KR102613862B1 - Method for automatically classifying care coundeling details through natural language precessing, and device thereof - Google Patents

Abstract

The present invention relates to a method performed by a caregiver consultation processing device, including the steps of loading caregiver consultation call data, converting call data into call document data using STT technology, and classifying call subjects from call document data. It relates to a method and device for automatically classifying care consultation details through natural language processing, including the step of selecting at least one characteristic word for each call subject from call document data.

Description

Method and device for automatically classifying care consultation details through natural language processing {METHOD FOR AUTOMATICALLY CLASSIFYING CARE COUNDELING DETAILS THROUGH NATURAL LANGUAGE PRECESSING, AND DEVICE THEREOF}

The present invention relates to a method and device for automatically classifying nursing consultation details through natural language processing, and more specifically, to a method and device for analyzing the subject of a call regarding the content of counseling related to nursing care and providing analysis and counseling information related thereto. will be.

Recently, the market related to natural language processing (NLP) in the field of artificial intelligence (AI) is rapidly growing. NLP technology is being used in a variety of places, including AI speakers, chatbot services, and phone consultations.

NLP is one of the major fields of AI that studies the interaction between computer and human language. AI, which has studied human language through machine learning, understands human speech and text and processes various tasks.

The growth of the natural language processing market is also indicated by indicators. Market & Market, a global market research firm, predicts that the global natural language processing market will grow from $2,571.2 million (about KRW 2.9838 trillion) in 2019, before COVID-19, to $9.427.9 billion (about KRW 10.941 trillion) in 2024. expected.

The average annual growth rate of the natural language processing market is 29.7%. In particular, in the United States, the natural language processing market, which was worth $190 million (about 220.4 billion won) in 2016, is expected to grow to $1.25 billion (about 1.45 trillion won) by 2025. Analysis shows that the domestic natural language processing market is also growing at an average annual rate of 51%.

The natural language processing market has already gone beyond a simple messenger function and is also being used as content to select and provide various services depending on the situation. In particular, the development of AI has led to the rapid advancement of natural language processing functions as well as the development of communication between natural language processing, such as financial, It appears that it can be used across all industries, including distribution, gaming, entertainment, and healthcare.

Natural language processing technology is seeking innovation after the coronavirus pandemic with the advantage of enabling immediate customer response and increasing work productivity without the need for additional consultation staff. Natural language processing is a technology that allows companies to reach the MZ generation and consumers who want quick service. It is expected to grow into one of the new communication strategies.

Conventionally, nursing work involves a caregiver providing care services to a patient or guardian, and the work is carried out person-to-person, and in the case of companies that manage caregiver work, there is a lot of counseling work related to nursing care. In addition, these consultation tasks were labor-intensive, and technology was needed to automate these tasks.

Therefore, as technology related to natural language processing grows rapidly, there is a need to introduce such technology in the nursing care market that provides nursing work, and to find methods and technologies that can further automate the currently labor-intensive tasks.

The above-described background technology is technical information that the inventor possessed for deriving the present invention or acquired in the process of deriving the present invention, and cannot necessarily be said to be technology known to the general public before filing the application for the present invention.

The problem to be solved through several embodiments of the present invention is to provide a method and device for automatically classifying and processing caregiver consultation details that can classify the call subject in consultation details related to nursing.

In addition, the problem to be solved through some embodiments of the present invention is to provide a method and device for classifying call subjects in consultation details related to nursing and setting different word weights for each call subject.

In addition, the problem to be solved through some embodiments of the present invention is a method of setting weights for characteristic words in nursing-related counseling history and generating analysis counseling information and providing it to users using a caregiver matching application; It is about providing the device.

In a method performed by a caregiver consultation processing device according to some embodiments of the present invention for solving the above technical problem, the step of loading caregiver consultation call data, converting call data into call document data using STT technology. It may include a step of classifying a call subject from the call document data, and performing a task of selecting at least one characteristic word for each call subject from the call document data.

In one embodiment, the step of classifying a call subject in call document data may further include setting a word weight according to the call subject classification.

In one embodiment, the step of classifying a call subject from call document data may further include selecting characteristic words based on word weights and generating and storing consultation information.

