KR20210114740A - Method to analyze consultation data - Google Patents

Abstract

According to an embodiment of the present invention, disclosed is a computer program stored in a computer-readable storing medium. When executed in one or more processors, the computer program performs operations as follows. The operations comprises: an operation of determining a type code about consultation data; an operation of using a pre-stored format for each type code to determine a format corresponding to the consultation data; an operation of extracting summary information corresponding to each of one or more lists included in the format from the consultation data; and an operation of generating a consultation summary result including one or more pieces of summary information.

Description

Consultation data analysis method {METHOD TO ANALYZE CONSULTATION DATA}

The present invention relates to a method of analyzing consultation data, and more particularly, to a method of generating a consultation summary result by analyzing customer consultation data.

Due to the growth of the Internet and mobile industries, a big data environment, which means a large amount of structured or unstructured data beyond the scale that can be collected, managed, stored, and analyzed with existing database management tools, is coming. Such big data is a large-scale data in various forms generated in a digital environment, and is regarded as a key resource that can influence future competitiveness of companies, etc.

In addition, extracting economically necessary values from big data may be referred to as big data technology. Utilizing big data can create various types of value, such as establishing marketing strategies, optimizing processes, improving productivity, and preventing fraud. Therefore, big data technology to effectively utilize such big data can be said to be a means of securing corporate competitiveness that should be considered first in the era of unlimited competition regardless of the type of company.

The insurance industry can also use big data to secure the competitiveness of the company concerned. For example, an insurance company could use big data to serve customers in a call center. In the case of telephone consultations conducted in a call center, the agent must directly summarize the contents of the consultation with the customer after responding to the customer or classify the type of the consultation contents. It takes a lot of time for the agent to summarize the consultation contents or classify the types of consultation contents manually after responding to the customer, and it may be impossible to respond to other customers while performing the following tasks. Therefore, there is a need in the art for a convenient method for summarizing or classifying types of consultations with customers in order to improve the work efficiency of counselors.

Korean Patent Registration No. 10-1949427 discloses an automatic evaluation system for consultation contents.

The present disclosure has been devised in response to the above background art, and aims to analyze counseling data.

According to an embodiment of the present disclosure for realizing the above-described problems, as a computer program stored in a computer-readable storage medium, the computer program performs the following operations for analyzing counseling data when executed on one or more processors. wherein the operations include: determining a type code for the consultation data; determining a format corresponding to the consultation data by using a format for each pre-stored type code; extracting summary information corresponding to each of one or more items included in the format from the consultation data; and generating a counseling summary result including one or more summary information.

In an alternative embodiment of the computer program operations for performing the following operations for analyzing the counseling data, the method further comprises: receiving feedback regarding the counseling summary result; and updating at least one of a method for determining a type code and a method for extracting summary information based on the feedback, or storing a result of the consultation summary; may further include.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the counseling data, the feedback comprises at least one of: an evaluation of at least a portion of the counseling summary result or a correction of at least a portion of the counseling summary result. may contain one.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the consultation data, updating at least one of a method for determining a type code or a method for extracting summary information based on the feedback, or a result of the consultation summary The storing operation includes: determining to update the type code determination method when the negative feedback is greater than or equal to a threshold value; Alternatively, when the negative feedback is less than a threshold value, the method may include determining to update the summary information extraction method.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the consultation data, updating at least one of a method for determining a type code or a method for extracting summary information based on the feedback, or a result of the consultation summary The storing may include: updating at least one of the method for determining the type code or the method for extracting summary information based on at least one of a predetermined time unit or a predetermined feedback degree.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the consultation data, the operation of determining the type code for the consultation data is: based on input of a type code of at least one of a customer terminal or an agent terminal to determine the type code; determining the type code using a type code determination model including one or more pre-trained network functions; or determining the type code by comparing at least one of the main words or main sentences related to the consultation data with the words or sentences for each type code stored in advance; It may include at least one operation of

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the consultation data, the type code determination model may include: a first sub for identifying a relationship between two or more semantic units included in the consultation data. and a second sub-model for outputting the type code based on a model and a relationship between the two or more semantic units.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the counseling data, the key word may be: determined based on a degree of simultaneous occurrence of two or more words included in the counseling data, and The main sentence: The sentences included in the counseling data may be determined based on a high degree of similarity with other sentences.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the consultation data, extracting summary information corresponding to each of one or more items included in the form from the consultation data includes: the consultation data and calculating the item information using a summary information determination model including one or more pre-trained network functions to extract the summary information; Alternatively, the method may include at least one operation of extracting the summary information by comparing at least one of the main words or main sentences related to the counseling data with the pre-stored summary information for each item.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the consultation data, the summary information determination model is configured to: compute at least one of a key word or a key sentence relating to the consultation data, and the item information Thus, it may be a model trained to output the summary information.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the consultation data, extracting summary information corresponding to each of one or more items included in the form from the consultation data includes: the consultation data extracting the summary information by using a sentence corresponding to a pre-stored sentence format for each item among sentences included in ; Alternatively, the method may include at least one operation of extracting the summary information by using a sentence including a semantic unit corresponding to a keyword for each item stored in advance among semantic units included in the consultation data.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the consultation data, the one or more items are: customer basic information related items, customer inquiry related items, agent response related items, consulting target related items, or It may include at least one of cost-related items.

In an alternative embodiment of the computer program operations for performing the following operations for analyzing the counseling data, the operation may further include outputting an analysis result based on the counseling summary result corresponding to two or more different time intervals.

In an alternative embodiment of the computer program operations to perform the following operations for analyzing the counseling data, the analysis result may include analysis information regarding at least one of a type code, an item, or summary information.

According to an embodiment of the present disclosure for realizing the above-described problem, a method for analyzing counseling data, the method comprising: determining a type code for the counseling data; determining a format corresponding to the consultation data by using a format for each pre-stored type code; extracting summary information corresponding to each of one or more items included in the format from the consultation data; and generating a counseling summary result including one or more summary information.

A server for analyzing counseling data according to an embodiment of the present disclosure for realizing the above-described problem, comprising: a processor including one or more cores; and a memory; wherein the processor determines a type code for the consultation data, determines a format corresponding to the consultation data by using a format for each type code stored in advance, and determines the format included in the format from the consultation data. It is possible to extract summary information corresponding to each of one or more items, and generate a counseling summary result including one or more summary information.

The present disclosure may provide a method for analyzing counseling data.

1 is a diagram illustrating a block diagram of a computing device that performs an operation for analyzing counseling data according to an embodiment of the present disclosure.
2 is a diagram exemplarily illustrating a method of analyzing counseling data according to an embodiment of the present disclosure.
3 is a diagram exemplarily illustrating a method of analyzing counseling data according to an embodiment of the present disclosure.
4 is a diagram exemplarily illustrating a method of analyzing counseling data according to an embodiment of the present disclosure.
5 is a flowchart of a counseling data analysis method according to an embodiment of the present disclosure.
6 is a block diagram of a computing device according to an embodiment of the present disclosure.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the present disclosure. However, it is apparent that these embodiments may be practiced without these specific descriptions.

The terms “component,” “module,” “system,” and the like, as used herein, refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or execution of software. For example, a component can be, but is not limited to being, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device may be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored therein. Components may communicate via a network such as the Internet with another system, for example via a signal having one or more data packets (eg, data and/or signals from one component interacting with another component in a local system, distributed system, etc.) may communicate via local and/or remote processes depending on the data being transmitted).

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or clear from context, "X employs A or B" is intended to mean one of the natural implicit substitutions. That is, X employs A; X employs B; or when X employs both A and B, "X employs A or B" may apply to either of these cases. It should also be understood that the term “and/or” as used herein refers to and includes all possible combinations of one or more of the listed related items.

