may include information on the processing period of the first category of the task.

8 is a flowchart illustrating a process of processing a task through confirmation of a person in charge according to an embodiment.

Referring to Figure 8, first, in step S801, the control server 300 through the first query from the third user terminal in a state in which the business processing through the first query is not requested during the business processing period of the first category You can check that the work processing has been requested.

Specifically, in a state in which business processing through the first query is not requested during the business processing period of the first category, the third user terminal may transmit a business processing request through the first query to the first customer server 110, , the control server 300 may confirm that the business processing through the first query is requested from the third user terminal through the first log bot 111 .

In step S802, the control server 300 logs in to the third user terminal when the business processing through the first query is requested from the third user terminal while the business processing through the first query is not requested during the business processing period The established third user account may be checked, and a team to which the third user belongs in the company may be identified through the third user account. At this time, the third user's identity, title, and information on the team to which the third user belongs are registered in the third user account, and the control server 300 operates the third user's team through the third user account. can confirm.

In step S803 , the control server 300 may identify the team to which the first user belongs as the second team through the third user account.

In step S804, the control server 300 may check the business processing field set in the second team. That is, the team may be divided by category of corporate work, and a work processing field is set for each team. For example, if the first team is divided into an accounting team, the second team is a human resources team, and the third team is a finance team, the business processing field of the first team is set as the first category, and the business processing of the second team The field may be set as the second category, and the work processing field of the third team may be set as the third category.

In step S805 , the control server 300 may check whether the first category is included in the task processing field of the second team.

If it is confirmed in step S805 that the first category is included in the business processing field of the second team, in step S806, the control server 300 generates company information by the first query requested through the third user terminal. can be controlled

For example, if the business processing field of the second team is set to the first category and the second category, the control server 300 confirms that the first category is included in the business processing field of the second team, The operation of the first log bot 111 may be controlled so that company information is generated by the first query requested through the third user terminal. In this case, when the company information is generated by the first query requested through the third user terminal, the control server 300 may transmit a notification message informing that the business processing through the first query is completed to the third user terminal. .

If it is confirmed in step S805 that the first category is not included in the business processing field of the second team, in step S807, the control server 300 generates company information by the first query requested through the third user terminal You can control it not to happen.

For example, when the business processing field of the second team is set as the second category, the control server 300 checks that the first category is not included in the business processing field of the second team, and the third user The operation of the first log bot 111 may be controlled so that company information is not generated by the first query requested through the terminal. At this time, if the company information is not generated by the first query requested through the third user terminal, the control server 300 may transmit a notification message to the third user terminal informing that confirmation of the person in charge for the first query is required. there is.

9 is a diagram for explaining learning of an artificial neural network according to an embodiment.

According to an embodiment, the artificial neural network may be an algorithm for predicting and outputting a business category of a query after receiving characteristic information of a query. The control server 300 in which the artificial neural network is learned may be the same device as the control server 300 for predicting the business category of a query using the learned artificial neural network, or it may be a separate device. Hereinafter, a process in which an artificial neural network is trained will be described.

First, in step S901, the control server 300 may generate an input based on the characteristic information of the query.

Specifically, the control server 300 may perform pre-processing on the characteristic information of the query. The preprocessed characteristic information may still be used as an input to the artificial neural network, or the input may be generated through a normal process of removing unnecessary information.

In step S902, the control server 300 may apply an input to the artificial neural network. The artificial neural network may be an artificial neural network trained according to reinforcement learning. The artificial neural network may be a Q-Network, DQN (Depp Q-Network), or relational network (RL) structure suitable for outputting abstract reasoning through reinforcement learning.

An artificial neural network trained according to reinforcement learning can be updated and optimized by reflecting the evaluation in various rewards. For example, the first reward may have a higher reward value when a task category suitable for a specific query is accurately predicted, and the second reward may have a higher reward value when queries having similar characteristics are predicted in the same task category.

In step S903, the control server 300 may obtain an output from the artificial neural network. The output of the artificial neural network may be a result of predicting a business category suitable for a query through characteristic information of the query. In this case, the artificial neural network may predict and output a category suitable for the query by analyzing in which period the query is regularly used and in which period the query is mainly used based on the characteristics of the query.

In step S904, the control server 300 may evaluate the output of the artificial neural network and pay a reward. In this case, the evaluation of the output may be divided into a first compensation, a second compensation, and the like.