In one embodiment, the step of selecting at least one characteristic word for each call subject from the call document data may further include generating analysis consultation information tagging the characteristic word from the call document data. .

In one embodiment, the step of selecting at least one characteristic word for each call subject from call document data further includes providing analysis consultation information to a user corresponding to the call subject classification by tagging the characteristic word. can do.

According to the problem-solving means of the present invention described above, it is possible to provide a method and device for automatically documenting caregiver consultation details and converting them into a database.

In addition, according to the problem solving means of the present invention, it is possible to automatically classify the caregiver counseling subject in the caregiver counseling details, thereby providing a method to improve work efficiency by simplifying and automating the caregiver counseling task.

In addition, according to the problem solving means of the present invention, a device is provided that sets a word weight according to the caregiver counseling subject in the caregiver counseling history, creates a counseling history report based on this, and provides it to the user who uses the caregiver matching application. can do.

1 illustrates an example environment in which a caregiver counseling processing device according to some embodiments of the present disclosure may be applied.
FIG. 2 is a flowchart illustrating a method of automatically classifying care counseling details that can be performed in a caregiver counseling processing device according to some embodiments of the present disclosure.
FIG. 3 is a flowchart illustrating a method of classifying call subjects from call document data according to some embodiments of the present disclosure.
Figure 4 is a flowchart for explaining a feature word selection process according to some embodiments of the present disclosure.
5 is a diagram of an example computing device that may implement devices and/or systems according to various embodiments of the present disclosure.

Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the attached drawings. The advantages and features of the present disclosure and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the technical idea of the present disclosure is not limited to the following embodiments and may be implemented in various different forms. The following examples are merely intended to complete the technical idea of the present disclosure and to be used in the technical field to which the present disclosure belongs. It is provided to fully inform those skilled in the art of the scope of the present disclosure, and the technical idea of the present disclosure is only defined by the scope of the claims.

When adding reference numerals to components in each drawing, it should be noted that the same components are given the same reference numerals as much as possible even if they are shown in different drawings. Additionally, in describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present disclosure, the detailed description will be omitted.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings that can be commonly understood by those skilled in the art to which this disclosure pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined. The terminology used herein is for the purpose of describing embodiments and is not intended to limit the disclosure. In this specification, singular forms also include plural forms unless specifically stated in the phrase.

Additionally, in describing the components of the present disclosure, terms such as first, second, A, B, (a), and (b) may be used. These terms are only used to distinguish the component from other components, and the nature, sequence, or order of the component is not limited by the term. When a component is described as being “connected,” “coupled,” or “connected” to another component, that component may be directly connected or connected to that other component, but there is another component between each component. It should be understood that elements may be “connected,” “combined,” or “connected.”

As used herein, “comprises” and/or “comprising” refers to the presence of one or more other components, steps, operations and/or elements. or does not rule out addition.

Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the attached drawings.

The caregiver consultation processing method and the device to which the method is applied according to some embodiments of the present disclosure can be applied to all fields in which a requester (or consumer) posts (or uploads) a notice and a bidder (or caregiver) proposes a bid. Here, the products to be provided by the bidder are not limited to goods and may include services.

As a specific example, the present disclosure may be applied to a field in which a caregiver proposes a bid when a notice about nursing services to be provided to a patient is posted. As another example, the present disclosure may apply to a field in which a hospital proposes a bid when a notice about hospital medical services to be provided to a patient is posted. Below, for convenience of explanation, an example will be given where a caregiver proposes a bid in an announcement about nursing services to be provided to a patient. However, it should be noted that even if explained according to this example, the scope of the present disclosure is not limited to the examples to be described later.

Additionally, when describing the components of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are only used to distinguish the component from other components, and the nature, sequence, or order of the component is not limited by the term. Throughout the specification, when a part is said to 'include' or 'have' a certain component, this means that it does not exclude other components but may further include other components, unless specifically stated to the contrary. . Additionally, terms such as 'unit' and 'module' used in the specification refer to a unit that processes at least one function or operation, and may be implemented as hardware, software, or a combination of hardware and software.