Also, the terms "comprises" and/or "comprising" should be understood to mean that the feature and/or element in question is present. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, elements and/or groups thereof. Also, unless otherwise specified or unless the context is clear as to designating a singular form, the singular in the specification and claims should generally be construed to mean "one or more."

Those skilled in the art will further appreciate that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or combinations of both. It should be recognized that they can be implemented with To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

Descriptions of the presented embodiments are provided to enable those skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art of the present disclosure. The generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present invention is not limited to the embodiments presented herein. This invention is to be construed in its widest scope consistent with the principles and novel features presented herein.

In an embodiment of the present disclosure, the server may include other configurations for performing a server environment of the server. The server may include any type of device. The server is a digital device, and may be a digital device equipped with a processor, such as a laptop computer, a notebook computer, a desktop computer, a web pad, and a mobile phone, and having a computing capability with a memory. The server may be a web server that processes the service. The above-described types of servers are merely examples, and the present disclosure is not limited thereto.

1 is a diagram illustrating a block diagram of a computing device that performs an operation for analyzing counseling data according to an embodiment of the present disclosure.

The computing device 100 performing an operation for analyzing counseling data according to an embodiment of the present disclosure may include a network unit 110 , a processor 120 , and a memory 130 .

Hereinafter, a method of analyzing counseling data will be described.

The processor 120 may receive consultation data through the network unit 110 .

The consultation data may be data including the contents of consultation between the counselor and the customer. Consultation data may refer to data collected or generated from a customer consultation start time to a customer consultation end time. For example, when the customer requests the consultation, the consultation data may mean data collected or generated during a time period between the time when the customer requests the consultation and the time when the customer consultation ends. For example, consultation data includes data recorded on calls between agents and customers in a call center, message data exchanged between agents and customers through chatting, and customer questions and answers uploaded to the VOC (Voice of Customer) bulletin board. and the like. The detailed description of the above-mentioned counseling data is only an example, and the present disclosure is not limited thereto.

The consultation data may include at least one of voice data and text data. For example, when the customer and the agent perform a consultation over the phone, the consultation data may include voice data, and when the customer and the agent perform the consultation through chatting, the consultation data may include text data. The detailed description of the above-mentioned counseling data is only an example, and the present disclosure is not limited thereto.

When the consultation data includes voice data, the processor 120 may convert the voice data into text data. For example, the processor 120 may convert voice data collected from a call center server into text data through a speech to text (STT) engine. For example, the STT engine may be an artificial neural network model trained to convert speech data into text data. The detailed description of the above-mentioned counseling data is only an example, and the present disclosure is not limited thereto.

The processor 120 may store the received counseling data or data converted from the counseling data in the memory 130 .

The processor 120 may generate a counseling summary result by using the counseling data.

The counseling summary result may be data summarizing the counseling data. The counseling summary result may be data summarized to include only important data of at least some of the data included in the counseling data. The counseling summary result according to an embodiment of the present disclosure may include a combination of at least some words included in the counseling data. For example, the consultation data says, “Yesterday, I was injured and was hospitalized, and the bone on my left arm was broken. In the case of including the sentence "Can you?", the counseling summary result may be "insurance in case of bone fracture" or "insurance in case of hospitalization", which is a combination of at least some words. The consultation summary result according to an embodiment of the present disclosure may include a combination of at least some sentences included in the customer consultation data. In the above example, the summary information may be a combination of at least some sentences included in the customer service data, "I broke my left arm bone. The detailed description of the above-mentioned counseling summary result is only an example, and the present disclosure is not limited thereto.

Hereinafter, a method for the processor 120 to determine a type code for counseling data will be described.

The type code may be information for classifying the intention of counseling included in the counseling data. The memory 130 may store a type code corresponding to each of the counseling intentions included in the counseling data. That is, the counseling data collected when the counselor and the customer perform counseling for a specific service may be classified into a predetermined type. The counseling data may be classified into at least one type code stored in the memory 130 . For example, the consultation data may be classified into one or more type codes based on three depths. The three depths may include a large classification, a medium classification, and a small classification for the counseling data. For example, a major category may be insurance, annuity, branch finding, contract inquiry, and insurance claim. A major category included in the major insurance category may be health insurance, retirement preparation, and raising a large sum of money, and a subcategory included in the health insurance category may be cancer insurance. , actual expenses insurance, and the like. The type code may include, for example, keywords, numbers, letters, and the like. For example, the consultation data says, “Yesterday, I was injured and was hospitalized, and the bone on my left arm was broken. When including the sentence "Can you?", the type code information may include a type code for "Insurance claim - insurance type - coverage". Specific description of the above type code is only an example, and the present disclosure is not limited thereto.

Hereinafter, a method of determining a type code for consultation data will be described.

According to an embodiment of the present disclosure, the processor 120 may determine the type code based on input of the type code of at least one of the customer terminal and the agent terminal. The processor 120 may receive the type code from at least one of the customer terminal and the agent terminal. For example, the customer may enter the type code according to the guidance from the automatic answering system before starting the telephone consultation with the agent. For example, voice guidance may be provided to the customer through an automated response system for type codes. The customer may speak or input a type code corresponding to his/her own consultation intention among voice-guided type codes. Alternatively, for example, the customer may input or click the type code according to the guidance from the automatic input guidance system before starting the consultation using text messages (eg, chatting, etc.) with the counselor. The processor 120 may display a display object (eg, an icon) capable of receiving a user input for type codes on the user interface. Users may click a display object of a type code corresponding to their consultation intention among a plurality of type codes displayed on the chatting window. For example, an agent may select a type code during a conversation with a customer. Specific description of the above type code is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 120 may determine the type code by using a type code determination model including one or more pre-trained network functions.

The type code determination model can be calculated with consultation data as input. The type code determination model may output a type code corresponding to the consultation data. The type code determination model may be a model trained to output a type code using past consultation data. The type code determination model may be a model trained using past counseling data as an input and learning data using a type code stored in correspondence with the past counseling data as a label.

The type code determination model may output a type code related to the consultation data by identifying a relationship between two or more semantic units included in the consultation data.

The type code determination model may include a first sub-model for identifying a relationship between two or more semantic units included in the counseling data. The semantic unit may mean at least a part of a sentence that may have a meaning. For example, the semantic unit may be a phoneme, a syllable, a word, a phrase, or the like. The output value output through the function activated in the node of the hidden layer included in the first sub-model is input to the node included in the next layer of the hidden layer, and also the next operation performed at the node of the hidden layer It can be re-entered by input of . A node included in the hidden layer may perform a recursive operation using, as its input, an output value output from a node included in the hidden layer according to an operation at a previous point in time. The first sub-model may recognize a relationship between two or more semantic units by recursively performing an operation on the semantic units included in the counseling data. The processor 120 may calculate two or more semantic units included in the consultation data as an input of the first sub-model. The processor 120 may output related semantic units among two or more semantic units using the first sub-model. That is, the processor 120 may output a relationship between two or more semantic units that have a correlation among a plurality of semantic units included in the counseling data by using the first sub-model and can determine the meaning of the counseling data. . The first sub-model may include, for example, a recurrent neural network (RNN) and a many-to-many RNN. The recurrent neural network may be a network model that outputs a prediction result whenever one step is performed, and updates the prediction result again when the next step is performed. The many-to-many recurrent neural network may be a recurrent neural network model that receives a plurality of inputs and outputs a plurality of outputs. For example, two or more semantic units included in the consultation data may be input to the many-to-many recurrent neural network. In addition, two or more semantic units having a relationship may be output from the many-to-many recurrent neural network. A detailed description of the aforementioned recurrent neural networks and many-to-many recurrent neural networks can be found in DNT How, KSM Sahari, Hu Yuhuang and Loo Chu Kiong, “Multiple sequence behavior recognition on humanoid, which is incorporated herein by reference in its entirety. robot using long short-term memory (LSTM)," 2014 IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), Kuala Lumpur, 2014, pp. 109-114. is discussed in more detail in The detailed description of the above-described first sub-model is merely an example, and the present disclosure is not limited thereto.

