KR20220146873A - Device for asking and diagnosing a patient for surgery, and a method for collecting patient status information through the device - Google Patents

Abstract

The present invention is to provide a device for automatically conducting a medical examination on a patient admitted to a hospital for surgery or the like, and a method for collecting patient condition information through the device. A device for conducting a medical examination includes: a question unit which outputs a question that induces a patient's voice answer; a collection unit which collects the voice answer; and a management unit which matches the voice answer to identification information of the patient, to manage the same.

Description

{Device for asking and diagnosing a patient for surgery, and a method for collecting patient status information through the device}

The present invention relates to an apparatus and method for interviewing a surgical patient and collecting patient status information.

When a patient is hospitalized for surgery, doctors make rounds every day to check on the patient's condition.

Since a large number of patients have to be checked, the amount of interview time that can be allocated to one patient during a round is reduced, which may reduce the quality of the interview.

Korean Patent Publication No. 1584308 discloses a smart electronic questionnaire system that can collect medical questionnaire data through a mobile terminal and utilize it for customized treatment for each patient. However, since a preset questionnaire is provided to the patient terminal, there is a limitation in that only a short-answer answer can be obtained from the patient.

Korean Patent Publication No. 1584308

An object of the present invention is to provide an apparatus for automatically performing a questionnaire for a patient admitted to a hospital for surgery, etc., and a method for collecting patient status information through the device.

The questionnaire apparatus of the present invention includes a questioning unit for outputting a question leading to a patient's voice answer; a collection unit for collecting the voice responses; a conversion unit for converting the voice response into text; an extraction unit for extracting the patient's status information from the voice response or the text; a recording unit for recording the voice response; It may include; a management unit that manages by matching at least one of the text, the status information, and the recording file of the voice response to the identification information of the patient.

The collection method of the present invention comprises the steps of transmitting a list of objects to be interviewed from the server to the questionnaire robot; moving, by the questionnaire robot, a specific patient included in the list to a target; The step of the questionnaire robot identifying the identification information of the specific patient, and transmitting the identified identification information to the server; retrieving whether existing questionnaire data exists with respect to the identification information of the specific patient in the server; transmitting a first question to the questionnaire robot if the existing questionnaire data does not exist in the server, and transmitting a second question to the questionnaire robot if the existing questionnaire data exists; converting the first question or the second question into voice in the questionnaire robot and outputting it; collecting the voice response of the specific patient in the questionnaire robot, and transmitting the voice response to the server; determining whether the voice answer is correct in the server, and transmitting an answer recognition result including the determination result and a next question to the questionnaire robot; storing the answer recognition result in the questionnaire robot and outputting the next question to the specific patient; transmitting the answer recognition result stored in the questionnaire robot and the recorded data of the voice answer stored in the questionnaire robot to the server when the questionnaire for the specific patient is completed by the questionnaire robot; and databaseizing the answer recognition result and the voice answer in the server.

According to the medical questionnaire and collection method of the present invention, it may be possible to provide a questionnaire dialogue system for automatically collecting the patient's status after surgery. Since the medical examination performed by the medical staff is automated, the burden of the medical examination on the medical staff can be reduced.

According to the present invention, data on the patient's progress in the hospital can be efficiently managed by databaseizing the process before and after surgery.

The questionnaire and collection method of the present invention may not perform any judgment on the condition through the patient's answer. The questionnaire and collection method of the present invention can only perform functions of accurately obtaining an answer from a patient and delivering the obtained answer to a medical staff as it is.

1 is a schematic diagram showing a paperweight device of the present invention.
Fig. 2 is a schematic diagram showing the action of the question order variable algorithm.
3 is a flowchart illustrating a method for collecting patient status information according to the present invention.
4 is a diagram illustrating a computing device according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art to which the present invention pertains can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

In this specification, duplicate descriptions of the same components will be omitted.

Also, in this specification, when a component is referred to as 'connected' or 'connected' to another component, it may be directly connected or connected to the other component, but other components in the middle It should be understood that there may be On the other hand, in the present specification, when it is mentioned that a certain element is 'directly connected' or 'directly connected' to another element, it should be understood that the other element does not exist in the middle.