1 illustrates an example environment in which a caregiver counseling processing device according to some embodiments of the present disclosure may be applied.

A variety of user experiences can be provided to caregivers and consumers (guardians, patients, elderly people, etc.) through a system that includes the caregiver consultation processing device 100 shown in FIG. 1 and the terminals 200 and 300 of users using the caregiver application. there is. As a specific example, a consumer may post a notice regarding the nursing services to be provided to the patient. Additionally, the caregiver can propose a bid on at least one of the posted announcements. Additionally, the consumer can select at least one caregiver among the caregivers who applied (or bid) for the announcement. Here, consumers can apply for a job posting to select a caregiver, or various information regarding this may be exposed to the consumer.

Hereinafter, the operations of the components shown in FIG. 1 will be described in more detail in relation to the operation of processing consultation details related to nursing among the various user experiences provided through the above-described system.

Figure 1 shows an example where the caregiver terminal 200 and the consumer terminal 300 are connected to the network, but this is only for convenience of understanding, and the number of terminals that can be connected to the network may vary.

Meanwhile, Figure 1 only shows a preferred embodiment for achieving the purpose of the present disclosure, and some components may be added or deleted as needed. Hereinafter, the components shown in FIG. 1 will be described in more detail.

The caregiver consultation processing device 100 may be a server device of a caregiver matching application. Such a server device may be implemented to provide the various user experiences described above to the caregiver terminal 200 and the consumer terminal 300, but detailed description will be omitted in order not to obscure the subject matter of the present disclosure.

The caregiver consultation processing device 100 can collect and analyze various information generated while the caregiver terminal 200 and the consumer terminal 300 use the caregiver matching application. Here, the caregiver counseling processing device 100 can process various collected and analyzed information. Specific details regarding this will be described in detail using Figures 2 to 5.

Meanwhile, the caregiver consultation processing device 100 may be implemented with one or more computing devices. For example, all functions of the caregiver counseling processing device 100 may be implemented in a single computing device. As another example, the first function of the caregiver counseling processing device 100 may be implemented in a first computing device, and the second function may be implemented in a second computing device. Here, the computing device may be a laptop, a desktop, a laptop, etc., but is not limited thereto and may include all types of devices equipped with a computing function. However, it may be desirable for the caregiver counseling processing device 100 to be implemented as a high-performance server-class computing device. An example of a computing device will be described with reference to FIG. 5 .

Next, the caregiver terminal 200 and the consumer terminal 300 can be provided with the functions of the caregiver matching application provided by the caregiver counseling processing device 100. For a specific example, a consumer may post a notice seeking a caregiver through the consumer terminal 300, and a caregiver may support a bid on the advertisement posted through the caregiver terminal 200. Here, the consumer can bid on the announcement or check the list of caregivers recommended in the announcement through the consumer terminal 300 and select one caregiver. In order to use the function of this caregiver matching application, the caregiver terminal 200 and the consumer terminal 300 may have a web browser or a dedicated application installed. For example, the caregiver terminal 200 and the consumer terminal (300) may be any one of a desktop, workstation, laptop, tablet, and smart phone, but is not limited thereto, and is equipped with a computing function. Can include all kinds of devices.

In some embodiments, components included in an environment to which the caregiver counseling processing device 100 is applied may communicate through a network. The network can be implemented as all types of wired/wireless networks such as Local Area Network (LAN), Wide Area Network (WAN), mobile radio communication network, Wibro (Wireless Broadband Internet), etc. You can.

Meanwhile, the environment shown in FIG. 1 shows that the caregiver terminal 200, the consumer terminal 300, and the caregiver counseling processing device 100 are connected via a network, but the scope of the present disclosure is not limited thereto. It should be noted that the caregiver terminal 200, the consumer terminal 300, and the caregiver counseling processing device 100 may be connected through P2P (Peer to Peer).

So far, with reference to FIG. 1 , an exemplary environment in which the caregiver counseling processing device 100 according to some embodiments of the present disclosure can be applied has been described. Hereinafter, with reference to the drawings of FIG. 2 and below, methods according to various embodiments of the present disclosure will be described in detail.

