KR102506429B1 - Control method of counseling work anlysing and delivering system - Google Patents

Abstract

A control method of a counseling task analysis and delivery system according to one aspect of the present invention comprises the following steps: a server receives counseling information indicating the contents of counseling carried out between a counselor and a counselee; the server analyzes the counseling information to generate counseling class information corresponding to the counseling information; the server compares counselor class information granted to the counselor with the counseling class information to determine which is higher; the server identifies a report-receiving supervisor who is to receive a report on the counseling among supervisors granted higher supervisor class information than the counseling class information based on a result of the class comparison; and the server analyzes and converts the counseling information into reporting information, then transmits the reporting information to a terminal of the report-receiving supervisor.

Description

Control method of counseling work analyzing and delivering system {Control method of counseling work analyzing and delivering system}

The present invention relates to a method for controlling a consultation task analysis and delivery system.

An artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, machines learn, judge, and become smarter on their own. The more AI systems are used, the higher the recognition rate and the more accurate understanding of user preferences, so existing rule-based smart systems are gradually being replaced by deep learning-based AI systems.

Speech recognition and image analysis are representative fields where artificial intelligence systems are applied. In particular, in the field of voice recognition, natural language processing technology for analyzing user conversations to understand user's intention and natural language processing technology for generating natural answers based on user's intention are required.

Meanwhile, in the counseling task, as voices are exchanged between the counselor and the counselee, the counselee transmits to the counselor what he/she wants to consult in voice, and the counselor transmits to the counselee the content of the answer desired by the counselee in voice.

At this time, the contents of the counseling that can be performed by the counselor may be limited according to the company's internal regulations, work regulations, and the counselor's capabilities. As such, when counseling is limited to the counselor, the counselor reports the counseling content to the manager, receives instructions and response content from the manager, and continues the counseling.

Accordingly, when counseling is limited depending on the counselor, there is a problem in that inaccurate counseling is provided to the counselee or the continuity of counseling is limited.

An object to be solved by the present invention is to provide a control method for a consultation task analysis and delivery system.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned will be clearly understood by those skilled in the art from the description below.

A control method of a counseling task analysis and delivery system according to an aspect of the present invention for solving the above problems includes receiving, by a server, counseling information indicating contents of counseling performed between a counselor and a counselee; generating, by the server, consultation level information corresponding to the consultation information by analyzing the consultation information; The server compares a high/low level between the counselor level information assigned to the counselor and the counseling level information, and receives a report on the consultation among managers to whom manager level information higher than the consultation level information is assigned based on the high/low comparison result. determining a reported manager; and analyzing, by the server, the consultation information, converting it into reporting information, and transmitting the reporting information to an administrator terminal of the reported manager.

Preferably, generating the consultation level information includes extracting a keyword based on the consultation information; generating information on the degree of occurrence of each of the keywords; Searching for the keyword in an internal DB of the server; checking keyword level information for each counseling field matched with the searched keyword; and generating counseling level information of the counseling information based on the prevalence information and the keyword level information for each counseling field.

Preferably, the generating of the counseling level information of the counseling information based on the prevalence information and the keyword grade information for each counseling field includes correcting the keyword grade information for each counseling field for each counseling keyword based on the prevalence information. correcting with keyword rating information; and calculating first grade average information of grades indicated by corrected keyword grade information for each counseling field of the searched keyword, and generating the calculated first grade average information as the counseling grade information.

Preferably, the determining of the manager to be reported may include, if the consultation level information is higher than the counselor level information, identifying a manager to whom manager level information higher than the consultation level information is assigned; determining the identified manager as the reported manager if the number of the identified managers is not plural; and determining the reported manager from among the identified managers based on the consultation level information and manager level information for each consultation field of each of the identified managers, if the number of the identified managers is plural.

Preferably, the determining of the manager to be reported from among the confirmed managers may include: calculating a second average grade for each consultation field of a grade indicated by corrected keyword level information for each consultation field used to generate the consultation level information; calculating grade deviation information between the second average grade information for each counseling field and the manager grade information for each counseling field of the identified manager; and determining, among the confirmed managers, a manager having the minimum level deviation information as the reported manager.