In addition, the terms used herein are used only to describe specific embodiments, and are not intended to limit the present invention.

Also in this specification, the singular expression may include the plural expression unless the context clearly dictates otherwise.

Also, in this specification, terms such as 'include' or 'have' are only intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, and one or more It should be understood that the existence or addition of other features, numbers, steps, acts, components, parts, or combinations thereof, is not precluded in advance.

Also in this specification, the term 'and/or' includes a combination of a plurality of listed items or any of a plurality of listed items. In this specification, 'A or B' may include 'A', 'B', or 'both A and B'.

Also, in this specification, detailed descriptions of well-known functions and configurations that may obscure the gist of the present invention will be omitted.

For patients after surgery, doctors may make rounds every day or hourly to check the progress of the surgery, etc. In this case, most of the rounds for the patient after surgery may be made as a simple process of checking whether there is an abnormality in the surgical site.

If this simple process is automated, it is obvious that the burden on the medical staff will be greatly reduced. The medical questionnaire and collection method of the present invention can automate rounds performed for patients after surgery, general questionnaires for general patients, and the like. The paperweight device of the present invention may be implemented in the form of a robot. The robot can collect information about the patient's condition and deliver the collected status information to the medical staff. It may suffice for medical staff to directly conduct an interview only for patients with unusual conditions among the status information received from the robot. Therefore, according to the medical questionnaire and collection method of the present invention, the time of medical staff consumed for rounds or questionnaires can be significantly reduced.

In the field dealing with human life and health, it may still be premature for a robot to judge a disease on behalf of a medical staff due to its reliability and risk in actual medical field. Therefore, the medical questionnaire and collection method of the present invention can focus on accurately collecting status information from the patient and delivering it to the medical staff as it is, without making any judgment on the condition.

1 is a schematic diagram showing a paperweight device of the present invention.

The paperweight device shown in FIG. 1 may include a paperweight robot 10 and a server 30 .

The questionnaire robot 10 may perform a question on the patient and collect the patient's voice answer to the question. In order to perform a question by voice and collect answers, the interview robot 10 may be spatially disposed within a distance of several meters to the patient to be questioned.

As an example, the paperweight robot 10 may be formed in a form having a moving means that directly visits the patient while driving along the ground. Alternatively, the questionnaire robot 10 may be formed in the form of a wearable device operated by a patient. Alternatively, the questionnaire robot 10 may be installed in a hospital room used by a patient or may be formed in the form of a speaker and a microphone installed around a bed.

The server 30 extracts a question to be performed on a specific patient using the identification information and transmits it to the questionnaire robot 10, records the voice response collected by the questionnaire robot 10 in the database 290, and transmits it to the medical staff have.

The paperweight device of the present invention internally includes a questioning unit 110 , a collecting unit 120 , a converting unit 220 , an extracting unit 230 , a recording unit 140 , a management unit 130 , a moving unit 150 , It may include a determination unit 240 and a processing unit 210 . In this case, some elements may be installed in the paperweight robot 10 , and other elements may be installed in the server 30 . The installation location of some elements may vary according to various environments.

For example, the questioning unit 110 and the collecting unit 120 functioning at a position facing the patient may be provided in the questionnaire robot 10 . It is preferable that the processing unit 210 that performs the databaseization process of recording voice responses obtained from a plurality of patients in the database 290 is provided in the server 30 capable of communicating with the plurality of questionnaire robots 10 . On the other hand, the conversion unit 220 , the extraction unit 230 , the recording unit 140 , the management unit 130 , the moving unit 150 , the determination unit 240 , etc., which can function even in a position not facing the patient, is a questionnaire It may be provided in the robot 10 or may be provided in the server 30 .

In FIG. 1 , the questioning unit 110 , the collecting unit 120 , the recording unit 140 , the moving unit 150 , and the management unit 130 are provided in the questionnaire robot 10 . In FIG. 1 , the processing unit 210 , the converting unit 220 , the extracting unit 230 , and the determining unit 240 are provided in the server 30 . At this time, the conversion unit 220 , the extraction unit 230 , etc. may be provided in the paper-weight robot 10 to ventilate once again.