Each step of the methods to be described later may be performed by a computing device. In other words, each step of the methods may be implemented as one or more instructions executed by a processor of a computing device. All steps included in these methods may be performed by a single physical computing device; however, the first steps of the method may be performed by a first computing device and the second steps of the method may be performed by a second computing device. It could be.

In FIGS. 2 to 4 below, the description will be continued assuming that each step of the methods is performed by the caregiver counseling processing device 100 illustrated in FIG. 1. However, for convenience of explanation, the description of the operator of each step included in the methods may be omitted.

FIG. 2 is a flowchart illustrating a method of automatically classifying care counseling details that can be performed in a caregiver counseling processing device according to some embodiments of the present disclosure.

In step S100, the caregiver consultation processing device 100 may load care consultation call data.

In the present invention, nursing consultation call data may be data about a consultation call made by a caregiver, patient, or guardian in relation to nursing care. Therefore, the storage format of the data may be one of the voice data formats, such as .mp3, .avi, .mp4, .mov, etc. The nursing consultation call data may be data that a caregiver, patient, or guardian consults by calling a counselor working at a caregiver matching platform company.

The data regarding the nursing consultation may include inquiries regarding nursing care, nursing care schedule, nursing care costs, nursing hours, and all information related to nursing. The data regarding the nursing counseling is provided within the range that a person skilled in the art can understand. It should be noted that it may include all work-related content that caregivers, patients, or guardians may consult with counselors.

In addition, due to the specificity of the caregiver matching application in the disclosure of the present invention, the data regarding the care consultation includes information about uploading a care posting, inquiries about caregivers who applied for the care posting, and the process of receiving care services after matching with a caregiver. may include inquiries regarding cancellation or re-matching.

In step S200, the caregiver consultation processing device 100 may convert call data into call document data. The caregiver consultation processing device 100 may convert the acquired data regarding the care consultation into call document data in step S100.

The caregiver consultation processing device 100 can convert data about the care consultation into call document data using STT (Speech-TO-Text) technology. In other words, the caregiver counseling processing device 100 can perform a process of interpreting voice language and converting the content into text data.

Here, the caregiver consultation processing device 100 may pre-process the input voice and then compare it with a training model to output a text result.

In the present invention, the fact that the caregiver counseling processing device 100 utilizes STT technology is not a major technical feature of the present invention, and may include all general information regarding STT technology to the extent that a person skilled in the art can understand. Of course, it can include all technical content within a range that a person skilled in the art can understand regarding the process of converting voice data into text data.

In step S300, the caregiver consultation processing device 100 may classify the call subject from the call document data.

The caregiver consultation processing device 100 may convert voice data into call document data and then classify the subject of the call from the call document data. The call subject may include patients, guardians, and caregivers in relation to caregiver counseling, and further, it is natural that the call subject may include counseling staff of a caregiver matching platform company, caregiver association, and hospital officials.

The caregiver consultation processing device 100 may select words corresponding to nouns from call document data and select call subjects based on whether or not they contain words corresponding to each call subject stored in advance. For example, the caregiver consultation processing device 100 searches the call document data for pre-stored words corresponding to disease, symptom, nursing service content, and nursing care requirements in order to select a 'patient' among the call subjects. The number of words included is determined, and if the included number exceeds a certain number, the subject of the call can be determined to be a patient.

Alternatively, the caregiver consultation processing device 100 determines the number of words specified above in the call document data for pre-stored words corresponding to nursing care costs, nursing care matching contents, nursing service provision contents, nursing service needs, and nursing difficulties, and , if the number included here exceeds a certain number, the subject of the call may be determined to be a caregiver.

Accordingly, the caregiver consultation processing device 100 may store words corresponding to each call subject in advance, determine how many of the stored words are included in the call document data, and then select the call subject.

The caregiver consultation processing device 100 generates the call document data when the number of pre-stored words included in the call document data is the same, that is, when the number of words corresponding to the subject of the call is 'caregiver' and 'patient' is the same. Information required to identify the subject of the call can be transmitted to the caregiver matching application and the caregiver terminal or consumer terminal. Accordingly, the caregiver counseling processing device 100 may additionally transmit additional required request information to determine who is the subject of the counseling call and select the call subject based on the reply information.

