KR102263973B1 - Artificial intelligence based scheduling system - Google Patents

Abstract

An artificial intelligence-based schedule management system for analyzing a user's call voice and managing the user's schedule based on the analyzed call content is disclosed. The artificial intelligence-based schedule management system according to an embodiment of the present invention receives the user's voice call contents, and converts the voice call contents into text based on the received voice call contents to generate call information. and, extracting the user's schedule from the call information to generate schedule-related information, and based on the generated schedule-related information, derive schedule information suitable for the user's situation, and use the derived schedule information to the user It may include a schedule management unit that proposes to

Description

Artificial intelligence based scheduling system

The present invention relates to an artificial intelligence-based schedule management system. In more detail, it relates to an artificial intelligence-based schedule management system that analyzes a user's call voice and manages the user's schedule based on the analyzed call content.

Speech Recognition refers to a technology that analyzes speech by a computer, converts it into text data, and processes it. It is one of the technologies attracting attention in that it can quickly and easily input information by voice without using a separate input device such as a keyboard.

Voice recognition in smartphones has been applied and used in various ways. The iPhone provided a voice command function so that simple commands such as running an app could be executed by voice, and Google provided a service that allows you to search the web by voice.

In addition, a translation application that receives the user's voice input and speaks it in another language or an application that checks whether the user's pitch is correct are examples of using voice recognition technology.

On the other hand, smartphones are being used through text-based SNS (eg KakaoTalk, Line, etc.) and voice calls. In the case of business, work schedules are coordinated through voice calls. In the case of a user who has many customers, he or she schedules the borrower or the next schedule while on the phone, checks the duplicate schedule, and the like. However, when moving through a vehicle, it is very difficult to register a schedule after the call ends.

To solve this problem, it was necessary to implement a service for checking and registering schedules through voice.

Laid-open Patent Publication No. 10-2009-0106630

An object of the present invention is to provide an artificial intelligence-based schedule management system that analyzes a user's call voice and manages the user's schedule based on the analyzed call content.

The artificial intelligence-based schedule management system according to an embodiment of the present invention for solving the above technical problem analyzes a user's call voice and manages the user's schedule based on the analyzed call contents, A call unit that receives the content of a voice call and converts the content of the voice call into text based on the received voice call content to generate call information, and extracts the user's schedule from the call information to generate schedule-related information and a schedule management unit for deriving schedule information suitable for the user's situation based on the generated schedule-related information, and proposing the derived schedule information to the user.

The call unit may include a call receiver for receiving the contents of the voice call.

The call unit includes a call recognition unit, and the call recognition unit extracts the user's voice information based on the content of the voice call.

The call recognition unit analyzes the extracted voice information as the user's voice pattern, segments the voice information for each voice, and matches the segmented voice with a specific word to generate voice unit information.

The call recognition unit learns the user's voice pattern from the user's uttered voice, and updates the accuracy of the voice pattern.

The call unit further includes a currency conversion unit, and the currency conversion unit generates the call information by converting the content of the voice information into text based on the voice unit information.

The currency conversion unit provides a summary of the text of the currency information to the user.

The schedule management unit includes a schedule generating unit, and the schedule generating unit generates schedule related information by extracting schedule related information included in the call information based on the call information.

The schedule management unit further includes a schedule comparison unit, wherein the schedule comparison unit compares the schedule-related information with the user's existing schedule to generate the schedule information.

When it is determined that the user does not have the existing schedule, the schedule comparison unit generates the schedule-related information as the schedule information as it is.

When it is determined that the user's existing schedule and the schedule-related information do not overlap with each other, the schedule comparison unit generates the schedule-related information as the schedule information as it is.

When the schedule comparison unit determines that the user's existing schedule and the schedule-related information overlap with each other, schedule adjustment request information including duplicate content between the existing schedule and the schedule-related information to adjust the schedule-related information create

The schedule management unit further includes a schedule adjustment unit, and when the schedule adjustment unit receives the schedule adjustment request information, it modifies the schedule-related information.

When the meeting time of the existing schedule and the schedule-related information overlaps, the schedule adjustment unit calculates the movement time based on the position of the existing schedule and the position of the schedule-related information, calculates the optimal location, and calculates the calculated By reflecting the optimal location, the meeting time of the schedule-related information is corrected, and the modified schedule-related information is generated.

When the meeting time of the existing schedule and the schedule-related information overlaps, the schedule adjustment unit calculates the expected required time of the existing schedule and the schedule-related information, and corrects the meeting time of the schedule-related information to modify the schedule-related information create

The schedule management unit generates the schedule information by modifying the schedule-related information based on the modified schedule-related information, suggests the daily information to the user, and transmits the schedule information to the user's call counterpart.