The question unit 110 may output a question that induces a patient's voice answer. The question unit 110 may include a speaker that audibly outputs various questions or a display that visually outputs various questions.

It is preferable that the questioning unit 110 be disposed within several meters from the user so that the patient can directly recognize the question content.

The collection unit 120 may collect the patient's voice response. The collection unit 120 may include a microphone for receiving a voice response.

The recording unit 140 may generate a recording file by recording the patient's voice responses collected through the collection unit 120 .

The conversion unit 220 may convert the patient's voice response into text.

The extractor 230 may extract the patient's status information from the voice response or text.

The patient's status information may be as follows, including the start time of the interview 'Date: 2020-11-16 11:58:55'. The patient's state information is stored in the database 290 by the processing unit 210, and the patient's identification information, index, etc. are added to enable search and extraction to be added to the database.

-----Patient status information-----

Date: 2020-11-16 11:58:55

Position: ['knee']

Quality: ['throbbing']

R_factor2: ['Walking', 'Sitting']

Severity: 4

Timing2: 1 year

Mood: Moderate

Anxiety: Yes

Sleep1: 1

Sleep2: bad

-----------------------

The patient's status information may include check items that the medical staff checks through an interview during a round trip.

The questions of the questioning unit 110 may be generated to induce a patient's voice answer to fill the corresponding check item.

For example, the first question including questions for a pre-operative patient before surgery may include the following ten.

1. Where is the most painful area right now? If there are multiple areas, please list them in the order of the most pain. (Pain area: a question to fill the 'Position' of the status information)

2. What kind of pain do you feel? Please express it like numbness and throbbing. (Pain modality: a question to fill the 'Quality' of the status information)

3. When is the pain most intense? (Time of intensification of pain)

4. Which position hurts the most? (Pain intensifying posture: a question to fill 'R_factor2' of status information)

5. Please rate how severe the pain is on a scale of 0 to 10. (Pain intensity: a question to fill in the 'Severity' of the status information)

6. How many days did the pain get worse? (Pain duration: question to fill 'Timing2' of status information)

7. How are you feeling now? Please say good, average, or bad. (Current mood; questions to fill in 'Mood' of status information)

8. Are you currently worried or anxious? Please answer yes or no. (Anxiety: a question to fill in the 'Anxiety' of status information)

9. How many hours did you sleep? (Sleep time: a question to fill 'Sleep1' of status information)

10. Did you sleep well without waking up in the middle? (Quality of sleep: a question to fill 'Sleep2' of status information)

As another example, the second question including questions for the patient after surgery is over may include the following 10 questions.

1. Do you feel any pain at the surgical site? (with or without pain)

2. What kind of pain do you feel at the surgical site? Please express it like numbness and throbbing. (Pain mode)

3. Please answer on a scale of 0 to 10 how severe the pain at the surgical site is. (pain intensity)

4. How many hours per day does the pain at the surgical site last? (pain duration)

5. Do you feel pain in the original pain area before surgery? (with or without pain)

6. What kind of pain do you feel? Please express it like numbness and throbbing. (Pain mode)

7. Please answer on a scale of 0 to 10 how severe the pain was in the area where it hurt before the operation. (pain intensity)

8. How many hours per day does the pain in the previously hurt area last? (pain duration)

9. How are you feeling now? Please say good, average, or bad. (Current mood)

10. Are you currently worried or anxious? Please answer yes or no. (Anxiety)

11. How many hours did you sleep? (sleep time)

12. Did you sleep well without waking up in the middle? (Quality of sleep)

The management unit 130 may manage by additionally matching at least one of text and state information with identification information of a patient. For example, the management unit 130 may store matching identification information, voice answer, text, status information, recording file, etc. together or transmit it to the server 30 .

The patient's identification information includes a UID (User Identifier) in which at least one of a number, a letter, and a special symbol is combined into a plurality, and may be formed regardless of the patient's personal information.

The interrogator 110 and the collection unit 120 may be disposed at positions facing the patient by the moving unit 150 .

The moving unit 150 may physically move or communicatively move the interrogator 110 and the collecting unit 120 .