Specifically, the control server 300 may award a large amount of the first reward when accurately predicting a work category suitable for a specific query, and may award a large amount of the second reward when queries having similar characteristics are predicted as the same work category.

In step S905, the control server 300 may update the artificial neural network based on the evaluation.

Specifically, the control server 300 sets a specific state so that the expected value of the sum of rewards is maximized in an environment in which the artificial neural network predicts a work category suitable for the query through the characteristic information of the query. The artificial neural network can be updated through the process of optimizing the policy that determines the actions to be taken in the states.

For example, if there is a problem in classifying the first query into the first category, the control server 300 uses information indicating that there is a problem in classifying the first query into the first category, 1 Generate training data, apply the first training data to the artificial neural network, and update the artificial neural network through the process of training the artificial neural network so that queries having characteristics similar to the first query are not classified into the first category. can

In addition, if there is no problem in classifying the first query into the first category, the control server 300 uses information indicating that there is no problem in classifying the first query into the first category, using information indicating that there is no problem in classifying the first query into the first category. The artificial neural network may be updated by generating data, applying the second learning data to the artificial neural network, and training the artificial neural network so that queries having characteristics similar to the first query are classified into the first category.

Meanwhile, the process of optimizing the policy may be performed through the process of estimating the maximum value of the expected value of the sum of rewards or the maximum value of the Q-function, or estimating the minimum value of the loss function of the Q-function. Estimation of the minimum value of the loss function may be performed through stochastic gradient descent (SGD) or the like. The process of optimizing the policy is not limited thereto, and various optimization algorithms used in reinforcement learning may be used.

The control server 300 may gradually update the artificial neural network by repeating the learning process of the artificial neural network as described above. Through this, the control server 300 can train the artificial neural network to predict and output a business category suitable for the query through the characteristic information of the query.

That is, the control server 300 learns the artificial neural network by reflecting reinforcement learning through the first reward, the second reward, etc. when predicting a work category suitable for the query through the characteristic information of the query, and adjusting the analysis criteria. can do it

According to an embodiment, the control server 300 may obtain a plan view of a first space that requires design of a communication infrastructure among files stored in the cloud storage 200 . In this case, the plan view of the first space may be stored in the cloud storage 200 at the request of the customer. Here, the first space is a space that requires the design of a communication infrastructure, and the communication infrastructure may include computer equipment and communication equipment, and the computer equipment is a computation equipment with a communication function, which communicates with an external device through the communication equipment. It is the equipment that performs the communication, and the communication equipment is the equipment that handles the connection between the computer equipment and the external device through wired/wireless communication.

The control server 300 may design a structure for how to arrange the equipment in the first space before actually placing the computing equipment, communication equipment, etc. in the first space, and By indicating the location, it is possible to provide the user with a service recommended for equipment arrangement.

According to one embodiment, in the plan view of the first space, the computing equipment to be arranged in the first space is marked. For example, the first space is divided into a first zone and a second zone, the locations of the first and second computing equipment are marked in the first zone, and the locations of the third computing equipment are displayed in the third zone may be displayed.

Specifically, the control server 300 may provide a plurality of space lists to the customer terminal, and when a first space is selected from the plurality of space lists, the plan view of the first space may be displayed on the screen of the customer terminal. there is. To this end, the control server 300 may store and manage each floor plan in a database for a plurality of spaces.

Then, the control server 300 on the plan view of the first space displayed on the screen of the customer terminal, when the positions of the computer equipment to be arranged in the first space are respectively set, the computer equipment to be arranged in the first space from the customer terminal is displayed A plan view of the first space in which there is can be obtained.

The control server 300 may check whether the computer equipment to be arranged in the first space is displayed on the plan view of the first space.

If it is confirmed that the computerized equipment is not displayed on the plan view of the first space, the control server 300 may transmit a notification message informing that it is necessary to set the location of the computerized equipment to be disposed in the first space, and the control server 300 ) may receive a plan view of the first space again.

When it is confirmed that the computing equipment to be disposed in the first space is displayed on the plan view, the control server 300 may apply the plan view of the first space to the pre-learned second artificial neural network.

According to an embodiment, the second artificial neural network may be an algorithm for receiving a plan view in which the arrangement positions of the computing devices are displayed, and then outputting the arrangement positions of the communication devices according to the arrangement positions of the computer equipment.