When the counterpart confirms the schedule information, a meeting schedule between the user and the counterpart is confirmed.

The call unit includes a call storage unit, and the call storage unit stores the contents of the voice call.

According to the present invention, there is provided an artificial intelligence-based schedule management system that analyzes a user's call voice and manages the user's schedule based on the analyzed call content.

The effects of the present invention are not limited to the above-mentioned effects, and the effects of other inventions can also be clearly understood from the description of the claims.

1 is a block diagram of an AI-based schedule management system according to an embodiment of the present invention.
2 is a flowchart illustrating a schedule management procedure of an AI-based schedule management system according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in a variety of different forms, and only these embodiments allow the disclosure of the present invention to be complete, and common knowledge in the technical field to which the present invention belongs It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the scope of the claims. Detailed contents for carrying out the present invention will be described in detail with reference to the accompanying drawings below. Regardless of the drawings, like reference numbers refer to like elements, and "and/or" includes each and every combination of one or more of the recited items.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. As used herein, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly defined in particular.

Hereinafter, an artificial intelligence-based schedule management system according to an embodiment of the present invention will be described.

1 is a block diagram of an AI-based schedule management system according to an embodiment of the present invention, and FIG. 2 is a flowchart illustrating a schedule management procedure of an AI-based schedule management system according to an embodiment of the present invention.

1 and 2 , the artificial intelligence-based schedule management system 10 according to an embodiment of the present invention may analyze the user's call voice and manage the user's schedule based on the analyzed call content. To this end, the AI-based schedule management system 10 according to an embodiment of the present invention receives the user's voice call content, and converts the voice call content into text based on the received voice call content to make a call The call unit 100 for generating information, extracts the user's schedule from the call information to generate schedule-related information, and based on the generated schedule-related information, derives schedule information suitable for the user's situation, , and a schedule management unit 200 that proposes the derived schedule information to the user. Meanwhile, the artificial intelligence-based schedule management system 10 of the present invention may be implemented as software executed by one or more processors of a computing device. In addition, the artificial intelligence-based schedule management system 10 is a mobile phone, a smart phone (smart phone), a notebook computer (notebook computer), a digital broadcasting terminal, PDA (Personal Digital Assistants), PMP (Portable Multimedia Player), navigation, tablet It may be a device applied to a PC, software, or a device driven by software.

First, the AI-based schedule management system 10 of the present invention may include a call unit 100 . The call unit 100 may include a call receiver 110 , a call recognition unit 120 , a currency conversion unit 130 , and a call storage unit 140 .

The call receiving unit 110 receives the user's voice call, which is the content of the call between the user and the user's counterpart (S101). To this end, the call receiver 110 receives an external sound signal by a microphone in a call mode, a recording mode, a voice recognition mode, and the like, and processes it as electrical voice data. That is, the content of the voice call may be converted into voice data, received and temporarily stored. On the other hand, the microphone may implement various noise removal algorithms for removing noise generated in the process of receiving an external sound signal.

Subsequently, the call recognition unit 120 of the call unit 100 extracts the user's voice information based on the content of the voice call received from the call receiver 110 . The call recognition unit 120 recognizes only the user's voice among various sounds included in the voice call content, and extracts voice information based thereon.

To this end, the call recognition unit 120 may include a voice information extraction unit (not shown). The voice information extraction unit regards only the user's voice input through the microphone as voice information, extracts only the user's voice from among various sounds, and extracts and generates voice information.

The call recognition unit 120 generates voice unit information from the extracted voice information. The voice unit information may be performed by a voice pattern analysis unit (not shown) of the call recognition unit 120 . More specifically, the voice pattern analyzer learns and stores the user's voice pattern. That is, data obtained by matching the user's voice pattern with respect to a specific word, learned through the user's usual speaking habits, etc., is stored. That is, a specific word group corresponding to the user's voice pattern is stored. For example, the user's voice pattern corresponding to the word "Gangnam Station" is stored as sound wave data. A plurality of such data may exist.

The voice pattern analyzer receiving the voice information from the voice information extractor analyzes the voice information as the user's voice pattern. At this time, the voice information is segmented for each voice corresponding to the voice pattern, and the segmented voice is matched with a specific word to generate voice unit information. That is, the user's voice information is analyzed as the learned user's voice pattern, and the words included in the voice information are analyzed through this. Words included in the voice information and analyzed are generated as voice unit information.