The type code determination model may include a second sub-model for outputting a type code based on a relationship between two or more semantic units. The second sub-model may output a type code based on a relationship between two or more semantic units output from the first sub-model. The second sub-model may output a type code by calculating an input of two or more semantic units having a relationship. That is, the second sub-model may determine the type of counseling data by analyzing two or more semantic units having a semantic relationship included in the counseling data. The processor 120 may operate by inputting two or more semantic units to a plurality of input nodes included in the input layer. Alternatively, the second sub-model may output a type code by calculating an input obtained by vectorizing a relationship between two or more semantic units. The processor 120 may convert two or more semantic units into word-to-vector (Word2Vec). The processor 120 may generate an auxiliary vector representing a relationship between two or more transformed vectors and additionally input the auxiliary vector to the second sub-model. For example, the auxiliary vector may indicate a degree of similarity between semantic units, a subject-predicate relationship, and the like. The second sub-model may include, for example, a convolutional neural network (CNN). A convolutional neural network may include one or more convolutional layers and subsampling layers. The convolutional neural network may extract features from input data by repeatedly performing a convolutional process and a subsampling process (eg, the aforementioned max pooling, etc.). Through an iterative convolutional process and subsampling process, a neural network can extract global features of input data. An output of the convolutional layer or the subsampling layer may be input to a fully connected layer. A fully connected layer is a layer in which all neurons in one layer and all neurons in neighboring layers are connected. The fully connected layer may mean a structure in which all nodes of each layer are connected to all nodes of other layers in a neural network. A description of a specific configuration for a convolutional neural network is discussed more specifically in US Patent No. US9870768B2, which is incorporated herein by reference in its entirety. The detailed description of the above-described second sub-model is merely an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 120 may determine the type code by comparing at least one of the main words or main sentences related to the counseling data with the words or sentences for each type code stored in advance.

The key word may be a word with high importance in classifying the customer's consultation intention among two or more words included in the consultation data. For example, the consultation data says, “Yesterday, I was injured and was hospitalized, and the bone on my left arm was broken. When including the sentence "Can you?", the key words may be "bone", "broken", "premium", "insurance", "subscription". Specific descriptions of the above key words are only examples, and the present disclosure is not limited thereto.

The main sentence may be a sentence having high importance for classifying the customer's counseling intention among two or more sentences included in the counseling data. For example, when there are sentences with high similarity among two or more sentences included in the counseling data, the processor 120 may determine only one representative sentence as the main sentence. For example, the processor 120 may determine a sentence including a plurality of words matching the type code among two or more sentences included in the counseling data as the main sentence. In the above example, the main sentence may be "I signed up for that insurance at the same time, can I get insurance?" Specific description of the above-mentioned main sentences is only an example, and the present disclosure is not limited thereto.

Hereinafter, a method for the processor 120 to pre-process counseling data according to an embodiment of the present disclosure will be described.

The processor 120 may perform pre-processing on the consultation data. The preprocessing may include an operation of removing syllables from which a customer intention cannot be derived from among syllables included in the counseling data in order to determine key words related to the counseling data. The processor 120 may pre-process the consultation data using natural language processing. Specifically, the processor 120 may perform pre-processing through morphological analysis on the consultation data. The processor 120 may remove a syllable from which a customer intention cannot be derived from the stemmed analysis of the consultation data. The syllable from which the customer's intention cannot be derived may be, for example, a syllable corresponding to a proposition, a suffix, or the like. The processor 120 may perform pre-processing to include a syllable capable of deriving a customer consultation intention with respect to the consultation data. The syllable from which the customer consultation intention can be derived may be, for example, a syllable corresponding to a noun, a verb, an adjective, or the like. For example, if the customer service data is "I signed up for the same insurance at that time, can I also receive the insurance?" , "insurance premium", "receive" can be preprocessed to include only. The detailed description of the above-described pretreatment is merely an example, and the present disclosure is not limited thereto.

Hereinafter, a method for the processor 120 to determine a key word based on the frequency of use of the word included in the consultation data according to an embodiment of the present disclosure will be described.

The processor 120 may determine the frequency of use of words included in the consultation data. The processor 120 may determine the frequency of use of words included in the pre-processed counseling data.

The processor 120 may determine the frequency of use based on the number of times the same word is included in the consultation data. The processor 120 may determine that the frequency of use is high when the number of times that the same word is included in the consultation data is equal to or greater than a predetermined threshold, or a word corresponding to a higher number of times among the use times of the words included in the consultation data. You may decide to use them frequently. For example, the processor 120 may classify the frequency of use as high, low, etc., or may determine the frequency of use as a value corresponding to the number of uses. 4, the word "insurance" was used 80 times in the consultation data, the word "treatment cost" was used 24 times, the word "traffic accident" was used 13 times, and " "injury" may have been used 18 times. According to an embodiment of the present disclosure, if it is determined that the frequency of use is high for words that are used more than 20 times, the processor 120 may determine that the frequency of use for the words “insurance” and “treatment cost” is high. have. According to another embodiment of the present disclosure, when it is determined that the words belonging to the top three frequencies of use are high in frequency of use, the processor 120 provides information about the words "insurance", "treatment cost" and "injury". The frequency of use may be determined to be high. The specific description regarding the frequency of use of the above-mentioned words is merely an example, and the present disclosure is not limited thereto.

Even when the same word or a word having a similar meaning is included in the counseling data in a modified form, the processor 120 may determine the frequency of use by determining that the same word is mentioned. The modified word may be, for example, a word having a different spacing, a word having a different ending, or the like. For example, the processor 120 may determine the frequency of use by determining "hospitalization fee" and "hospitalization fee" as the same word. Also, for example, the processor 120 may determine the frequency of use by determining the hospitalization fee and the hospital fee as similar words. The specific description regarding the frequency of use of the above-mentioned words is merely an example, and the present disclosure is not limited thereto.

The processor 120 may determine a key word related to the consultation data based on the frequency of use of the words. The processor 120 may determine a key word based on words that are frequently used. The processor 120 may determine words having a higher frequency of use as main words. For example, when the number of times of use for each of the words included in the counseling data is 24, 25, 1, 6, 14, 5, and 4, the processor 120 uses the words corresponding to the number of times 24 and 25 It may be determined that the frequency is high, and words corresponding to the number of times 24 and 25 may be determined as the main words. The detailed description of the above-described key word determination is merely an example, and the present disclosure is not limited thereto.

Hereinafter, a method for the processor 120 to determine a key word based on the degree of simultaneous appearance of words included in counseling data according to an embodiment of the present disclosure will be described.

The processor 120 may perform pre-processing on the consultation data as described above. The processor 120 may determine the main word based on the degree of simultaneous appearance of words included in the preprocessed counseling data.