A method for controlling a consultation task analysis and delivery system according to the present invention includes the steps of the server sending a request signal to stop consulting to the counselor terminal; receiving counseling response information from the manager terminal in response to the transmission of the reporting information; and transmitting the counseling response information to the counselor terminal and the counselee terminal.

Other specific details of the invention are included in the detailed description and drawings.

According to various embodiments of the present invention described above, there is an effect of improving the accuracy and convenience of counseling services by providing a consulting task analysis and delivery system combined with artificial intelligence.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a system diagram illustrating a system according to one embodiment of the present invention.
2 is a flowchart illustrating a consulting task analysis and delivery system according to an embodiment of the present invention.
3 is a flowchart illustrating a method of transmitting counseling response information according to an embodiment of the present invention.
4 is a flowchart illustrating a method of generating consultation level information according to an embodiment of the present invention.
5 is a flowchart illustrating a method of generating counseling level information of counseling information based on prevalence information and keyword level information for each counseling field according to an embodiment of the present invention.
6 is a flowchart illustrating a method of determining a reported manager according to an embodiment of the present invention.
7 is a flowchart illustrating a method of determining a reported manager from among confirmed managers according to an embodiment of the present invention.
8 is a configuration diagram of a device according to an embodiment of the present invention.

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

Terminology used herein is for describing the embodiments and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements. Like reference numerals throughout the specification refer to like elements, and “and/or” includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various components, these components are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first element mentioned below may also be the second element within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

The term "unit" or "module" used in the specification means a hardware component such as software, FPGA or ASIC, and "unit" or "module" performs certain roles. However, "unit" or "module" is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside in an addressable storage medium and may be configured to reproduce one or more processors. Thus, as an example, a “unit” or “module” may refer to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. Functions provided within components and "units" or "modules" may be combined into smaller numbers of components and "units" or "modules" or may be combined into additional components and "units" or "modules". can be further separated.

The spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe a component's correlation with other components. Spatially relative terms should be understood as including different orientations of elements in use or operation in addition to the orientations shown in the drawings. For example, if you flip a component that is shown in a drawing, a component described as "below" or "beneath" another component will be placed "above" the other component. can Thus, the exemplary term “below” may include directions of both below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer means any kind of hardware device including at least one processor, and may be understood as encompassing a software configuration operating in a corresponding hardware device according to an embodiment. For example, a computer may be understood as including a smartphone, a tablet PC, a desktop computer, a laptop computer, and user clients and applications running on each device, but is not limited thereto.

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

Although each step described in this specification is described as being performed by a computer, the subject of each step is not limited thereto, and at least a part of each step may be performed in different devices according to embodiments.

1 is a system diagram illustrating a system according to one embodiment of the present invention.

A system according to the present invention may include a server 10, a counselor terminal 20, a counselee terminal 30, and a manager terminal 40.

The server 10 is a component for providing a counseling task analysis and delivery service to the counselor terminal 20 , the counselee terminal 30 and the manager terminal 40 . As an embodiment, the service of analyzing and delivering counseling work may be provided to the counselor terminal 20 and the counselee terminal 30 in the form of an application.

Specifically, the server 10 analyzes counseling information transmitted and received between the counselor terminal 20 and the counselee terminal 30, and if the counseling level information of the counseling information is higher than the counselor level information of the counselor of the counselor terminal 20, counseling Among the managers to whom manager level information higher than the level information is assigned, a reported manager to be reported on counseling may be determined, and the consultation information may be analyzed, converted into reporting information, and transmitted to the manager terminal of the reported manager.

The server 10 may use an artificial intelligence model to analyze counseling information transmitted and received between the counselor terminal 20 and the counselee terminal 30 to generate counseling level information and convert it into reporting information.