Alternatively, the caregiver consultation processing device 100 automatically stores a plurality of call subjects corresponding to the tie when the number of words included in the call document data is tied, and later uses them to operate a caregiver matching application. You can also let the caregiver platform company make the decision. Accordingly, if the number of pre-stored words included in the call document data is equal, the caregiver counseling processing device 100 may classify the call subject into multiple subjects.

The method of classifying and utilizing the currency subjects will be described in detail using FIG. 3.

FIG. 3 is a flowchart illustrating a method of classifying call subjects from call document data according to some embodiments of the present disclosure.

In step S310, the caregiver counseling processing device 100 may set word weights according to the call subject classification. That is, in FIG. 2, the caregiver consultation processing device 100 classifies the call counseling subjects based on pre-stored words, but the caregiver counseling processing device 100 classifies each call subject based on some data classifying the call counseling subjects. You can set weights for frequently used words and terms in the corresponding currency document data. The weight may be set to include two words even if one word is included in the case of a word for which the weight value was set in the process of selecting the number of words included previously set in FIG. 2. Therefore, the weight is set to 2 to improve the efficiency of the currency subject selection process through the weight of a specific word.

Accordingly, the caregiver counseling processing device 100 can set a certain weight for frequently used words and terms for each call subject, and the weight may be the same or different.

In step S320, the caregiver counseling processing device 100 may select characteristic words and store counseling information based on word weights.

The caregiver counseling processing device 100 may select words with set weights as characteristic words. Accordingly, the caregiver counseling processing device 100 may separate the counseling call history including the characteristic word for a word selected as a characteristic word and store it as counseling information. In other words, the caregiver consultation processing device 100 stores frequently used words and terms as consultations containing the above words and terms are more frequent than other consultations, and stores the consultation contents as consultation information for later use. You can.

Specifically, the content that the caregiver counseling processing device 100 utilizes as counseling information will be described in detail again with reference to FIG. 2 .

In step S400, the caregiver counseling processing device 100 may perform the task of selecting characteristic words.

The caregiver counseling processing device 100 may select characteristic words, tag specific analysis counseling information for the characteristic words based on the selected words, and provide the same. More specifically, it is described in detail with reference to FIG. 4 .

Figure 4 is a flowchart for explaining a feature word selection process according to some embodiments of the present disclosure.

In step S410, the caregiver counseling processing device 100 may generate analysis counseling information by tagging characteristic words in call document data.

The caregiver counseling processing device 100 may generate analysis counseling information corresponding to a word selected as a characteristic word among words. That is, the caregiver counseling processing device 100 may generate and store analysis counseling information in advance, and the analysis counseling information may include counseling information regarding the caregiver's work details that can be provided to each caregiver, patient, or guardian.

The analysis counseling information generated by the caregiver counseling processing device 100 may be information generated based on tagging characteristic words in pre-stored call document data.

For example, the caregiver counseling processing device 100 may generate and store analysis counseling information related to 'ostomy', which corresponds to 'ostomy' among the characteristic words. The analysis counseling information corresponding to 'ostomy' may include the definition of 'ostomy', care methods required for patients who need 'ostomy', nursing tips, information on caregivers who performed 'ostomy' tasks, etc.

Alternatively, if the characteristic word is 'meal', the caregiver counseling processing device 100 may provide analysis counseling information corresponding to 'meal' such as 'meal' care tips, 'meal' assistance method, 'meal' cycle, and 'meal' assistance. It may include information about the caregiver who performed the work.

Therefore, since the analysis counseling information generated by the caregiver counseling processing device 100 is information that changes as the caregiver progresses care in the caregiver matching application, it is natural that it can be updated and regenerated based on a certain period.

More specifically, the caregiver consultation processing device 100 generates and stores analysis consultation information in advance, and then, when new care consultation call data is input after the generation point, the new care consultation call data is converted into call document data. You can convert call subject classification and feature word selection from call document data. Thereafter, based on the characteristic words extracted from the new nursing counseling call data, the feature words may be compared with previously stored feature words, and analysis counseling information generated based on the corresponding feature words may be generated. Accordingly, even when new nursing counseling call data is input, the nursing counseling processing device 100 can extract characteristic words and generate analysis counseling information based on the new nursing counseling call data, thereby generating analysis counseling information in real time.