For example, when the body on which the interrogation unit 110 and the collection unit 120 are mounted is provided, the moving unit 150 includes a driving means such as a motor that moves the body, a wheel rotating or walking by the driving means, and infinite It may include a moving means such as an orbit, articulated legs, and the like. In this case, the interrogation unit 110 and the receiving unit may visit a specific patient on a bed in a specific hospital room while physically traveling in a hallway or a hospital room by the moving unit 150 .

As another example, when the interrogator 110 and the collection unit 120 are installed on a wall around a hospital room, a bed, or a bed, the moving unit 150 includes a plurality of interrogators 110 and a collection unit ( 120) A control signal for operating the interrogator 110 and the collection unit 120 facing the bed of a specific patient from among the plurality may be transmitted.

In the case of the moving unit 150 that moves physically, the interrogator 110 and the collection unit 120 may operate only for a specific patient at a point in time.

On the other hand, when the interrogator 110 and the collection unit 120 are provided for each bed, a plurality of interrogators 110 and the collection unit 120 disposed in the same ward in terms of hardware may operate at the same time. However, since the plurality of questioning units 110 and the plurality of collecting units 120 operate at the same time in the same ward, and when a plurality of patients each respond by voice, the sounds are mixed and propagated, so it may be difficult to perform both questions and answers normally. have. The mobile unit 150 transmits a signal for controlling only one of the interrogating units 110 and the collecting units 120 to operate at a point in time among the plurality of interrogating units 110 and collecting units 120 arranged in the same hospital room by wire or wireless. It can be transmitted to each interrogation unit 110 and each collection unit 120 through a communication network.

When the list of questionnaires is obtained, the moving unit 150 may move the questioning unit 110 and the collecting unit 120 to a target bed of a ward in which a specific patient included in the list is hospitalized. For example, the moving unit 150 may travel along the corridor and the hospital room from the initial position and arrive at the bed of a specific patient together with the interrogator 110 and the collection unit 120 . Alternatively, the moving unit 150 operates (on) the interrogation unit 110 and the collecting unit 120 installed on the bed or the wall around the bed in which a specific patient is hospitalized, and the remaining interrogation units in the hospital room where the specific patient is hospitalized. 110 and the collection unit 120 may turn off the operation. Through this, the same effect as if the normally operating interrogator 110 and the collection unit 120 were physically moved to a specific patient may be exhibited.

If the interrogation unit 110 and the collection unit 120 meet a state of physically or communicatively facing the bed of a specific patient, the moving unit 150 directly identifies the patient from the patient located on the bed separately from the list. information can be obtained. The questioning unit 110 may output a different question depending on whether existing questionnaire data targeting the current identification information obtained through the mobile unit 150 exists.

In the case of medical care, a serious accident may occur if the diagnosis of a specific patient and that of another patient are reversed. In order to prevent this, the moving unit 150 may check once again who the patient on the bed is, even if the patient in the bed of a specific patient is estimated to be the specific patient.

The first patient may go to the bathroom while the second patient in another ward has visited the first patient. In this state, the mobile unit 150 visiting the bed may make an error of performing an interview of the first patient with respect to the second patient. To prevent this, the mobile unit 150 may check the current identification information of the patient (the second patient) currently located on the bed once again. Confirmation of the identification information may be performed by scanning a patient identification code worn by the patient on the arm.

When the mobile unit 150 visits the first patient recorded in the list, but the second patient is recognized instead of the first patient through the current identification information, the mobile unit 150 determines whether the second patient is included in the list can be checked. When the second patient is included in the list, since the second patient must be interviewed anyway, the questioning unit 110 and the collecting unit 120 may perform the questioning of the second patient.

If the current identification information of the first patient is obtained from the bed of the first patient, the questioning unit 110 may output different questions according to whether existing questionnaire data exists for the first patient according to the list. have.

Existing questionnaire data may include state information obtained through the performance of the first question or the second question as described above. In this case, when there is existing questionnaire data for a specific patient, the questioning unit 110 may perform a second question. When the existing questionnaire data for a specific patient does not exist, the questioning unit 110 may perform a first question.

The determination unit 240 may determine whether the patient's voice answer to the specific question intended for the first type of answer is correct. In the present specification, that the voice answer is correct may mean that the corresponding voice answer exists in the set answer list for the question. If the voice answer does not exist in the set answer list, the determination unit 240 may determine that the voice answer is incorrect.