The control server 300 may select a location where communication devices are to be arranged in the first space based on the output of the second artificial neural network.

According to an embodiment, the second artificial neural network may be trained to output the positions of communication devices disposed on the communication wiring by arranging the communication devices to be disposed in the first space to be located on the communication wiring. To this end, when the communication wiring is marked on the plan view of the first space, the second artificial neural network may output the arrangement positions of the communication devices so that the communication devices are disposed on the communication wiring.

Also, the second artificial neural network may be trained to arrange communication devices to be disposed in the first space for each zone of the first space, and to output positions of the communication devices disposed for each zone. To this end, when the first space is divided into a plurality of zones, the second artificial neural network may output the arrangement positions of the communication devices so that the communication devices are disposed for each zone.

In addition, the second artificial neural network may be trained to output the positions of the communication equipment to be disposed in the first space by disposing the communication equipment to be disposed in the first space adjacent to the computing equipment to be disposed in the first space. . To this end, when the positions of the plurality of computing devices are marked on the plan view of the first space, the second artificial neural network may output the arrangement positions of the communication devices so that the communication devices are disposed adjacent to the computing devices.

In addition, the second artificial neural network is arranged to minimize overlapping areas by comparing the area occupied by the communication devices to be disposed in the first space and the area occupied by the user movement line, so that the communication equipment and the user movement line do not overlap. It can be learned to output the location of communication equipment. To this end, when the user movement line is displayed in the plan view of the first space, the second artificial neural network may output the arrangement positions of the communication devices so that the communication devices do not overlap the user movement line.

The control server 300 may modify the floor plan by displaying the communication devices on the floor plan based on the positions where the communication devices are to be arranged in the first space.

When the positions of the first computer equipment, the second computer equipment, and the third computer equipment are displayed in the plan view of the first space, the control server 300 determines the positions of the first computer equipment, the second computer equipment, and the third computer equipment. Based on the , it is possible to select a location where the first communication equipment and the second communication equipment are to be arranged, and by displaying the first communication equipment and the second communication equipment on the plan view of the first space, it is possible to modify the floor plan of the first space. there is.

The control server 300 may transmit the revised floor plan to the customer terminal.

That is, after the control server 300 receives a plan view of the first space in which only the positions of the computerized equipment are displayed from the customer terminal, the control server 300 additionally displays the positions of the communication equipments in the modified first space. The floor plan can be transmitted to the customer terminal.

As a result of checking the plan view of the first space received from the customer terminal, the control server 300 determines that the first space is divided into a first area and a second area, based on the plan view of the first space, in the first area. You can check the computer equipment that is deployed. In this case, the computer equipment disposed in the first zone may be set by user selection.

The control server 300 may calculate the number of computing devices disposed in the first area as the first number of devices.

As a result of checking the plan view of the first space received from the customer terminal, the control server 300 determines that the first space is divided into a first area and a second area, based on the plan view of the first space, in the second area. You can check the computer equipment that is deployed. In this case, the computer equipment disposed in the second zone may be set by user selection.

The control server 300 may calculate the number of computing devices disposed in the second area as the second number of devices.

The control server 300 may calculate the third number of devices by summing the first number of devices and the second number of devices. That is, when the first space is divided into a first area and a second area, the control server 300 may calculate the number of computer equipment disposed in the first space as the third equipment number.

The control server 300 may check whether the number of third devices is greater than a reference value. Here, the reference value may be set differently depending on the embodiment.

If it is confirmed that the third number of equipment is greater than the reference value, the control server 300 displays the first communication equipment in the first area based on the location where the communication equipment is to be arranged in the first space, and displays the first communication equipment in the second area. By displaying the equipment, it is possible to modify the floor plan of the first space.

That is, when the third number of equipment is greater than the reference value, on the plan view of the first space, the first communication equipment is displayed in the first area and the second communication equipment is displayed in the second area, so that the communication equipments can be arranged for each area. there is.

Meanwhile, when it is confirmed that the third number of devices is smaller than the reference value, the control server 300 may check whether the first number of devices is greater than the second number of devices.

If it is confirmed that the first number of equipment is greater than the second number of equipment, the control server 300 displays the first communication equipment only in the first area based on the location where the communication equipment is to be arranged in the first space, and in the second area By not displaying the second communication equipment, the plan view of the first space can be modified.