As an embodiment, the server may acquire counseling information, counseling grade information corresponding to the counseling information, and reporting information corresponding to the counseling information as training data for learning, thereby learning the artificial intelligence model. Specifically, the server 10 may input counseling information to an artificial intelligence model and train the artificial intelligence model to output counseling grade information and reporting information.

In this case, the server 10 may generate counseling level information and reporting information for counseling information between all counselees and counselors through the first general-purpose artificial intelligence model, and furthermore, through the second personalized artificial intelligence model, the specific counselee Consultation level information and reporting information about consultation information between the agent and the agent may be created.

That is, the server 10 uses initially set arbitrary learning data and learning data obtained from each counselee and counselor as learning data of the first artificial intelligence model, but learning data learned from a specific counselee and counselor. can be used as training data for the second artificial intelligence model.

In one embodiment, when the server 10 receives counseling information about a specific counselee and counselor, the server 10 independently inputs the counseling information as an input value to the first artificial intelligence model and the second artificial intelligence model, thereby generating an output value (i.e., counseling grade information and reporting information) may be obtained, and at least one output value of an output value output through the first artificial intelligence model and an output value output through the second artificial intelligence model may be obtained as a final output value. For example, the server 10 acquires the output value output through the first artificial intelligence model as a final output value when the accuracy of the output value output through the second artificial intelligence model is equal to or less than a preset value, and obtains the second artificial intelligence model output value as a final output value. When the accuracy of the output value output through is greater than a preset value, the output value output through the second artificial intelligence model may be obtained as a final output value. Through the above-described method, the server 10 provides a personalized response using the second artificial intelligence model, but converts the second artificial intelligence model, which does not guarantee an accurate result output due to a relatively insufficient amount of learning data, to the first artificial intelligence model. This can be supplemented by models.

Meanwhile, in order to analyze the counseling information received from the counselor terminal 20 and the counselee terminal 30, the server 10 according to the present invention includes a natural language understanding unit (NLU), a counseling information management management module, and a natural language It may include a natural language generator (NLG), and a database.

The natural language understanding unit is a component for identifying a task related to an entity and an intent of the counseling information based on the received counseling information. Specifically, the natural language understanding unit may interpret the sentence through analysis of the structure and main components of the sentence and perform sentence analysis using statistics/analysis.

The counseling information management management module is a configuration for acquiring information on counseling level information and reporting information corresponding to counseling information based on a result of natural language understanding and data stored in a database. Consultation information management management module can be implemented as Frame-based, Agent-based, etc., and of course it can be implemented through MDP (Markov Decision Process) and Reinforcement Learning-based modeling. At this time, the consultation information management management module may acquire information for generating a response (consultation grade information or reporting information), and as described above, the obtained information is the task identified through the natural language understanding unit and the data stored in the database. can be determined based on The natural language generating unit may acquire natural language as a response to the counseling information based on information acquired through the counseling information management management module.

The database is a component for storing information necessary for generating a response in the consultation information management management module. At this time, the data stored in the database may be various. As an embodiment, the data stored in the database includes a history of conversation contents of counseling information transmitted and received in the past between the counselor terminal 20 and the counselee terminal 30, consultation grade information generated according to past conversation contents, and reporting. It may be information and data received from the counselor terminal 20 and the counselee terminal 30 . However, it goes without saying that in addition to the above-described data, the server 10 may store various data for determining data to be transmitted to the counselor terminal 20 and the counselee terminal 30 .

In this case, it may be an artificial intelligence model based on convolutional deep neural networks (CNN) learned by inputting the artificial intelligence model training data according to the present invention. However, it is not limited thereto, and it goes without saying that various artificial intelligence models can be applied to the present invention. For example, models such as a deep neural network (DNN), a recurrent neural network (RNN), and a bidirectional recurrent deep neural network (BRDNN) may be used as an artificial intelligence model, but are not limited thereto.