For example, the determination unit 240 may extract a characteristic word from among a plurality of words included in the voice answer through analysis of an auditory voice response or analysis of text converted by the converting unit 220 . The characteristic word may include various words that can be an answer to the status information. For example, 'knee', 'throbbing', 'when walking', 'one year', 'normal', etc. may correspond to the characteristic words.

The determination unit 240 may determine whether a characteristic word exists in the set answer list to the question. If the characteristic word does not exist in the set answer list, the question unit 110 may output a similar question intended to answer the first type instead of moving on to the next question.

For example, the question unit 110 asks 'Where is the most painful part now? If there are multiple areas, please list them in the order of the most pain.”

To this, the patient can answer that the cat is sick, not the same as 'knee'.

In this case, in order to induce the [pain] 'knee', the question unit 110 asks, 'Which part hurts the most now?' Alternatively, you can print a similar question, such as 'Where is the most uncomfortable place right now?'

The question unit 110 may output similar questions such as 'How do you feel pain?'

The question unit 110 may output similar questions such as 'When is the most painful time period?' and 'When do you have the most pain?' .

In order to induce an appropriate answer to [pain intensity], the question unit 110 includes 'How many points would you have if you expressed pain on a scale of 0 to 10?', 'Can you describe how much pain you are in a number between 0 and 10?' You can also print similar questions.

The question unit 110 may output similar questions such as 'How long has the pain been severe?' and 'How long has the pain been intensified recently?' .

When the first answer is obtained through the first question for obtaining the first type of characteristic word, the collection unit 120 may detect not only the first type of characteristic word but also the second type of characteristic word from the first answer. have.

For example, the question unit 110 asks 'Where is the most painful part now? If there are multiple areas, please list them in the order of the most pain.”

At this time, the patient can answer 'My knee hurts when I walk' instead of 'My knee hurts'. The collection unit 120 may detect 'knee' corresponding to the first type of characteristic word from 'knee hurts when walking'. It does not stop there, and the collection unit 120 may additionally detect 'when walking' corresponding to the second type of characteristic word in the first answer.

When the second type of characteristic word is detected in the first answer, the question unit 110 sets the second question item for obtaining the second type of characteristic word to the question immediately following the first question regardless of a preset question order can be determined and printed.

It also includes an answer to the fourth question, 'My knee hurts when I walk', which is the answer to the first question.

In this state, in order, 'What kind of pain do you feel? Please express it like numbness and throbbing.' and the third question, 'What kind of pain do you feel? After performing the same expression as numbness and throbbing.', the fourth question 'When is the time when the pain is most severe?' can be performed. However, in this case, it is easy for the patient to have a negative feeling that he is being teased through a pun. As a method for suppressing the patient's negative emotions toward the questionnaire, if the answer to the fourth question is obtained through the first question, the questioning unit 110 may perform the fourth question immediately after the first question.

In other words, if the patient answers 'Knee hurts when walking', the question unit 110 skips the second and third questions and asks 'What posture hurts the most when walking?' corresponding to the fourth question. can In this case, although repeated answers are requested, the patient may perceive it as a dimension to confirm his or her answer, and may not have negative emotions. Thereafter, the second question and the third question in which the question order is pushed back may be performed.

In order for the patient to recognize as a dimension for confirming his or her answer, the questioning unit 110 identifies a second type of characteristic word included in the first answer instead of the fourth question corresponding to the preset second question. It is possible to output the revised second question of the dimension.

For example, the question unit 110 may immediately perform the fourth question corresponding to the second question after the first question, and in this case, the fourth question may be modified as a question for confirmation.

In other words, when the patient answers 'the knee hurts when walking', the question unit 110 replaces the fourth question 'which posture hurts the most?' Confirmation questions such as 'Does it hurt the most when walking?' with 'when walking' can be performed. According to the present embodiment, the user's discomfort due to the wrong questioning method can be minimized.

On the other hand, 'what kind of pain do you feel? To the question of 'Please express like numbness and throbbing', the patient can answer 'It hurts'.