On the other hand, the voice pattern analyzer of the call recognition unit 120 continuously learns the user's voice pattern from the user's uttered voice to improve and update the accuracy of the voice pattern. As the accuracy of the voice pattern is improved, it is possible to more accurately analyze and extract the words included in the voice information. Learning of voice patterns can be implemented through artificial intelligence technology. Through the above-described process, the call recognition unit 120 recognizes the user's call (S102).

The call unit 100 includes a currency conversion unit 130 , and the currency conversion unit 130 converts the content of the voice information into text based on the voice unit information received from the call recognition unit 120 . That is, the phonetic unit information includes information on words matching the phonetic unit, and these words are converted into text. Through this, the content of the voice information is converted into text, and the voice information is generated as call information (S103). On the other hand, the currency conversion unit 130 may provide a summary of the sentence content of the call information including the text information to the user. For example, the content of the text may be summarized within 20 characters, and the summarized content may be provided to the user as a notification. Thereby, the user can quickly obtain information about the schedule.

Next, the schedule management unit 200 of the AI-based schedule management system 10 will be described as follows. The schedule management unit 200 may include a schedule generator 210 , a schedule comparison unit 220 , a schedule registration unit 230 , a schedule adjustment unit 240 , and a schedule notification unit 250 .

The schedule generation unit 210 receives call information from the currency conversion unit 130 . Based on the received call information, schedule-related information is generated by extracting schedule-related information included in the call information. To this end, the schedule generator 210 may have character data related to the schedule as a reference. Based on the reference, schedule-related text is extracted from the call information, and schedule-related information is primarily generated with the extracted text (S201).

Subsequently, the schedule comparison unit 220 compares the schedule-related information with the user's existing schedule, and generates schedule information (S202). This will be described in more detail as follows.

First, when it is determined that there is no existing schedule of the user, the schedule comparison unit 220 generates the schedule-related information as the schedule information as it is (S203). That is, without modifying the generated schedule-related information, it is generated as schedule information and automatically registered as the user's schedule in the schedule registration unit 230 . Accordingly, the user can check his/her schedule without a separate record. That is, a schedule is automatically created only by a call with the other party (S205).

Meanwhile, when it is determined that the user's existing schedule exists, but the existing schedule and the schedule-related information do not overlap with each other, the schedule comparison unit 220 generates the schedule-related information as the schedule information as it is (S204). ). That is, without modifying the generated schedule-related information, it is generated as schedule information and automatically registered as the user's schedule in the schedule registration unit 230 (S205).

Next, when the schedule comparison unit 220 determines that the user's existing schedule and the schedule-related information overlap with each other, the duplicate content between the existing schedule and the schedule-related information is compared to adjust the schedule-related information. It is possible to generate schedule adjustment request information including (S204). The schedule adjustment request information may include a meeting date that overlaps the existing schedule and the schedule-related information, and a time for cooking. The schedule-related information is corrected by the above information.

Specifically, the generated schedule adjustment request information is transmitted to the schedule adjustment unit 240 . When the schedule adjustment unit 240 receives the schedule adjustment request information, it corrects the schedule-related information based on the overlapping contents (S206)

For example, when the meeting time of the existing schedule and the schedule-related information overlaps, the schedule adjustment unit 240 calculates a movement time based on the position of the existing schedule and the position of the schedule-related information, The location is calculated, and the meeting time of the schedule related information is corrected by reflecting the calculated optimal location to generate the modified schedule related information (S206). In addition, when the meeting time of the existing schedule and the schedule-related information overlaps, the schedule adjustment unit calculates the expected required time between the existing schedule and the schedule-related information, and corrects the meeting time of the schedule-related information to modify the schedule. Related information may be generated (S206). The schedule adjustment unit 240 modifies the previously generated schedule related information based on the generated modified schedule related information to finally generate schedule information.

The schedule management unit 200 generates the schedule information by modifying the schedule-related information based on the modified schedule-related information, proposes the daily information to the user, and transmits the schedule information to the user's call counterpart do (S207). The transmission of schedule information may be performed through the schedule notification unit 250 . When the other party confirms the schedule information (S208), the meeting schedule between the user and the other party is confirmed. The confirmed schedule information is stored in the schedule registration unit 230 (S205).

The algorithm for obtaining the distribution of meeting time for the entire schedule will be described in more detail as follows.

Typically, a time distribution can be obtained through a semantic category group.

이다.Here, the semantic category group is

to be.

Meanwhile, the estimated time is as follows.