When the distance between words included in the consultation data is equal to or less than a predetermined value, the processor 120 may determine a relationship of simultaneous appearance of words. When the distance between words included in the pre-processed counseling data is equal to or less than a predetermined value, the processor 120 may determine the co-occurrence relationship of words. The co-occurrence relationship may be information on whether a distance between words included in the counseling data is equal to or less than a predetermined value. For example, if the consultation data is "I was hospitalized yesterday because of an injury, and my left arm bone was broken", and the predetermined value is 3, the distance between the words "injured" and "hospitalized" is 2, so the processor 120 ) may determine that “injured” and “hospitalized” are in a co-occurrence relationship, and since the distance between the words “injured” and “bone” is 5, the processor 120 determines that “injured” and “bone” are co-occurring. can be determined not to exist. The detailed description of the above-mentioned co-appearance relationship is only an example, and the present disclosure is not limited thereto.

The processor 120 may perform post-processing on the words based on the degree of simultaneous appearance of the words. Post-processing may refer to an operation of transforming words according to the degree of simultaneous appearance of the words. The post-processing may include grouping into one word when the degree of simultaneous appearance of words is high. When the distance between words is 1, the processor 120 may determine an adjacent word relationship. The processor 120 may re-define the words as one word by grouping the words in the case of the words determined as the adjacent word relationship more than a predetermined threshold number of times. For example, when a case in which the distance between the words "actual cost" and "insurance" is 1 is found 5 times in the counseling data, the processor 120 may calculate that the word relationship is determined 5 times. The processor 120 may determine that the words "actual expenses" and "insurance" are determined as adjacent words more than a predetermined threshold number of times, group them into "actual expenses insurance" and redefine them as one word. The detailed description of the post-processing operation described above is merely an example, and the present disclosure is not limited thereto.

The processor 120 may determine a key word related to the consultation data based on the degree of simultaneous appearance of the words. Hereinafter, a method of determining a key word related to counseling data based on the degree of simultaneous appearance of words will be described with reference to FIGS. 3 and 4 .

The processor 120 may generate two or more nodes corresponding to each of two or more words included in the consultation data. The processor 120 may generate two or more nodes corresponding to each of two or more words in consideration of a post-processing operation on the consultation data. The processor 120 may generate a word redefined as one word as one node based on the post-processing operation. A circle corresponding to each of A, B, C, and D in FIG. 3A may be a node. Each of A, B, C, and D may correspond to each of the words included in the counseling data. For example, if the consultation data is "Yesterday, I was hospitalized because I was injured, and my left arm bone was broken." You can create a node corresponding to each of ", "bone", and "broken". The detailed description of the above-mentioned node is only an example, and the present disclosure is not limited thereto.

The processor 120 may generate an edge connecting nodes of words having a co-occurrence relationship. According to an embodiment of the present disclosure, the processor 120 may generate an edge connecting nodes corresponding to each of words having a co-occurrence relationship. According to another embodiment of the present disclosure, the processor 120 may generate an edge only for words having a co-occurrence relationship more than a predetermined number of times. A line connecting between nodes A and B in FIG. 3A may be an edge. In this example, the words for each of A-B, A-D, B-D, and C-D may be words having a co-occurrence relationship, or words having co-occurrence more than a predetermined number of times. The detailed description of the above-described edge is only an example, and the present disclosure is not limited thereto.

The processor 120 may equally distribute a weight of 1 to each of the two or more nodes. In FIG. 3A , the processor 120 equally distributes a weight of 1 to each of nodes A, B, C, and D, so that each of the nodes may have received a weight of 0.25. The detailed description of the above-described weights is only an example, and the present disclosure is not limited thereto.

The processor 120 may calculate a weight for each edge. The processor 120 may calculate to distribute the weights of each node equally to the edges connected to the node. In FIG. 3B , the processor 120 may calculate to equally distribute the weight 0.25 for the node A to each of the two edges connected to the node B and the node D. The processor 120 may calculate to distribute the weight 0.25 of node A to each edge by 0.125. The processor 120 may calculate to evenly distribute a weight of 0.25 for node D to each of the three edges connected to each of nodes A, B, and C. The processor 120 may calculate to distribute the weight 0.25 of the node D to each edge by 0.083. In FIG. 3(b) , the edge weight calculation with respect to the B node and the C node is omitted. The detailed description of the above-described edge weight calculation is merely an example, and the present disclosure is not limited thereto.

The processor 120 may calculate the importance of each of the two or more nodes based on the weight of the edge. The processor 120 may calculate the importance of the node by multiplying the weight of the node by a predetermined first probability and adding each value obtained by multiplying the weight of the edge connected to the node by the predetermined second probability. A sum of the first predetermined probability and the second predetermined probability may be 100 percent. The initial importance value for node B is calculated by multiplying the weight of node B (0.25) by a first predetermined probability (0.15), and the edge weight between node B and node A (0.125) and the edge weight between node B and node D It may be a sum ((0.125+0.083)*0.85+(0.25)*0.15=0.214) of each value obtained by multiplying a value obtained by adding (0.083) to a predetermined second probability (0.85). In FIG. 3(c) , the initial importance values obtained by performing the calculation for each node in the same manner may be 0.214 for the A node, 0.214 for the B node, 0.108 for the C node, and 0.463 for the D node. The processor 120 may calculate the weight of the edge based on the initial importance value of each node and repeat the process of calculating the importance again. If the importance value is repeatedly calculated several times, the importance value may converge to one value for each node. When the importance value converges to one value for each node, the processor 120 may finally determine the corresponding value as the importance value for the node. The specific description regarding the above-mentioned importance value is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 120 may determine a key word based on the importance of each of two or more nodes. According to an embodiment of the present disclosure, the processor 120 may determine, as a key word, a word corresponding to nodes having an importance greater than or equal to a predetermined threshold value among nodes. According to another embodiment of the present disclosure, the processor 120 may determine a word corresponding to nodes having a higher importance value among the nodes as the main word. Referring to the importance 410 of FIG. 4 , the importance value of the node corresponding to the word “insurance” is 0.089849, the importance value of the node corresponding to the word “treatment cost” is 0.026183, and the node corresponding to the word “traffic accident” The importance value of may be 0.017231. According to an embodiment of the present disclosure, when a word having an importance value equal to or greater than a predetermined threshold value of 0.02 is determined as a key word, the processor 120 may determine the words “insurance” and “treatment cost” as key words. According to another embodiment of the present disclosure, when determining words having the top three importance values as key words, the processor 120 may determine the words “insurance”, “treatment cost” and “traffic accident” as key words. . Specific descriptions of the above key words are only examples, and the present disclosure is not limited thereto.

Hereinafter, a method for the processor 120 to determine a main sentence based on the similarity of sentences included in the counseling data according to an embodiment of the present disclosure will be described.

According to an embodiment of the present disclosure, the processor 120 may determine one sentence among two or more sentences having a high similarity included in the counseling data as the representative sentence. The processor 120 may determine a main sentence regarding the counseling data based on the representative sentence. The representative sentence may mean one sentence that can represent two or more sentences with high similarity. For example, the processor 120 may say, "I called to inquire about whether I can receive premiums with the insurance I have purchased." Since the matching rate of the words in the sentence and the sentence "I signed up for that insurance at the same time, can I also get insurance?" sentences is high, it can be determined that the similarity between the two sentences is high. The processor 120 responds to the two sentences, "I called to inquire about whether I can receive premiums with the insurance I subscribed to." A sentence can be determined as a representative sentence. The determination of similarity between sentences will be described later in detail. The processor 120 may determine a representative sentence of at least some of the representative sentences as the main sentence. Specific description of the above-mentioned main sentences is only an example, and the present disclosure is not limited thereto.