In step S420, the caregiver counseling processing device 100 may provide analysis counseling information to a user corresponding to the call subject classification by tagging characteristic words.

The caregiver counseling processing device 100 may provide the analysis counseling information generated in step S410 to the user corresponding to the call subject. In other words, the caregiver counseling processing device 100 may not provide the analysis counseling information to the subject of the call, but may provide it to the user corresponding to the subject of the call. For example, if the call subject is classified as a patient, the caregiver consultation processing device 100 may provide the analysis consultation information generated in step S410 to the patient classified as the call subject, but is caring for the patient or , the nursing care efficiency of the patient can be improved by providing it to multiple caregivers who may provide care.

However, it is natural that the caregiver consultation processing device 100 can immediately provide the consultation analysis information to the calling subject. The above-described above is only an example, and in the case where the calling subject is classified as a patient, It should be noted that the responding user is not always a caregiver.

Additionally, the caregiver counseling processing device 100 may tag the counseling analysis information with a characteristic word and provide it along with the characteristic word. Accordingly, the user who has received the counseling analysis information can check the characteristic words that summarize the counseling analysis information, thereby improving user convenience.

In step S430, the caregiver counseling processing device 100 may acquire corresponding data of the user who has received the analysis counseling information.

The caregiver counseling processing device 100 can obtain data about the user's response to the analysis counseling information through a terminal corresponding to the user who has received the analysis counseling information. For example, the caregiver counseling processing device 100 may view the counseling analysis information and obtain information about the time the information was viewed as data, and obtain the time taken to view the counseling analysis information as data. can do.

Alternatively, the caregiver counseling processing device 100 may obtain the number of times the counseling analysis information is viewed as data. Therefore, the caregiver counseling processing device 100 may determine whether the user who provided the counseling analysis information actively utilizes the counseling analysis information based on the corresponding data, and the caregiver counseling processing device 100 may determine whether the user who provided the counseling analysis information actively utilizes the counseling analysis information. It is possible to determine whether the counseling analysis information generated by tagging the corresponding data with the counseling analysis information is better generated information.

Therefore, the caregiver counseling processing device 100 may later select the most efficient and effective counseling analysis information based on the corresponding data tagged with the counseling analysis information.

Hereinafter, a device and system in which the contents of the present disclosure can be implemented will be described with reference to FIG. 5.

5 is a diagram of an example computing device that may implement devices and/or systems according to various embodiments of the present disclosure.

The computing device 1500 includes one or more processors 1510, a bus 1550, a communication interface 1570, and a memory 1530 that loads a computer program 1591 executed by the processor 1510, It may include a storage 1590 that stores a computer program 1591. However, only components related to the embodiment of the present disclosure are shown in FIG. 5 . Accordingly, a person skilled in the art to which this disclosure pertains can recognize that other general-purpose components other than those shown in FIG. 5 may be further included.

The processor 1510 controls the overall operation of each component of the computing device 1500. The processor 1510 includes a Central Processing Unit (CPU), Micro Processor Unit (MPU), Micro Controller Unit (MCU), Graphic Processing Unit (GPU), or any type of processor well known in the art of the present disclosure. It can be. Additionally, the processor 1510 may perform operations on at least one application or program to execute a method according to embodiments of the present disclosure. Computing device 1500 may include one or more processors.

The memory 1530 stores various data, commands, and/or information. The memory 1530 may load one or more programs 1591 from the storage 1590 to execute a method according to embodiments of the present disclosure. The memory 1530 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

Bus 1550 provides communication functionality between components of computing device 1500. The bus 1550 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

The communication interface 1570 supports wired and wireless Internet communication of the computing device 1500. Additionally, the communication interface 1570 may support various communication methods other than Internet communication. To this end, the communication interface 1570 may be configured to include a communication module well known in the technical field of the present disclosure.

According to some embodiments, communication interface 1570 may be omitted.

The storage 1590 can non-temporarily store the one or more programs 1591 and various data.