At this time, convolutional deep neural networks (CNNs) are a type of multilayer perceptrons designed to use a minimum of preprocessing. A convolutional neural network consists of one or several convolutional layers and general artificial neural network layers placed on top of them, and additionally utilizes weights and pooling layers. Thanks to this structure, convolutional neural networks can fully utilize input data with a two-dimensional structure. Also, convolutional neural networks can be trained via standard back-propagation. Convolutional neural networks are easier to train than other feedforward artificial neural network techniques and have the advantage of using fewer parameters.

In addition, deep neural networks (DNNs) are artificial neural networks (ANNs) consisting of a plurality of hidden layers between an input layer and an output layer.

At this time, the structure of the deep neural network may be composed of a perceptron. Perceptron consists of several inputs, one processor, and one output value. The processor multiplies each of a plurality of input values by a weight, and then sums all the input values multiplied by the weight. Then, the processor substitutes the summed value into the activation function and outputs one output value. If a specific value is desired as an output value of the activation function, a weight value multiplied with each input value may be modified, and an output value may be recalculated using the corrected weight value. At this time, each perceptron may use a different activation function. In addition, each perceptron accepts the outputs passed from the previous layer as inputs, and then obtains the outputs using the activation function. The obtained output is passed as input to the next layer. Through the process as described above, several output values can finally be obtained.

Also, going back to the description of the deep learning technique, a recurrent neural network (RNN) refers to a neural network in which connections between units constituting an artificial neural network constitute a directed cycle. Unlike feed-forward neural networks, recurrent neural networks can utilize the memory inside the neural network to process arbitrary inputs.

Deep Belief Networks (DBN) is a generative graphical model used in machine learning. In deep learning, it means a deep neural network consisting of multiple layers of latent variables. There are connections between layers, but there is no connection between units within a layer.

Due to the characteristics of a generative model, the deep trust neural network can be used for prior learning, and after learning initial weights through prior learning, the weights can be fine-tuned through backpropagation or other discrimination algorithms. This characteristic is very useful when there is little training data, because the smaller the training data, the stronger the influence of the initial weight values on the resulting model. The pre-learned initial value of the weight becomes closer to the optimal weight than the arbitrarily set initial value of the weight, which enables the performance and speed of the fine-tuning step to be improved.

The above-described artificial intelligence and its learning method are described for illustrative purposes, and the artificial intelligence and its learning method used in the embodiments described below are not limited. For example, all kinds of artificial intelligence technologies and learning methods that can be applied by a person skilled in the art to solve the same problem can be used to implement the system according to the disclosed embodiment.

The counselor terminal 20 may be a counselor's terminal that provides counseling to a counselee. To this end, the counselor terminal 20 may be configured to obtain and transmit the counselor's voice to the counselee terminal 30, and to receive and output the counselee's voice.

According to one embodiment, of course, the server 10 and the counselor terminal 20 may be implemented as a single device.

The counselee terminal 30 may be a terminal of a counselee who requests counseling from a counselor and receives counseling from the counselor. To this end, the counselee terminal 30 may be configured to acquire and transmit the counselee's voice to the counselor terminal 20, and to receive and output the counselor's voice.

The manager terminal 40 may be a manager terminal that provides counseling services and manages counselors. Administrators may have the authority to view more information than counselors.

The manager terminal 40 may receive reporting information from the server 10 .

The counselor terminal 20 , the counselee terminal 30 , and the manager terminal 40 may communicate with each other based on the consultation task analysis and delivery application provided from the server 10 .

In one embodiment, the counselor terminal 20, the counselee terminal 30, and the manager terminal 40 may be a smartphone, a tablet personal computer (tablet PC), a mobile phone, a video phone, or an e-book reader. (e-book reader), desktop PC (desktop PC), laptop PC (laptop PC), netbook computer, workstation, server, PDA (personal digital assistant), PMP (portable multimedia player) may contain at least one.

Hereinafter, various embodiments of the present invention will be described using FIGS. 2 to 6 .

2 is a flowchart illustrating a consulting task analysis and delivery system according to an embodiment of the present invention.

Referring to FIG. 2 , in step S110, the server 10 may receive counseling information indicating contents of counseling performed between a counselor and a counselee.