The processor 120 may calculate a degree of similarity between two or more sentences included in the counseling data. According to an embodiment of the present disclosure, the processor 120 may calculate the similarity by performing analysis based on the meaning and arrangement of one or more words included in each of the sentences, and the relationship between each word. The processor 120 may calculate the similarity based on the matching rate of the meaning and arrangement of one or more words included in each of the sentences. The processor 120 may determine that the higher the matching rate, the higher the similarity. According to another embodiment of the present disclosure, the processor 120 may calculate the similarity between two sentences using natural language processing. The processor 120 may calculate the similarity between the two sentences by calculating the similarity between the sentence vectors by calculating the sentence vector for each of the two sentences. For example, if the consultation data says, “I called to ask if I could receive insurance premiums with the insurance I signed up for. Yesterday, I was injured and was hospitalized, and the bone in my left arm was broken. In the case of including the sentences, "I signed up for the insurance at the same time, can I also receive insurance?", the processor 120 says, "I called to inquire about whether I can receive insurance with the insurance I have purchased." Since the matching rate of the words in the sentence and the sentence "I signed up for that insurance at the same time, can I also get insurance?" sentences is high, it can be determined that the similarity between the two sentences is high. The detailed description of the above-described sentence similarity is only an example, and the present disclosure is not limited thereto.

The processor 120 may generate two or more nodes corresponding to each of two or more sentences included in the consultation data. Hereinafter, it will be described with reference to FIG. 3 . A circle corresponding to each of A, B, C, and D in FIG. 3A may be a node. Each of A, B, C, and D may correspond to each of the sentences included in the counseling data. The detailed description of the above-mentioned node is only an example, and the present disclosure is not limited thereto.

The processor 120 may generate an edge connecting nodes of sentences having a similar relationship. The processor 120 may generate an edge only for nodes corresponding to each of the sentences having a similarity greater than or equal to a predetermined threshold value. A line connecting between nodes A and B in FIG. 3A may be an edge. In this example, sentences for each of A-B, A-D, B-D, and C-D may be sentences having a similar relationship (eg, two sentences having a similarity greater than or equal to a predetermined threshold). The detailed description of the above-described edge is only an example, and the present disclosure is not limited thereto.

The processor 120 may equally distribute a weight of 1 to each of the two or more nodes. The processor 120 may calculate a weight for each edge. The processor 120 may calculate the importance of each of the two or more nodes based on the weight of the edge. A method of distributing a weight, calculating a weight for an edge, and calculating an importance for each node is the same as described above.

The processor 120 may determine the main sentence based on the importance for each of the two or more nodes. According to an embodiment of the present disclosure, the processor 120 may determine, as the main sentence, a sentence corresponding to nodes having an importance greater than or equal to a predetermined threshold value among the nodes. According to another embodiment of the present disclosure, the processor 120 may determine a sentence corresponding to nodes having a higher importance value among the nodes as the main sentence. For example, the importance value of the node corresponding to the sentence "I called to inquire about whether I can receive premiums with the insurance I subscribed to" is 0.24, and the importance value of the node corresponding to the sentence "I was hospitalized yesterday because I was injured" is If it is 0.01 and the importance value of the node corresponding to the sentence “I broke my left arm bone” is 0.18, the sentence corresponding to the node with high importance value is “I called to inquire about whether I can receive insurance with my insurance” can be determined as the main sentence. Specific description of the above-mentioned main sentences is only an example, and the present disclosure is not limited thereto.

One or more words or sentences for each type code may be stored in the memory 130 . For example, words such as 'discount', 'non-smoking period', and 'blood sugar' may be matched and stored for the type of 'inquiry about insurance premium discount'. Or, for example, for the type of 'Inquiry about premium discount', 'How do I get a discount?', 'Can I get a discount?' Such sentences may be matched and stored. Specific descriptions of words or sentences for each type code described above are merely examples, and the present disclosure is not limited thereto.

The processor 120 may compare the main words or main sentences extracted based on the counseling data with the words or sentences stored by matching for each type code. The processor 120 may determine a main word or main sentence and a type code having the most same word or the same sentence as the type code for the consultation data. The processor 120 compares the main word or main sentence with the semantic similarity of the word or sentence stored in the memory 130, and determines the type code having the highest semantic similarity of the word or sentence as the type code for the consultation data. have. The semantic similarity may be determined by vectorizing sentences or words and calculating a distance between the vectorized sentences or words. The detailed description of the above-described type code determination is merely an example, and the present disclosure is not limited thereto.

The processor 120 may determine a format corresponding to the consultation data by using the pre-stored format for each type code.

The format by type code may be data in which items frequently appearing by type code are arranged. The processor 120 may output a counseling summary result using a format for each type code. When counseling is performed on a specific field, the content of counseling can be standardized by type of counseling. A standardized format may be stored in the memory 130 . The processor 120 may summarize and organize the consultation data to correspond to the format. A format for each type code will be described below with reference to FIG. 2 .

A format per type code may contain one or more items. In each of the two or more formats, items frequently appearing when performing counseling corresponding to the corresponding format may be stored. There may be items in common to two or more forms, or there may be different items.

The item may be a superset of related consultation contents. The consultation content may mean at least a part of consultation data. The one or more items may include at least one of a customer basic information related item, a customer inquiry related item, an agent response related item, a consultation target related item, or a cost related item. The customer basic information related items may be consultation contents for distinguishing customers from other customers. For example, the customer basic information related item may be a customer age item, a customer name item, a customer disease item, and the like. The summary information for the customer's disease item may include no history of heart disease, no history of liver disease, and history of family dementia. The customer inquiry-related item may be a customer's main inquiry. For example, a customer inquiry related item may be matched with summary information such as whether insurance premium discount is applicable, documents required for insurance premium discount application, and the like. The agent response related item may be associated with an additional action performed by the agent in response to a customer inquiry. For example, the item related to the agent response may be matched with summary information such as a change in customer information according to a customer request and a guide to documents required for insurance premium discount. The item related to the subject to be consulted may be an item related to the subject to be consulted. The consultation target may be product-related content provided by the service. For example, the item related to the consultation target may be a product category, a product name, and the like. For example, the items related to the consultation target may be matched with summary information such as protection-type insurance, actual cost insurance, and type A actual cost insurance. Specific description of the above items is only an example, and the present disclosure is not limited thereto.

Referring to FIG. 2, for example, types and items will be described. 2( a ) may be a format for a type code of an insurance premium discount inquiry. When consulting on insurance premium discount inquiries, frequently asked questions may include insurance membership, non-smoking period, blood pressure, blood sugar, and body mass (BMI), and related items may be included in the insurance premium discount inquiry form. 2(b) may be a format for a specific stroke-corresponding disease inquiry. When consulting on which diseases are included in the 'specific stroke' listed in the insurance policy, frequently asked questions may be the name of the product, whether it is a non-distributive or non-refundable type, and the name of the disease. may be included. For example, the formats for two or more type codes may include a customer inquiry item and an agent response item in common. Specific descriptions of the above-described forms and items are merely examples, and the present disclosure is not limited thereto.

The processor 120 may extract summary information corresponding to each of one or more items included in the format from the consultation data.