The storage 1590 may be non-volatile memory such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, or a technology field to which the present disclosure pertains. It may be configured to include any type of computer-readable recording medium well known in the art.

The computer program 1591, when loaded into the memory 1530, may include one or more instructions that cause the processor 1510 to perform methods/operations according to various embodiments of the present disclosure. That is, the processor 1510 can perform methods/operations according to various embodiments of the present disclosure by executing the one or more instructions.

So far, various embodiments of the present disclosure and effects according to the embodiments have been mentioned with reference to FIGS. 1 to 5 . The effects according to the technical idea of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned may be clearly understood by those skilled in the art from the description of the specification.

The technical idea of the present disclosure described so far with reference to FIGS. 1 to 5 may be implemented as computer-readable code on a computer-readable medium. The computer-readable recording medium may be, for example, a removable recording medium (CD, DVD, Blu-ray disk, USB storage device, removable hard disk) or a fixed recording medium (ROM, RAM, computer-equipped hard disk). You can. The computer program recorded on the computer-readable recording medium can be transmitted to another computing device through a network such as the Internet and installed on the other computing device, and thus can be used on the other computing device.

In the above, even though all the components constituting the embodiments of the present disclosure have been described as being combined or operated in combination, the technical idea of the present disclosure is not necessarily limited to these embodiments. That is, within the scope of the purpose of the present disclosure, all of the components may operate by selectively combining one or more of them.

Although operations are shown in the drawings in a specific order, it should not be understood that the operations must be performed in the specific order shown or sequential order or that all illustrated operations must be performed to obtain the desired results. In certain situations, multitasking and parallel processing may be advantageous. Moreover, the separation of the various components in the embodiments described above should not be construed as necessarily requiring such separation, and the program components and systems described may generally be integrated together into a single software product or packaged into multiple software products. You must understand that it exists.

Although embodiments of the present disclosure have been described above with reference to the attached drawings, those skilled in the art will understand that the present disclosure can be implemented in other specific forms without changing the technical idea or essential features. I can understand that I can. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. The scope of protection of this disclosure shall be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope shall be construed as being included in the scope of rights of the technical ideas defined by this disclosure.

Claims (12)

In a method performed by a caregiver consultation processing device,
Loading caregiver consultation call data;
Converting the call data into call document data using STT technology;
Classifying a call subject from the call document data; and
Comprising: performing the task of selecting at least one characteristic word for each call subject from the call document data,
The step of classifying the call subject from the call document data includes setting a word weight according to the call subject classification, selecting characteristic words based on the word weight, and generating and storing consultation information,
The step of selecting at least one characteristic word for each call subject from the call document data includes generating analysis consultation information tagging the characteristic word in the call document data and tagging the characteristic word to correspond to call subject classification. Further comprising the step of providing analysis consultation information to the user.
Automatic classification method of nursing consultation details through natural language processing. delete delete delete delete According to paragraph 1,
The step of selecting at least one characteristic word for each call subject from the call document data further includes obtaining corresponding data of a user who has received the analysis consultation information.
Automatic classification method of nursing consultation details through natural language processing. processor;
network interface;
Memory; and
Includes a computer program loaded into the memory and executed by the processor,
The processor,
Instructions for loading caregiver consultation call data;
Instructions for converting the call data into call document data using STT technology;
Instructions for classifying call subjects from the call document data; and
an instruction for selecting at least one characteristic word for each call subject from the call document data; Perform including,
The instruction for classifying the call subject from the call document data further includes an instruction for setting a word weight according to the call subject classification and an instruction for selecting characteristic words and generating and storing consultation information based on the word weight.
An instruction that performs the task of selecting at least one characteristic word for each call subject from the call document data corresponds to call subject classification by tagging the characteristic word and an instruction that generates analysis consultation information tagging the characteristic word in the call document data. Performed by further including instructions that provide analysis consultation information to the user.
Automatic classification device for nursing consultation details through natural language processing. delete delete delete delete In clause 7,
The instruction for performing the task of selecting at least one characteristic word for each call subject from the call document data further includes an instruction for obtaining corresponding data of a user who has received the analysis consultation information.
Automatic classification device for nursing consultation details through natural language processing.