If the patient answered 'it hurts', it is practically difficult to categorize the patient's condition. This is because experimentally, the expression 'sting' is commonly used (intersecting) in somatic pain, neuropathic pain, and visceral pain.

In this case, even when a plurality of similar questions with different expressions are performed, the patient can continue to answer 'pick' corresponding to the intersecting characteristic word. In order to avoid or exclude the intersecting characteristic word, the question unit 110 may generate an avoidance question including the intersecting characteristic word and an exclusive word excluding the intersecting characteristic word. The avoidance question may include an intersecting characteristic word 'pick', such as 'please express yourself differently except for sting', and may include an exclusive word such as 'exclude'. When asking avoidance questions that contain intersecting characteristic words and exclusive words together, the patient can express pain with other expressions instead of 'sting'.

The check-up device can be operated until the list of check-ups to be carried out per day is completed. When there is no previous questionnaire data for a specific patient, the medical questionnaire may set a patient questionnaire script before surgery.

If there is previous (existing) questionnaire data for a specific patient, the questionnaire may set a patient questionnaire script after surgery.

The preoperative patient questionnaire script will include questions about pain-related pain site, pain pattern, timing of pain intensification, posture intensifying pain, pain intensity, duration of pain, current mood related to stress, anxiety, sleep duration, and sleep quality. can

In the post-operative patient questionnaire, information is collected by dividing pain-related pain, pain pattern, pain intensity, and pain duration for the surgical site and the site of pain before surgery, and stress-related current mood, anxiety, sleep time, and sleep Questionnaires may be included to collect information about the quality of the product.

The questionnaire apparatus of the present invention applies a reinforcement learning algorithm for a natural conversation, so that the questions are not always performed in the same order, but the question order can be variably changed according to circumstances. For example, when a specific answer includes an answer to another question, the other question may be output as a next question for a natural conversation.

Figure 2 is a schematic diagram showing the action of the query order variable algorithm.

The question order variable algorithm can be expressed as Equation 1 below.

[Equation 1]

The question order variable method may use a Q-Learning algorithm.

An action represented by 'a' in Equation 1 may be composed of each question, a first greeting, and an ending greeting.

Actions are 'Greeting', 'Position', 'Quality', 'R_factor1', 'R_factor2', 'Severity', 'Timing', 'Mood', 'Anxiety', 'Sleep1', 'Sleep2', 'Bye', etc. may include. Each action can contain at least 3 sentences including similar questions with the same meaning. After an action is selected, one question among several questions of the corresponding action may be randomly performed.

A state represented by 's' in Equation 1 may represent whether each question (action action) is performed by an array of 0 and 1.

For example, states are [0,0,0,0,0,0,0,0,0,0,0,0] to [1,1,1,1,1,1,1, 1,1,1,1,1] can be composed of 2 ¹² =4096 pieces.

For example, [0,0,0,0,0,0,0,0,0,0,0,0] may indicate a state in which no query is performed. [1,0,0,0,0,0,0,0,0,0,0,1] may indicate a state in which only 'Greeting' and 'Bye' are performed.

As for the reward represented by 'r' in Equation 1, 'Greeting' comes first, 'Bye' is performed after all answers are received, pain questions are first performed, and then stress-related questions are performed. It can be designed to give a reward value for executing the query sequences that fit the criteria.

The question order variable algorithm can be designed to give rewards and penalties. If the penalty value satisfies the set value, the turn may be forcibly ended.

For example, when Greeting appears first, when a Position question is asked after Greeting, when a Quality question is asked after Greeting and Position questions, when the rest of the words related to Pain are followed by Greeting and Position, the Stress question is asked after completing the Pain question. In this case, if Mood questions are performed before Anxiety questions, rewards can be given if Bye is printed after all answers are received. If a reward is given, the priority level to be adopted as a question to be printed next may be increased.

For example, if a Bye question is asked without all other answers received, if the action is not Greeting or Position when a Position answer is not received, when a Quality answer is not received, the action is not one of Greeting, Position, and Quality. In this case, if a stress-related question is asked even though the Pain question has not been completed, if Greeting does not appear first, if the question that has already been answered is performed again, a penalty may be given. If a penalty is given, the priority level to be adopted as the next output question may be lowered. The questionnaire according to the present invention obtains the patient's answer after performing the question, and then determines whether the patient's answer is an appropriate answer to the question. . At this time, the questionnaire determines the patient's status information by matching the data of the vocabulary database 290 with the patient's answer, and when it is not stored in the vocabulary database 290 or when an answer corresponding to another category is performed, the patient Assuming that you did not correctly recognize the intent of the question, you can ask a similar question to help you understand the question again.