According to an embodiment of the present disclosure, the processor 120 may extract the summary information by calculating the consultation data and item information using a summary information determination model including one or more pre-trained network functions. The summary information determination model may be a model trained to output summary information by calculating at least one of main words or main sentences and item information related to the counseling data. The main word or main sentence may be extracted as described above. The summary information determination model may determine which content corresponds to the item information by using main words or main sentences and item information extracted from the counseling data. The item information is information about the item, and may be data obtained by vectorizing the description of the item, or a code matched for each item. That is, the summary information determination model may calculate the vectorized main word or main sentence and item information that is a superset of content to be extracted from the main word or main sentence. The summary information determination model may be a recurrent neural network as described above. The summary information determination model may output content corresponding to item information among main words or main sentences. The detailed description of the above-described summary information determination model is merely an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 120 may extract summary information by comparing at least one of a main word or a main sentence related to the counseling data with the pre-stored summary information for each item. The processor 120 may extract the main words or main sentences related to the consultation data as described above. The memory 130 may store summary information for each item in advance. The processor 120 may determine summary information having a high degree of correspondence with a main word or main sentence from among the summary information stored in the memory 130 as summary information of the corresponding consultation data. When consulting for one service is performed, the number of pieces of summary information that can be derived from one item may be limited. For example, summary information that can be derived for the product name item may exist as much as the number of products provided by the service. For example, the memory 130 may have product A, product B, and product C matched to the product name item. And the main word extracted from the counseling data may be B. The processor 120 may determine a product B having a high degree of correspondence with the main word B as summary information on the product name item. The detailed description of the above summary information is only an example, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 120 may extract summary information by using a sentence corresponding to a pre-stored sentence format for each item among sentences included in the counseling data. The memory 130 may store a sentence format that can be used for each item. The sentence format may include, for example, an interrogative sentence, a declarative sentence, and a negative sentence. For example, the customer inquiry item may be stored by matching the interrogative sentence form among the customer utterance sentences. The processor 120 may extract summary information on the customer inquiry item by using an utterance sentence corresponding to the interrogative sentence form among the utterance sentences of the customer. For example, in order to check whether insurance premiums are discounted, an agent may ask a customer for a blood sugar level, and the customer may answer their own blood sugar level. The memory 130 may store the customer's declarative sentence format, which is matched to the blood sugar item and uttered after the counselor's interrogative sentence format utterance. When there is a customer's utterance in the declarative sentence form after the counselor's utterance in the interrogative sentence form, the processor 120 may extract summary information on the blood sugar item by using the customer uttered sentence in the descriptive sentence form. Specific details regarding extraction of summary information according to the above-described sentence format are merely examples, and the present disclosure is not limited thereto.

According to an embodiment of the present disclosure, the processor 120 may extract summary information by using a sentence including a semantic unit corresponding to a keyword for each item stored in advance among semantic units included in the consultation data. In the memory 130 , one or more keywords for each item may be stored in advance. For example, 'how much', 'won', and 'amount' may be stored in the memory 130 as keywords matching items related to insurance payment. For example, summary information on insurance payment related items can be extracted based on the sentence “1 million won will be paid” that includes the keyword 'won'. The processor 120 may extract summary information by analyzing a sentence including the keyword as it is. Alternatively, the processor 120 may extract summary information by analyzing a sentence including a semantic unit corresponding to the keyword. That is, even if the keyword stored in the memory 130 does not match the keyword included in the customer's utterance, if the content has the same semantic unit in context, the summary information may be extracted using the corresponding sentence. The detailed description of the above-described abstract information extraction is only an example, and the present disclosure is not limited thereto.

The processor 120 may generate a counseling summary result including one or more summary information. When summary information for each of one or more items included in the format is extracted, the processor 120 may generate a counseling summary result by using the extracted summary information. The processor 120 may generate the counseling summary result by filling in the blank in the form with summary information. For example, in the format of FIG. 2A , the processor 120 may generate a counseling summary result by writing a blank part corresponding to each item as summary information. The detailed description of the above-mentioned counseling summary result is only an example, and the present disclosure is not limited thereto.

The processor 120 may determine to deliver the consultation summary result to the customer terminal. The processor 120 may transmit the consultation summary result to the customer terminal through the network unit 110 . For example, the processor 120 may transmit the consultation summary result to the customer terminal using a messenger after the telephone consultation is finished. Alternatively, after the chatting consultation is finished, the consultation summary result may be transmitted to the customer terminal using the corresponding chatting channel. The detailed description regarding the delivery of the above-mentioned counseling summary result is only an example, and the present disclosure is not limited thereto.

The customer may receive a consultation summary result after consulting with the agent. By receiving the consultation summary result, the customer does not need to memorize the consultation contents one by one. In addition, it is possible to check with what content the consultation was conducted later or what kind of reply was received. By delivering the result of the consultation summary to the customer, it is possible to solve the inconvenience of taking notes during a call. In addition, it is possible to prevent the customer from repeatedly inquiring about the same content, thereby relieving the burden of work in the call center.

The following is a description of customer feedback corresponding to the consultation summary result.

The processor 120 may receive feedback regarding the counseling summary result. The processor 120 may receive feedback regarding the consultation summary result from the customer terminal.

The feedback may include an evaluation of at least a portion of the counseling summary results. The feedback may include satisfaction with the counseling summary result. For example, satisfaction may be expressed as a quantitative measure (eg, score, rating, etc.). The feedback may include satisfaction with some of the counseling summary results. For example, satisfaction may be evaluated differently for each of the first item and the second item among the counseling summary results, or satisfaction may be evaluated for only one item. Or, for example, satisfaction may include a description of customer satisfaction. For example, the processor 120 may receive a customer input such as 'like' and 'not very good' as feedback. The detailed description of the above feedback is only an example, and the present disclosure is not limited thereto.

The processor 120 may determine to update the type code determination method when the negative feedback is equal to or greater than a threshold value. If the negative feedback is too high, the processor 120 may determine that the type code itself is incorrectly determined. The processor 120 may update the method for determining the type code. Alternatively, the processor 120 may update both the method for determining the type code and the method for extracting summary information.

When the negative feedback is less than a threshold value, the processor 120 may determine to update the summary information extraction method. When there is some negative feedback, but the degree is not too severe, the processor 120 may determine that the type code has been properly determined, but some content (ie, summary information) included in the type code has been incorrectly extracted. The processor 120 may update the summary information extraction method.

The feedback may include corrections regarding at least a portion of the counseling summary results. The feedback may include correction of at least some of the summary information included in the counseling summary result. The customer can check the result of the consultation summary and, if there are some incorrect parts, correct the part. The processor 120 may receive a correction for at least a portion of the summary information from the customer terminal. The processor 120 may update the summary information extraction method by using the corrected information.

The following is a description of a method for the processor 120 to update the consultation data analysis method based on customer feedback.

The processor 120 may update at least one of a method for determining a type code and a method for extracting summary information based on the feedback. The processor 120 may update at least one of the method for determining the type code and the method for extracting summary information based on at least one of a predetermined time unit or a predetermined feedback degree. The processor 120 may update the method for determining the type code or the method for extracting summary information at regular intervals. The processor 120 may update the method for determining the type code or the method for extracting summary information when the negative feedback is received above the threshold value or the customer's correction information is received above the threshold value. That is, when there is a sufficient amount to generate new training data using customer feedback, new training data may be generated, and a method for determining a type code or a method for extracting summary information may be updated. The detailed description of the above feedback is only an example, and the present disclosure is not limited thereto.

The processor 120 may store the counseling summary result in the memory 130 . The processor 120 may store the counseling summary result in the memory 130 in order to use the counseling summary result for another purpose according to the feedback on the counseling summary result. For example, if the feedback is positive, the counseling summary result may be stored, and the processor 120 may be used as future learning data or used for trend analysis. Alternatively, for example, if the feedback is negative, the counseling summary result may be stored, and the processor 120 may later use it as learning data including the correction result. That is, when the counseling summary result is normal, it can be stored in the memory 130 to learn a model for extracting the counseling summary result later, and when the counseling summary result is abnormal, using the later corrected data as a new label It may be stored in the memory 130 in order to train a model for extracting the counseling summary result.

Hereinafter, a method of grasping a trend using consultation data will be described.