Here, the counseling information may be voice data representing the voices of the counselor and the counselee, respectively.

In an embodiment, the server 10 may receive counseling information transmitted and received between the counselor terminal 20 and the counselee terminal 30 .

In step S120, the server 10 may generate consultation level information corresponding to the consultation information by analyzing the consultation information.

In step S130, the server 10 compares the level between the counselor level information assigned to the counselor and the consultation level information, and based on the comparison result, reports on counseling among managers who have been assigned manager level information higher than the consultation level information. You can decide who will receive the report.

In step S140, the server 10 may analyze and convert the consultation information into reporting information, and transmit the reporting information to the manager terminal of the reported manager.

3 is a flowchart illustrating a method of transmitting counseling response information according to an embodiment of the present invention.

Referring to FIG. 3 , in step S210 , the server 10 may transmit a counseling stop request signal to the counselor terminal 20 .

That is, the server 10 may transmit a counseling stop request signal to the counselor terminal 20 to stop the counseling of the counselor when the counseling level information of the counseling information is higher than the counselor grade information assigned to the counselor.

In step S220, the server 10 may receive counseling response information from the manager terminal 30 in response to the transmission of the reporting information.

Here, the counseling response information may be information for responding to counseling input to the manager terminal 40 from a manager receiving reporting information obtained by analyzing and converting the counseling information.

In step S230, the server 10 may transmit counseling response information to the counselor terminal 20 and the counselee terminal 30.

Through this, counseling that has been stopped because the counseling level information of the counseling information is higher than the counselor grade information assigned to the counselor can be continuously performed due to the counseling response information transmitted from the manager terminal 40 .

To this end, the server 10 may match and store counselor grade information for each counselor, as shown in Table 1 below.

consultant Agent Rating Information go 2 you 4 ... ...

4 is a flowchart illustrating a method of generating consultation level information according to an embodiment of the present invention.

Referring to FIG. 4 , in step S310, the server 10 may extract keywords based on counseling information.

As an embodiment, the server 10 may extract keywords by morphologically analyzing counseling information.

In another embodiment, the server 10 inputs counseling information to a natural language understanding unit to obtain a task related to an entity of the counseling information and an intent of the counseling information, and uses the obtained task. You can judge by keyword. In this case, a task related to the intent of the counseling information may be information necessary for a response to the counseling information. For example, when the consultation information is design-related consultation, the task may be design inquiry.

In step S320, the server 10 may generate information on the appearance of each keyword.

As an embodiment, the server 10 may generate a ratio of the number of extracted keywords to the total number of keywords extracted from the counseling information as appearance information.

For example, when the server 10 extracts 1, 2, and 3 keywords “A”, “B”, and “C” from the counseling information, a total of 6 keywords, “A” appearance information is provided. It can be calculated as 1/6.

In step S330, the server 10 may search for keywords in the internal DB.

In step S340, the server 10 may check keyword rating information for each consultation field matched to the searched keyword.

To this end, the server 10 may match and store keyword rating information for each consultation field for each keyword, as shown in Table 2 below.

keyword Keyword Rating Information for Consultation Field 1 Keyword Rating Information for Consultation Field 2 ... A 2 3 ... B 4 2 ... C One 5 ... ... ... ... ... ... ... ... ...

Meanwhile, in the present specification, counseling level information may be information representing a level required of a counselor or manager capable of conducting counseling on counseling information.

In addition, in the present specification, counselor level information may be information representing a minimum level of counseling information at which the corresponding counselor can conduct counseling.

Also, in the present specification, manager level information may be information representing a minimum level of counseling information at which a corresponding manager can conduct counseling.

The keyword level information may be level information partially representing counseling level information of counseling information from which a corresponding keyword is extracted.

The above-mentioned level information (consultation level information, counselor level information, manager level information, keyword level information) may mean a value expressed as an absolute number, such as a first level level or a second level level, but a consultation task analysis and delivery system It may refer to a relative grade set differently according to counselors and managers using , counseling information and keywords used in a counseling task analysis and delivery system.