은 시맨틱 카테고리 그룹

의 세부그룹으로 정의되고, 회의 예상시간에 대한 분포는 다음과 같다.Meeting Estimated Time Distribution Group

is the semantic category group

It is defined as a subgroup of , and the distribution of the expected meeting time is as follows.

Time series data analysis (Dynamic Time warping, DTW) and hierarchical clustering techniques are used to obtain the expected meeting time. Predicted running times are possible for meetings that the user has not yet conducted.

, 회의 시간 반환하는 함수

라 하면, 아직 진행하지 않은 회의는

가 시맨틱 카테고리 그룹

에 속한다. 회의 예상시간 분포 그룹

에 속할 경우, 예상 회의 진행 시간은 반환하는 함수

로 정의된다.About a meeting hosted by user μ

, a function that returns the meeting time

In other words, a meeting that has not been held

A semantic category group

belongs to Meeting Estimated Time Distribution Group

A function that returns the expected meeting duration when belonging to

is defined as

Based on these premises, the expected meeting time can be calculated as follows.

이고, 사용자 μ가 아직 진행하지 않은 미회의

의 예상시간

는

과 같은 분포인

의 평균시간은 다음과 같다.All visiting meetings of user μ

, and the user μ has not yet proceeded

estimated time of

is

the same distribution as

The average time of

Meanwhile, the recommended schedule is as follows.

By the above algorithm, the user's meeting schedule may be determined.

The above method is only an example, and it will be said that there are various methods of coordinating the entire schedule in consideration of the meeting time and expected time.

Meanwhile, the call unit 100 includes a call storage unit 140 , and the call storage unit 140 stores the contents of the voice call. To this end, the call storage unit 140 includes a flash memory type, a hard disk type, a multimedia card micro type, and a card type memory (eg, SD or XD). memory, etc.), RAM (Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) magnetic It may include at least one type of storage medium among a memory, a magnetic disk, and an optical disk. The user can check the stored voice calls whenever necessary.

The controller 300 typically controls the AI-based schedule management system 10 . By controlling the control of the call unit 100 and the schedule management unit 200, it is possible to propose and register a schedule in a voice call.

Meanwhile, an embodiment of the present invention may be implemented in a computer-readable recording medium using, for example, software, hardware, or a combination thereof.

According to the hardware implementation, the embodiments described herein are ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays, It may be implemented using at least one of processors, controllers, micro-controllers, microprocessors, and electrical units for performing functions. It may be implemented by the control unit 300 .

According to the software implementation, embodiments such as a procedure or function may be implemented together with a separate software module for performing at least one function or operation. The software code may be implemented by a software application written in a suitable programming language.

The artificial intelligence-based schedule management system 10 according to an embodiment of the present invention may be implemented as, for example, a data processing device.

Data processing apparatus includes all kinds of apparatuses, devices, and machines for processing data, including through an exemplary programmable processor, computer, system on a chip, or many, or combinations of the foregoing. . The device may include special purpose logic circuitry, such as, for example, a field programmable gate way array (FPGA) or an application-specific integrated circuit (ASIC). The device may also include, in addition to hardware, code that constitutes processor firmware, protocol stack, database management system, operating system, cross-platform runtime environment, virtual machine, or one or more combinations thereof; Contains code that creates an execution environment for the computer program in question. The coexistence and execution environment may realize a variety of different computing model infrastructures, such as, for example, web services, distributed computing, and grid computing infrastructures.

A computer program (also known as a program, software, software application, script or code) may be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, said A computer program may be deployed in any form, including as a standalone program or module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program, although not required, may correspond to a file in a file system. A program may be stored in other programs or parts of a file holding data (eg, one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple organized files (eg, for example, one or more modules, sub-programs, or files that store portions of code). A computer program may be deployed to be executed on one computer or multiple computers, wherein the single computer or multiple computers are located at one site or are distributed over multiple sites and are connected to a communication network. are interconnected by

The processes and logic flows may be performed by one or more programmable computers by operating on input data and generating output, the programmable computers executing one or more computer programs to perform functions. The processes and logic flows and apparatus in which they may be implemented may also be implemented by special purpose logic circuitry, such as, for example, a field programmable gate way array (FPGA) or application specific integrated circuit (ASIC).