The processor 120 may output an analysis result based on the counseling summary result corresponding to two or more different time intervals. The processor 120 may analyze the time-series counseling summary results and output the analysis results. The processor 120 may compare a past consultation summary result with a recent consultation summary result, and output an analysis result. The analysis result may include analysis information regarding at least one of a type code, an item, or summary information. The analysis result may include increase/decrease information in recent data when compared with past data. For example, analysis results may include analysis regarding types or items that have recently increased customer inquiries. The analysis result may include content grouped by a predetermined criterion. For example, the analysis result may include customer group analysis using customer information included in the summary information. The detailed description of the aforementioned trend identification is only an example, and the present disclosure is not limited thereto.

The network unit 110 may transmit/receive data for performing consultation data analysis according to an embodiment of the present disclosure to other computing devices, servers, and the like. The network unit 110 may transmit/receive customer consultation data and the like to other computing devices, servers, and the like in order to analyze the consultation data. In addition, the network unit 110 may enable communication between a plurality of computing devices so that learning of a network function is performed in a distributed manner in each of the plurality of computing devices. The network unit 110 may enable communication between a plurality of computing devices so that generation of analysis data using a network function may be distributed and processed.

In the present disclosure, the network unit 110 may be configured regardless of its communication mode, such as wired and wireless, and may be configured with various communication networks such as a personal area network (PAN) and a wide area network (WAN). can In addition, the network may be a well-known World Wide Web (WWW), and may use a wireless transmission technology used for short-range communication, such as infrared (IrDA) or Bluetooth (Bluetooth). The techniques described herein may be used in the networks mentioned above, as well as in other networks.

The processor 120 may include one or more cores, and a central processing unit (CPU) of a computing device, a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU). unit), such as counseling data analysis, may include a processor for deep learning. The processor 120 may read the computer program stored in the memory 130 to perform counseling data analysis according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 120 may perform an operation for learning the neural network. The processor 120 is for learning of the neural network, such as processing input data for learning in deep learning (DN), extracting features from the input data, calculating an error, and updating the weight of the neural network using backpropagation. calculations can be performed. At least one of a CPU, a GPGPU, and a TPU of the processor 120 may process learning of a network function. For example, the CPU and the GPGPU can process learning of a network function and analysis of counseling data using the network function together. In addition, in an embodiment of the present disclosure, learning of a network function and analysis of counseling data using the network function may be processed by using the processors of a plurality of computing devices together. In addition, the computer program executed in the computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

According to an embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 120 and any type of information received by the network unit 110 .

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, a hard disk type, a multimedia card micro type, or a card type memory (eg, SD or XD memory, etc.), Random Access Memory (RAM), Static Random Access Memory (SRAM), Read-Only Memory (ROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Programmable Read (PROM) -Only Memory), a magnetic memory, a magnetic disk, and an optical disk may include at least one type of storage medium. The computing device 100 may operate in relation to a web storage that performs a storage function of the memory 130 on the Internet. The description of the above-described memory is only an example, and the present disclosure is not limited thereto.

5 is a flowchart of a counseling data analysis method according to an embodiment of the present disclosure.

The computing device 100 may determine 510 a type code for the consultation data.

The computing device 100 may determine ( 520 ) a format corresponding to the consultation data by using the pre-stored format for each type code.

The computing device 100 may extract 530 summary information corresponding to each of one or more items included in the format from the consultation data. The one or more items may include at least one of a customer basic information related item, a customer inquiry related item, an agent response related item, a consultation target related item, or a cost related item.

The computing device 100 may generate ( 540 ) a consultation summary result including one or more pieces of summary information.

The computing device 100 may receive feedback regarding the consultation summary result. The feedback may include at least one of an evaluation of at least a portion of the counseling summary result or a correction of at least a portion of the counseling summary result.

The computing device 100 may update at least one of a method for determining a type code and a method for extracting summary information based on the feedback, or may store a consultation summary result. The computing device 100 may update at least one of a method for determining a type code and a method for extracting summary information based on at least one of a predetermined time unit or a predetermined feedback degree.

The computing device 100 may output an analysis result based on the counseling summary result corresponding to two or more different time intervals. The analysis result may include analysis information regarding at least one of a type code, an item, or summary information.

6 is a block diagram of a computing device according to an embodiment of the present disclosure.

6 is a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above generally in the context of computer-executable instructions that may be executed on one or more computers, it will be appreciated by those skilled in the art that the present disclosure may be implemented in combination with other program modules and/or as a combination of hardware and software. will be.

Generally, program modules include routines, programs, components, data structures, etc. that perform particular tasks or implement particular abstract data types. In addition, those skilled in the art will appreciate that the methods of the present disclosure can be applied to single-processor or multiprocessor computer systems, minicomputers, mainframe computers as well as personal computers, hand-held computing devices, microprocessor-based or programmable consumer electronics, etc. (each of which is It will be appreciated that other computer system configurations may be implemented, including those that may operate in connection with one or more associated devices.

The described embodiments of the present disclosure may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Any medium accessible by a computer may be a computer-readable medium. Computer-readable media includes volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. includes media. Computer storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device or other magnetic storage device; or any other medium that can be accessed by a computer and used to store the desired information.

Computer-readable transmission media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as other transport mechanisms, and includes all information delivery media. do. The term modulated data signal means a signal in which one or more of the characteristics of the signal is set or changed so as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1100 implementing various aspects of the disclosure is shown including a computer 1102 , the computer 1102 including a processing unit 1104 , a system memory 1106 , and a system bus 1108 . do. The system bus 1108 couples system components, including but not limited to system memory 1106 , to the processing device 1104 . The processing device 1104 may be any of a variety of commercially available processors. Dual processor and other multiprocessor architectures may also be used as processing unit 1104 .

The system bus 1108 may be any of several types of bus structures that may further be interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112 . A basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, EEPROM, etc., which is the basic input/output system (BIOS) that helps transfer information between components within computer 1102, such as during startup. contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

Computer 1102 may also be configured for external use within an internal hard disk drive (HDD) 1114 (eg, EIDE, SATA) - this internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes, magnetic floppy disk drive (FDD) 1116 (eg, for reading from or writing to removable diskette 1118), and optical disk drive 1120 (eg, CD-ROM) for reading from, or writing to, disk 1122, or other high capacity optical media such as DVD. The hard disk drive 1114 , the magnetic disk drive 1116 , and the optical disk drive 1120 are connected to the system bus 1108 by the hard disk drive interface 1124 , the magnetic disk drive interface 1126 , and the optical drive interface 1128 , respectively. ) can be connected to The interface 1124 for external drive implementation includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer readable media provide non-volatile storage of data, data structures, computer executable instructions, and the like. In the case of computer 1102, drives and media correspond to storing any data in a suitable digital format. Although the description of computer readable media above refers to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will use zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other tangible computer-readable media such as etc. may also be used in the exemplary operating environment and any such media may include computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in the drive and RAM 1112 , including an operating system 1130 , one or more application programs 1132 , other program modules 1134 , and program data 1136 . All or portions of the operating system, applications, modules, and/or data may also be cached in RAM 1112 . It will be appreciated that the present disclosure may be implemented in various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer 1102 via one or more wired/wireless input devices, for example, a pointing device such as a keyboard 1138 and a mouse 1140 . Other input devices (not shown) may include a microphone, IR remote control, joystick, game pad, stylus pen, touch screen, and the like. Although these and other input devices are often connected to the processing unit 1104 through an input device interface 1142 that is connected to the system bus 1108, parallel ports, IEEE 1394 serial ports, game ports, USB ports, IR interfaces, It may be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also coupled to the system bus 1108 via an interface, such as a video adapter 1146 . In addition to the monitor 1144, the computer typically includes other peripheral output devices (not shown), such as speakers, printers, and the like.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148 via wired and/or wireless communications. Remote computer(s) 1148 may be workstations, computing device computers, routers, personal computers, portable computers, microprocessor-based entertainment devices, peer devices, or other common network nodes, and are typically connected to computer 1102 . Although it includes many or all of the components described for it, only memory storage device 1150 is shown for simplicity. The logical connections shown include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, eg, a wide area network (WAN) 1154 . Such LAN and WAN networking environments are common in offices and companies, and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, for example, the Internet.