The medical questionnaire may update the status information when a correct answer is obtained, and when the answers to all questions are obtained in this way, store the questionnaire result corresponding to the collected status information and transmit it to the server 30 .

The interviewer can communicate the results to the medical staff after completing the interview for all patients that need to be performed. At this time, information about the patient who seems to need a doctor's diagnosis, such as an increase in pain intensity, a prolonged pain duration, or all information related to stress showing poor results, may be additionally transmitted to the medical staff.

3 is a flowchart illustrating a method for collecting patient status information according to the present invention.

The collection method of FIG. 3 may be performed by the paperweight device shown in FIG. 1 .

The server 30 may transmit a list of questionnaires to the robot 10 (S501). Through this, the questionnaire robot 10 can obtain a list of the questionnaire objects. The list of interview subjects may include the patient's UID information, hospital room information, and bed information.

The questionnaire robot 10 or the server 30 may check whether the questionnaire for all patients included in the list is completed (S 514). When all the patient's interview is completed, the interview robot 10 or the server 30 may deliver the interview result to the doctor in charge of each patient (S 515).

The questionnaire robot 10 may move a specific patient included in the list to the target.

The questionnaire robot 10 may recognize identification information of a specific patient and transmit the identified identification information to the server 30 .

If the patient UID corresponding to the identification information obtained from the questionnaire robot 10 matches the list (S 502), the server 30 may search whether existing questionnaire data exists for the identification information of a specific patient. (S 503).

The server 30 may transmit the first question to the questionnaire robot 10 if the existing questionnaire data does not exist (S 504). The server 30 may transmit the second question to the questionnaire robot 10 if the existing questionnaire data exists (S 505).

The questionnaire robot 10 may convert the questions included in the first question or the second question into voice and output it. The questionnaire robot 10 may ask questions whose order is dynamically adjusted based on reinforcement learning (S 506).

The questionnaire robot 10 may collect voice responses of a specific patient (S507). The questionnaire robot 10 may continue to ask questions about a specific patient until it obtains answers to all questions included in the first question or the second question (S 511).

The questionnaire robot 10 may transmit a specific patient's voice response to the server 30 . The server 30 may determine whether the voice answer is correct, and transmit the answer recognition result including the determination result and the next question to the questionnaire robot 10 (S508). When it is determined that the patient's voice answer is incorrect, the questionnaire robot 10 may perform a similar question (S509)

When it is determined that the patient's voice answer is correct, the questionnaire robot 10 may update or self-store the answer recognition result or the patient's state information extracted from the answer recognition result (S 510, S 512). After storing the answer recognition result, the questionnaire robot 10 may output the following questions for a specific patient.

When the questionnaire for a specific patient is finished (S 511), the questionnaire robot 10 may transmit the pre-stored answer recognition result and the recorded data of the voice answer to the server 30 (S 513).

The server 30 may database the answer recognition result and the voice answer.

4 is a diagram illustrating a computing device according to an embodiment of the present invention. The computing device TN100 of FIG. 4 may be a device (eg, a paperweight device, etc.) described herein.

In the embodiment of FIG. 4 , the computing device TN100 may include at least one processor TN110 , a transceiver device TN120 , and a memory TN130 . Also, the computing device TN100 may further include a storage device TN140 , an input interface device TN150 , an output interface device TN160 , and the like. Components included in the computing device TN100 may be connected by a bus TN170 to communicate with each other.

The processor TN110 may execute a program command stored in at least one of the memory TN130 and the storage device TN140. The processor TN110 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to an embodiment of the present invention are performed. The processor TN110 may be configured to implement procedures, functions, and methods described in connection with an embodiment of the present invention. The processor TN110 may control each component of the computing device TN100 .