For example, the higher the level indicated by the agent level information and the manager level information (closer to the 1st grade level), this may mean that counseling that each corresponding counselor and manager can proceed with is not limited.

In addition, the higher the level indicated by the consultation level information and the keyword level information (closer to the first level level), the more limited counselors and managers capable of conducting consultations corresponding to the corresponding consultation information.

In step S350, the server 10 may generate consultation level information of the consultation information based on the degree of occurrence information and the keyword level information for each consultation field.

5 is a flowchart illustrating a method of generating counseling level information of counseling information based on prevalence information and keyword level information for each counseling field according to an embodiment of the present invention.

Referring to FIG. 5 , in step S410, the server 10 may correct the keyword rating information for each consultation field to corrected keyword rating information for each consultation field based on the degree of appearance information.

First, the server 10 may generate type ratio information of keywords extracted from counseling information. Specifically, the server 10 may check the number of keyword types of the extracted keywords and generate a ratio occupied by any one keyword among the total number of keyword types as type ratio information.

For example, when the server 10 extracts 1, 2, and 3 keywords "A", "B", and "C" from the consultation information, a total of 6 keywords are identified, the number of keyword types is 3, Type ratio information of each of the keywords “A”, “B”, and “C” may be generated at a percentage of 1/3.

Thereafter, the server 10 compares the size of the extracted keyword type ratio information and the appearance information, and as a result of the comparison, if the extracted keyword type ratio information and the extracted keyword appearance information are the same, the keyword rating information for each consultation field and consultation Corrected keyword level information for each consultation field may be corrected so that the corrected keyword level information for each field is the same.

Thereafter, the server 10 compares the size of the extracted keyword type ratio information and the appearance information, and if the comparison result, the appearance information is identical to the extracted keyword type ratio information, the keyword rating information for each consultation field and consultation Corrected keyword level information for each consultation field may be corrected so that the corrected keyword level information for each field is the same.

On the other hand, the server 10 compares the size of the extracted keyword type ratio information and the appearance information, and as a result of the comparison, if the appearance information exceeds the extracted keyword type ratio information, the keyword rank for each consultation field of the corresponding keyword. It is possible to check whether the information is higher than the keyword central level information.

Subsequently, the server 10 provides counseling as much as the difference between the appearance information and the type ratio information when the appearance information exceeds the type ratio information of the extracted keyword and the keyword grade information for each counseling field of the corresponding keyword is higher than the keyword central grade information. Corrected keyword level information for each consultation field may be corrected by increasing the keyword level information for each field.

Conversely, the server 10 provides counseling as much as the difference between the appearance information and the type ratio information when the appearance information exceeds the type ratio information of the extracted keyword and the keyword grade information for each counseling field of the corresponding keyword is equal to or less than the keyword central grade information. Corrected keyword level information for each consultation field may be corrected by lowering the keyword level information for each field.

On the other hand, the server 10 compares the size of the extracted keyword type ratio information and the appearance information, and as a result of the comparison, if the appearance information is less than the extracted keyword type ratio information, keyword rating information for each consultation field of the corresponding keyword. It is possible to check whether is higher than the keyword central level information.

Subsequently, the server 10 determines that the difference between the appearance information and the type ratio information is equal to the difference between the appearance information and the type ratio information when the keyword rating information for each consulting field of the keyword is higher than the central keyword rating information. Corrected keyword level information for each consultation field may be corrected by lowering the level information for each keyword.

Conversely, the server 10 provides counseling as much as the difference between the appearance information and the type ratio information when the appearance information exceeds the type ratio information of the extracted keyword and the keyword grade information for each counseling field of the corresponding keyword is equal to or less than the keyword central grade information. Corrected keyword level information for each consultation field may be corrected by increasing the keyword level information for each field.

Here, the keyword central level information may mean a central level between the highest level and the lowest level of the keyword level information.

In step S420, the server 10 may calculate first grade average information of grades indicated by corrected keyword grade information for each counseling field of the searched keyword, and generate the calculated first grade average information as counseling grade information.