When used in a LAN networking environment, the computer 1102 is connected to the local network 1152 through a wired and/or wireless communication network interface or adapter 1156 . Adapter 1156 may facilitate wired or wireless communication to LAN 1152 , which also includes a wireless access point installed therein for communicating with wireless adapter 1156 . When used in a WAN networking environment, the computer 1102 may include a modem 1158, be connected to a communication computing device on the WAN 1154, or establish communications over the WAN 1154, such as over the Internet. have other means. A modem 1158 , which may be internal or external and a wired or wireless device, is coupled to the system bus 1108 via a serial port interface 1142 . In a networked environment, program modules described for computer 1102 or portions thereof may be stored in remote memory/storage device 1150 . It will be appreciated that the network connections shown are exemplary and other means of establishing a communication link between the computers may be used.

Computer 1102 may be associated with any wireless device or object that is deployed and operates in wireless communication, for example, printers, scanners, desktop and/or portable computers, portable data assistants (PDAs), communications satellites, wireless detectable tags. It operates to communicate with any device or place, and phone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network or may simply be an ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) makes it possible to connect to the Internet, etc. without a wire. Wi-Fi is a wireless technology such as cell phones that allows these devices, eg, computers, to transmit and receive data indoors and outdoors, ie anywhere within range of a base station. Wi-Fi networks use a radio technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks may operate in unlicensed 2.4 and 5 GHz radio bands, for example, at 11 Mbps (802.11a) or 54 Mbps (802.11b) data rates, or in products that include both bands (dual band). have.

One of ordinary skill in the art of this disclosure will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, instructions, information, signals, bits, symbols and chips that may be referenced in the above description are voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields particles or particles, or any combination thereof.

A person of ordinary skill in the art of the present disclosure will recognize that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein include electronic hardware, (convenience For this purpose, it will be understood that it may be implemented by various forms of program or design code (referred to herein as "software") or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. A person skilled in the art of the present disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be interpreted as a departure from the scope of the present disclosure.

The various embodiments presented herein may be implemented as methods, apparatus, or articles of manufacture using standard programming and/or engineering techniques. The term "article of manufacture" includes a computer program or media accessible from any computer-readable device. For example, computer-readable media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash memory. devices (eg, EEPROMs, cards, sticks, key drives, etc.). Also, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. Based on design priorities, it is understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure. The appended method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art of the present disclosure. The generic principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present disclosure is not intended to be limited to the embodiments presented herein, but is to be construed in the widest scope consistent with the principles and novel features presented herein.

Claims (16)

A computer program stored on a computer readable storage medium, wherein the computer program, when executed on one or more processors, causes the following operations to be performed for analyzing counseling data, the operations comprising:
determining a type code for the consultation data;
determining a format corresponding to the consultation data by using a format for each pre-stored type code;
extracting summary information corresponding to each of one or more items included in the format from the consultation data; and
generating a counseling summary result including one or more summary information;
comprising,
A computer program stored in a computer-readable storage medium.
The method of claim 1,
receiving feedback on the counseling summary result; and
updating at least one of a method for determining a type code and a method for extracting summary information based on the feedback, or storing a result of the consultation summary;
further comprising,
A computer program stored in a computer-readable storage medium.
3. The method of claim 2,
The feedback is:
at least one of evaluating at least a portion of the counseling summary result or correcting at least a portion of the counseling summary result.
A computer program stored in a computer-readable storage medium.
3. The method of claim 2,
Updating at least one of a method for determining a type code and a method for extracting summary information based on the feedback, or storing a result of the consultation summary includes:
determining to update the type code determination method if the negative feedback is greater than or equal to a threshold value; or
determining to update the summary information extraction method when the negative feedback is less than a threshold value;
comprising,
A computer program stored in a computer-readable storage medium.
3. The method of claim 2,
Updating at least one of a method for determining a type code and a method for extracting summary information based on the feedback, or storing a result of the consultation summary includes:
updating at least one of the method for determining the type code or the method for extracting summary information based on at least one of a predetermined time unit or a predetermined feedback degree;
comprising,
A computer program stored in a computer-readable storage medium.
The method of claim 1,
The operation of determining the type code for the consultation data includes:
determining the type code based on input of at least one of a customer terminal and an agent terminal;
determining the type code using a type code determination model including one or more pre-trained network functions; or
determining the type code by comparing at least one of the main words or main sentences related to the counseling data with the words or sentences for each type code stored in advance;
comprising at least one operation of
A computer program stored in a computer-readable storage medium.
7. The method of claim 6,
The type code determination model is:
A first sub-model for identifying a relationship between two or more semantic units included in the consultation data and a second sub-model for outputting the type code based on the relationship between the two or more semantic units,
A computer program stored in a computer-readable storage medium.
7. The method of claim 6,
The key words are:
is determined based on the degree of simultaneous appearance of two or more words included in the consultation data, and
The main sentence above is:
Determined based on a high degree of similarity between sentences included in the counseling data with other sentences,
A computer program stored in a computer-readable storage medium.
The method of claim 1,
The operation of extracting summary information corresponding to each of one or more items included in the format from the consultation data includes:
extracting the summary information by calculating the consultation data and item information using a summary information determination model including one or more pre-trained network functions; or
extracting the summary information by comparing at least one of main words or main sentences related to the counseling data with pre-stored summary information for each item;
comprising at least one operation of
A computer program stored in a computer-readable storage medium.
10. The method of claim 9,
The summary information determination model is:
A model trained to output the summary information by calculating at least one of a main word or a main sentence related to the consultation data, and the item information,
A computer program stored in a computer-readable storage medium.
The method of claim 1,
The operation of extracting summary information corresponding to each of one or more items included in the format from the consultation data includes:
extracting the summary information by using a sentence corresponding to a pre-stored sentence format for each item from among the sentences included in the counseling data; or
extracting the summary information by using a sentence including a semantic unit corresponding to a keyword for each item stored in advance among semantic units included in the counseling data;
comprising at least one operation of
A computer program stored in a computer-readable storage medium.
The method of claim 1,
The one or more items are:
Including at least one of items related to customer basic information, items related to customer inquiries, items related to customer service, items related to customers to be consulted, or items related to costs;
A computer program stored in a computer-readable storage medium.
The method of claim 1,
outputting an analysis result based on the counseling summary result corresponding to two or more different time intervals;
further comprising,
A computer program stored in a computer-readable storage medium.
14. The method of claim 13,
The analysis result is,
comprising analysis information regarding at least one of a type code, item, or summary information;
A computer program stored in a computer-readable storage medium.
A method for analyzing counseling data, comprising:
determining a type code for the consultation data;
determining a format corresponding to the consultation data by using a format for each pre-stored type code;
extracting summary information corresponding to each of one or more items included in the format from the consultation data; and
generating a counseling summary result including one or more summary information;
containing,
Methods for analyzing counseling data.
As a server for analyzing consultation data,
a processor including one or more cores; and
Memory;
including,
The processor is
determine a type code for the consultation data;
Determining a format corresponding to the consultation data using a format for each pre-stored type code,
extracting summary information corresponding to each of one or more items included in the format from the consultation data; and
generating a consultation summary result comprising one or more summary information;
Server for analyzing consultation data.

Images