Processors suitable for execution of a computer program include, by way of example, general and special purpose microprocessors and any one or more processors of any kind in digital computers. In general, a processor will receive instructions and data from read-only memory or random accessor memory or both. The essential elements of a computer are a processor for performing operations consistent with the instructions and one or more memory devices for storing instructions and data. In general, a computer includes, receives data from, or transmits data to, or operatively on one or more mass storage devices, eg, one or more mass storage devices, eg, magnetic, magneto-optical disks or optical disks. can be connected However, the computer need not include these devices. Furthermore, a computer may be, to name a few, for example, a mobile telephone, PDA, mobile audio or video player, game console, Global Positioning System (GPS) receiver or portable storage device (eg, a universal serial bus (USB ) may be included in other devices, such as flash drives). Devices suitable for storing computer program instructions and data are, for example, EPROM, EEPROM and flash memory devices, magnetic disks such as an internal hard disk or removable disks, magneto-optical disks and CD - Includes all forms of non-volatile memory, media and memory devices, including by way of example methods of semiconductor memory devices, such as ROM and DVD-ROM disks. The processor and memory may be supplemented by, or integrated into, special purpose logic circuitry.

Although the embodiments of the present invention have been described above, the present invention is not limited to the above embodiments, but may be manufactured in a variety of different forms, and those of ordinary skill in the art to which the present invention pertains will appreciate the technical spirit of the present invention However, it will be understood that the invention may be embodied in other specific forms without changing essential features. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

10: artificial intelligence-based schedule management system 100: Ministry of currency
110: call receiving unit 120: call recognition unit 130: currency conversion unit
140: call storage unit 200: schedule management unit 210: schedule generation unit
220: schedule comparison unit 230: schedule register 240: schedule adjustment unit
250: schedule notification unit

Claims (13)

In the artificial intelligence-based schedule management system that analyzes the user's call voice and manages the user's schedule based on the analyzed call content,
a call unit for receiving the user's voice call content, and converting the voice call content into text based on the received voice call content to generate call information; and
The user's schedule is extracted from the call information to generate schedule-related information, and based on the generated schedule-related information, schedule information suitable for the user's situation is derived, and the derived schedule information is proposed to the user. including a schedule management unit that
The call unit includes a call receiver for receiving the content of the voice call,
The call unit includes a call recognition unit for extracting the user's voice information based on the content of the voice call,
The schedule management unit includes a schedule generator for generating schedule related information by extracting schedule related information included in the call information based on the call information,
The call unit includes a call storage unit, characterized in that the call storage unit stores the content of the voice call,
The schedule management unit further includes a schedule comparison unit, wherein the schedule comparison unit compares the schedule-related information with the user's existing schedule to generate the schedule information,
When it is determined that the schedule comparison unit does not overlap with the user's existing schedule and the schedule-related information, the schedule-related information is generated as the schedule information as it is,
When the schedule comparison unit determines that the user's existing schedule and the schedule-related information overlap with each other, schedule adjustment request information including duplicate content between the existing schedule and the schedule-related information in order to adjust the schedule-related information create,
The schedule management unit further includes a schedule adjustment unit, and when the schedule adjustment unit receives the schedule adjustment request information, it modifies the schedule-related information,
When the meeting time of the existing schedule and the schedule-related information overlaps, the schedule adjustment unit calculates the movement time based on the position of the existing schedule and the position of the schedule-related information, calculates an optimal position, and calculates the calculated Modifying the meeting time of the schedule-related information by reflecting the optimal location to generate modified schedule-related information, or
When the meeting time of the existing schedule and the schedule-related information overlaps, the schedule adjustment unit calculates the expected required time between the existing schedule and the schedule-related information, and corrects the meeting time of the schedule-related information to modify the schedule-related information create,
The schedule management unit generates the schedule information by modifying the schedule-related information based on the modified schedule-related information, proposes the schedule information to the user, and transmits the schedule information to the user's counterpart,
When the counterpart confirms the schedule information, an artificial intelligence-based schedule management system in which a meeting schedule between the user and the counterpart is confirmed. The method of claim 1,
The call recognition unit analyzes the extracted voice information as the user's voice pattern, segments the voice information by voice, and matches the segmented voice with a specific word to generate voice unit information. based scheduling system. 3. The method of claim 2,
The call recognition unit learns the user's voice pattern from the user's uttered voice, and updates the accuracy of the voice pattern. 3. The method of claim 2,
The call unit further includes a currency conversion unit, wherein the call conversion unit converts the content of the voice information into text based on the voice unit information to generate the call information. 5. The method of claim 4,
The currency conversion unit artificial intelligence-based schedule management system, characterized in that the summary of the sentence content of the call information is provided to the user. delete The method of claim 1,
The schedule comparison unit artificial intelligence-based schedule management system, characterized in that when it is determined that the user does not have the existing schedule, the schedule-related information is generated as the schedule information as it is. delete delete delete delete delete delete

Images