If it is confirmed that the second number of equipment is greater than the first number of equipment, the control server 300 displays the second communication equipment only in the second area based on the location where the communication equipment is to be arranged in the first space, and in the first area By not displaying the first communication equipment, the plan view of the first space can be modified.

That is, when the number of third devices is smaller than the reference value, communication devices are displayed in only one of the first zone and the second zone on the plan view of the first space, and only one communication device can be disposed in the first space. .

10 is an exemplary diagram of a configuration of a control server according to an embodiment.

The control server 300 according to an embodiment includes a processor 310 and a memory 320 . The processor 310 may include at least one of the devices described above with reference to FIGS. 1 to 9 , or perform at least one method described above with reference to FIGS. 1 to 9 . A person or organization using the control server 300 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 9 .

The memory 320 may store information related to the above-described methods or a program for implementing the above-described methods. The memory 320 may be a volatile memory or a non-volatile memory.

The processor 310 may execute a program and control the control server 300 . The code of the program executed by the processor 310 may be stored in the memory 320 . The control server 300 may be connected to an external device (eg, a personal computer or a network) through an input/output device (not shown) and exchange data through wired/wireless communication.

The control server 300 may be used to train an artificial neural network or to use a learned artificial neural network. The memory 320 may include a learning or learned artificial neural network. The processor 310 may learn or execute an artificial neural network algorithm stored in the memory 320 . The control server 300 for learning the artificial neural network and the control server 300 for using the learned artificial neural network may be the same or may be separate.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, 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), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute 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 the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one 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 in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium 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 floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. 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 comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or apparatus, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

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

Claims (3)

In a method for automatically processing and generating corporate information based on artificial intelligence, performed by a control server,
Based on the log data stored in the database, by determining when and how often the first query is used during a preset reference period, the usage pattern of the first query is analyzed through the time when the first query is used, and the Using the analysis result of the usage pattern of the first query, the characteristic information of the first query, wherein the characteristic information of the first query includes information indicating in which period the first query is used regularly extracting;
predicting a business category of the first query by applying the characteristic information of the first query to an artificial neural network and based on an output of the artificial neural network;
when the prediction result for the business category of the first query is confirmed as the first category, checking a business processing period set in the first category; and
If the business processing through the first query is not requested during the business processing period, the business processing request through the first query is transmitted to the first customer server, which is one of the plurality of customer server servers, by the first query controlling the creation of corporate information;
The artificial neural network is an artificial neural network that is learned according to reinforcement learning. It is learned to predict the business category of a query through the characteristic information of the query, and after receiving the characteristic information of the query, consider the characteristics of the query. It is characterized by predicting and outputting the business category,
The control server generates an input based on characteristic information of a query to learn the artificial neural network, applies the generated input to the artificial neural network, and performs a task suitable for a query through the characteristic information of the query from the artificial neural network Obtaining an output that is a result of predicting a category, evaluating the obtained output to pay a reward, and updating the artificial neural network based on the evaluation of the output,
A method for automatically processing and generating corporate information based on artificial intelligence. According to claim 1,
After confirming the business processing period,
If the business processing through the first query is not requested until the day before the last day of the business processing period, the company information has never been generated by the first query transmitted from the first user terminal based on the log data. confirming that there is;
checking the team to which the first user belongs in the company through the first user account logged into the first user terminal; and
When the first user belongs to the first team and the first user and the second user form the first team, a notification message requesting business processing through the first query is sent to the first user Further comprising the step of transmitting to the terminal and the second user terminal,
A method for automatically processing and generating corporate information based on artificial intelligence. According to claim 1,
After confirming the business processing period,
During the business processing period, when business processing through the first query is requested from a third user terminal in a state in which business processing through the first query is not requested, the third user account logged into the third user terminal through, confirming the team to which the third user belongs in the company;
when it is confirmed that the third user belongs to the second team, checking a business processing field set in the second team;
when it is confirmed that the first category is included in the work processing field of the second team, controlling the company information to be generated by the first query; and
When it is confirmed that the first category is not included in the business processing field of the second team, the method further comprising the step of controlling so that the company information is not generated by the first query,
A method for automatically processing and generating corporate information based on artificial intelligence.

Images