Each of the memory TN130 and the storage device TN140 may store various information related to the operation of the processor TN110 . Each of the memory TN130 and the storage device TN140 may be configured as at least one of a volatile storage medium and a nonvolatile storage medium. For example, the memory TN130 may include at least one of a read only memory (ROM) and a random access memory (RAM).

The transceiver TN120 may transmit or receive a wired signal or a wireless signal. The transceiver TN120 may be connected to a network to perform communication.

On the other hand, the embodiment of the present invention is not implemented only through the apparatus and/or method described so far, and a program for realizing a function corresponding to the configuration of the embodiment of the present invention or a recording medium in which the program is recorded may be implemented. And, such an implementation can be easily implemented by those skilled in the art from the description of the above-described embodiments.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention as defined in the following claims are also present. It belongs to the scope of the invention.

10... Paperweight Robot 30... Server
110...Question Division 120...Collection Division
130...Management Department 140...Recording Department
150...Movement unit 210...Processing unit
220...Converter 230...Extractor
240...Judgement 290...Database

Claims (7)

a questioning unit for outputting a question leading to a patient's voice answer;
a collection unit for collecting the voice responses;
a management unit for managing the voice response by matching it with the patient's identification information;
A paperweight device comprising a.
According to claim 1,
A conversion unit for converting the voice response into text, an extraction unit for extracting the patient's status information from the voice response or the text, and a recording unit for recording the voice response are provided,
The management unit manages by additionally matching at least one of the text and the status information to the identification information,
The identification information includes a UID (User Identifier) in which at least one of a number, a letter, and a special symbol is combined in a plurality, and is formed regardless of the patient's personal information.
According to claim 1,
A moving unit that physically moves or communicatively moves the interrogation unit and the collecting unit is provided,
When the list of questionnaires is obtained, the moving unit moves the questioning unit and the collecting unit to the target bed of the hospital room where the specific patient included in the list is hospitalized,
When the interrogator and the collection unit meet the state of facing the bed, the moving unit obtains the current identification information of the patient directly from the patient located on the bed separately from the list,
The questioning unit outputs a different question depending on whether there is existing questionnaire data targeting the current identification information obtained through the mobile unit.
According to claim 1,
A determination unit is provided for determining whether the patient's voice answer to a specific question intended for a first type of answer is correct,
The determination unit extracts a characteristic word from among a plurality of words included in the voice answer,
The determination unit determines whether the characteristic word exists in the set answer list for the question,
When the question unit does not include the characteristic word in the set answer list, the questionnaire outputs a similar question intended for the first type of answer instead of moving on to the next question.
According to claim 1,
When a first answer is obtained through a first question for obtaining a first type of characteristic word, the collection unit detects not only the first type of characteristic word but also a second type of characteristic word from the first answer,
When the second type of characteristic word is detected in the first answer, the question unit sets a second question item for obtaining the second type of characteristic word to the question immediately following the first question item regardless of a preset question order A paperweight device that decides and outputs the matter.
6. The method of claim 5,
The questioning unit outputs a modified second question item in the dimension of confirming the second type of characteristic word included in the first answer instead of a preset second question item.
In the patient's condition information collection method performed by the questionnaire device,
Transmitting a list of the questionnaire object from the server to the questionnaire robot;
moving, by the questionnaire robot, a specific patient included in the list to a target;
The step of the questionnaire robot identifying the identification information of the specific patient, and transmitting the identified identification information to the server;
retrieving whether existing questionnaire data exists with respect to the identification information of the specific patient in the server;
transmitting a first question to the questionnaire robot if the existing questionnaire data does not exist in the server, and transmitting a second question to the questionnaire robot if the existing questionnaire data exists;
converting the first question or the second question into voice in the questionnaire robot and outputting it;
collecting the voice response of the specific patient in the questionnaire robot and transmitting the voice response to the server;
determining whether the voice answer is correct in the server, and transmitting an answer recognition result including the determination result and a next question to the questionnaire robot;
storing the answer recognition result in the questionnaire robot and outputting the next question to the specific patient;
transmitting the pre-stored answer recognition result and the recorded data of the voice answer to the server when the interviewing robot for the specific patient is finished;
databaseizing the answer recognition result and the voice answer in the server;
A collection method comprising.

Images