Specifically, the server 10 may calculate an average of corrected keyword level information for all counseling fields of all keywords as the first level average information.

6 is a flowchart illustrating a method of determining a reported manager according to an embodiment of the present invention.

Referring to FIG. 6 , in step S510, if the consultation level information is higher than the counselor level information, the server 10 may identify a manager assigned manager level information higher than the counseling level information.

In step S520, the server 10 may determine the confirmed manager as the reported manager if there are not a plurality of confirmed managers.

In step S530, if there are a plurality of confirmed managers, the server 10 may determine a reported manager from among the confirmed managers based on the consultation level information and the manager level information for each consultation field of each confirmed manager.

To this end, the server 10 may match and store manager level information for each consultation field for each manager, as shown in Table 3 below.

Here, the manager level information may be an average of manager level information for each consultation field.

manager Manager level information Manager level information for consultation field 1 Manager level information in consultation field 2 ... go 2.5 2 3 ... me 3 4 2 ... all 3 One 5 ... la 2 2 2 ... ... ... ... ...

7 is a flowchart illustrating a method of determining a reported manager from among confirmed managers according to an embodiment of the present invention.

Referring to FIG. 7 , in step S610, the server 10 may calculate a second average grade for each counseling field of a grade indicated by the corrected keyword grade information for each counseling field used to generate counseling grade information.

Specifically, the server 10 classifies the corrected keyword rating information for each counseling field for each keyword according to the counseling field, and calculates an average grade among corrected keyword rating information having the same counseling field among the corrected keyword rating information for each keyword. It can be calculated with the second average grade information for each star.

In step S620, the server 10 may calculate grade deviation information between the second average grade information for each consultation field and the manager grade information for each consultation field of each confirmed manager.

That is, the server 10 may calculate the grade deviation between the second average grade information of the same counseling field and the manager grade information of the confirmed manager, and add the calculated grade deviations to calculate the grade deviation information.

In step S630, the server 10 may determine a manager having the minimum level deviation information among the confirmed managers as the reported manager.

8 is a configuration diagram of a server 10 according to an embodiment of the present invention.

The processor 102 may include one or more cores (not shown) and a graphic processor (not shown) and/or a connection path (eg, a bus) for transmitting and receiving signals to and from other components. .

Processor 102 according to one embodiment performs the method described with respect to FIGS. 2-6 by executing one or more instructions stored in memory 104 .

For example, the processor 102 acquires new training data by executing one or more instructions stored in memory, performs a test on the acquired new training data using a learned model, and labels the test result as First training data in which the extracted information is obtained with accuracy equal to or higher than a predetermined first reference value is extracted, the extracted first training data is deleted from the new training data, and the new training data from which the extracted training data is deleted is stored. The learned model can be re-learned by using

Meanwhile, the processor 102 includes RAM (Random Access Memory, not shown) and ROM (Read-Only Memory) temporarily and/or permanently storing signals (or data) processed in the processor 102. , not shown) may be further included. In addition, the processor 102 may be implemented in the form of a system on chip (SoC) including at least one of a graphics processing unit, RAM, and ROM.

The memory 104 may store programs (one or more instructions) for processing and control of the processor 102 . Programs stored in the memory 104 may be divided into a plurality of modules according to their functions.

Steps of a method or algorithm described in connection with an embodiment of the present invention may be implemented directly in hardware, implemented in a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any form of computer readable recording medium well known in the art to which the present invention pertains.

Components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, such as C, C++ , Java (Java), can be implemented in a programming or scripting language such as assembler (assembler). Functional aspects may be implemented in an algorithm running on one or more processors.

Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features of the present invention. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

10: Server
20: agent terminal
30: counselee terminal
40: administrator terminal

Claims (6)

In the control method of the consulting business analysis and delivery system,
Receiving, by a server, counseling information representing contents of counseling performed between a counselor and a counselee;
generating, by the server, consultation level information corresponding to the consultation information by analyzing the consultation information;
The server compares a high/low level between the counselor level information assigned to the counselor and the counseling level information, and receives a report on the consultation among managers to whom manager level information higher than the consultation level information is assigned based on the high/low comparison result. determining a reported manager; and
The server analyzes the consultation information, converts it into reporting information, and transmits the reporting information to an administrator terminal of the reported manager;
The step of generating the consultation level information,
extracting keywords based on the counseling information;
generating information on the degree of occurrence of each of the keywords;
Searching for the keyword in an internal DB of the server;
checking keyword level information for each counseling field matched with the searched keyword; and
Generating consultation level information of the consultation information based on the appearance information and keyword level information for each consultation field;
Generating the consultation level information of the consultation information based on the appearance information and the keyword level information for each consultation field,
correcting the keyword level information for each consultation field into corrected keyword level information for each consultation keyword based on the appearance information; and
Calculating first grade average information of grades indicated by corrected keyword grade information for each counseling field of the searched keyword, and generating the calculated first grade average information as the counseling grade information;
The step of correcting the keyword rating information for each counseling field with corrected keyword rating information for each counseling keyword based on the appearance information,
generating a ratio occupied by any one keyword among the number of keyword types of all the extracted keywords as type ratio information;
comparing magnitudes of the type ratio information and the degree of occurrence information; and
correcting corrected keyword rating information for each consultation field so that the keyword rating information for each consultation field and the corrected keyword rating information for each consultation field are the same when the type ratio information and the appearance information are the same;
Comparing the size of the type ratio information and the appearance information,
if the appearance information exceeds the type ratio information, determining whether keyword rating information for each consultation field of the excess keyword is higher than keyword central rating information; and
If the keyword rating information for each consulting field of the excess keyword is higher than the central keyword rating information, the keyword rating information for each consulting field is raised by the difference between the appearance information and the type ratio information to obtain corrected keyword rating information for each consulting field. Correction is made, but if the keyword grade information for each counseling field of the excess keyword is less than or equal to the keyword central grade information, the keyword grade information for each counseling field is lowered by the difference between the appearance information and the type ratio information to correct keywords for each counseling field. Including; correcting the rating information;
Comparing the size of the type ratio information and the appearance information,
if the prevalence information is less than the type ratio information, determining whether keyword rating information for each counseling field of the less than keyword is higher than keyword central rating information; and
If keyword rating information for each consultation field of keywords less than the above is higher than keyword central rating information, correction keyword rating information for each consultation field is corrected by lowering the keyword rating information for each consultation field by a difference between the appearance information and the type ratio information. However, if the keyword rating information for each consultation field of keywords less than the above is equal to or less than the central keyword rating information, the keyword rating information for each consultation field is raised by the difference between the appearance information and the type ratio information to correct keyword rating information for each consultation field. Including; correcting the
The keyword central rating information,
Characterized in that the central level between the highest level and the lowest level of the keyword level information, the control method.
delete delete According to claim 1,
The step of determining the reported manager,
if the consultation level information is higher than the counselor level information, identifying a manager to whom manager level information higher than the consultation level information is assigned;
determining the identified manager as the reported manager if the number of the identified managers is not plural; and
If the number of the identified managers is plural, determining the reported manager from among the identified managers based on the consultation level information and the manager level information for each consultation field of each of the identified managers.
Including control methods.
According to claim 4,
The step of determining the reported manager among the confirmed managers,
calculating a second average grade for each counseling field of grades indicated by corrected keyword grade information for each counseling field used to generate the counseling grade information;
calculating grade deviation information between the second average grade information for each counseling field and the manager grade information for each counseling field of the identified manager; and
determining a manager having the minimum level deviation information among the identified managers as the reported manager;
Including control methods.
According to claim 1,
transmitting, by the server, a counseling stop request signal to the counselor terminal of the counselor;
receiving, by the server, counseling response information from the manager terminal in response to transmission of the reporting information; and
transmitting, by the server, the counseling response information to the counselor terminal and the counselee terminal of the counselee;
A control method further comprising.

Images