KR102395697B1 - Video conference system server which is able to take minutes of a video conference and the operating method thereof - Google Patents

Abstract

Disclosed are a video conferencing system server capable of generating meeting minutes and an operating method thereof. The present invention identifies voice data corresponding to each user among voice signals transmitted from terminals of users participating in a video conference, and converts voice data into voice recognition text based on voice recognition technology to record voice recognition text. By presenting a video conferencing system server capable of generating meeting minutes that, after generating a meeting minutes document, transmits a file for the created meeting minutes document to users' terminals, and an operating method thereof, it is possible to increase the convenience of users using the video meeting service. there is.

Description

A video conferencing system server capable of generating meeting minutes and an operating method thereof

The present invention relates to a video conferencing system server capable of generating meeting minutes and an operating method thereof.

Recently, as electronic terminal devices, such as computers, smart phones, or tablet PCs, have become widespread, various video conferencing services have emerged that allow meetings to be conducted even in situations where it is impossible to face-to-face using such electronic terminal devices.

In particular, as the global COVID-19 pandemic continues for a long time, in a situation where contact and movement between people are limited, users who use video conferencing services to hold meetings between people in remote places are increasing.

On the other hand, in order to organize the contents of the meeting, people attending the meeting often write meeting minutes in which the contents of the meeting are recorded. However, in order to record the meeting contents in the past, there was a inconvenience in that a person attending the meeting had to write the meeting minutes by typing the meeting contents directly. In addition, since it is difficult to memorize the details of the meeting, there was a problem that important content was omitted in the process of writing the meeting minutes.

In this regard, in the process of conducting a video conference, based on the audio signal received from the terminals of users participating in the video conference, using the speech recognition technology to convert the speech data into text, it is supported to create a document of the meeting minutes You can consider introducing a video conferencing system.

If the meeting minutes document can be created through the video conferencing system without the person attending the video conference directly typing, the convenience of users attending the video conference may be increased. In addition, if the file for the generated meeting minutes document can be transmitted to the terminals of users participating in the video conference, the users will be able to easily check the meeting contents by executing the file for the received meeting minutes document.

Therefore, there is a need for a study on a technology for a video conference service capable of generating minutes based on voice signals transmitted from terminals of users participating in the video conference.

The present invention identifies voice data corresponding to each user among voice signals transmitted from terminals of users participating in a video conference, and converts voice data into voice recognition text based on voice recognition technology to record voice recognition text. By presenting a video conferencing system server capable of generating meeting minutes that, after generating a meeting minutes document, transmits a file for the created meeting minutes document to users' terminals, and an operating method thereof, the convenience of users using the video meeting service can be increased. We want to support you to

The video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention relates to a signal section in which a signal having a volume equal to or higher than a preset reference volume among sound signals transmitted from each terminal of a plurality of users participating in the video conference is maintained. A data identification unit for identifying sound data as voice data corresponding to each of the plurality of users, whenever the voice data corresponding to each of the plurality of users is identified, the voice data corresponding to each of the plurality of users , a storage processing unit that matches identification information on a user corresponding to each voice data and information on an order in which each voice data is identified and stores them in the voice data storage unit; When a termination request for terminating the video conference is received from the terminal, an event generating unit for terminating the video conference and generating a meeting minutes event for creating minutes for the video conference, when the meeting minutes creation event occurs , After extracting voice data corresponding to each of the plurality of users from the voice data storage unit, a preset voice recognition model for converting voice data into text for voice data corresponding to each of the plurality of users A text generator for generating a plurality of speech recognition texts by performing speech recognition based on voice recognition and converting speech data corresponding to each of the plurality of users into text, and when the plurality of speech recognition texts are generated, the plurality of speech A document generation unit for generating a meeting minutes document recorded by sequentially listing the recognition texts along with identification information on the user corresponding to each of the voice recognition texts according to the order in which the voice data corresponding to each of the plurality of users are identified, and the and a file transmission unit for transmitting a file for the meeting minutes document to terminals of the plurality of users when the meeting minutes document is generated.

In addition, in the method of operating a video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention, a signal having a volume greater than or equal to a preset reference volume among sound signals transmitted from each terminal of a plurality of users attending the video conference is maintained. Identifying sound data for a signal section to be used as voice data corresponding to each of the plurality of users, whenever voice data corresponding to each of the plurality of users is identified, corresponding to each of the plurality of users storing the voice data in a voice data storage unit by matching the voice data with identification information on a user corresponding to each voice data and information on an order in which each voice data is identified; When a termination request for terminating the video conference is received from the user's terminal, terminating the video conference and generating a meeting minutes event for creating minutes for the video conference; , After extracting voice data corresponding to each of the plurality of users from the voice data storage unit, a preset voice recognition model for converting voice data into text for voice data corresponding to each of the plurality of users generating a plurality of voice recognition texts by performing voice recognition based on voice recognition and converting voice data corresponding to each of the plurality of users into text; when the plurality of voice recognition texts are generated, the plurality of voice recognition texts According to the order in which the voice data corresponding to each of the plurality of users are identified, sequentially listing together with identification information about the user corresponding to each voice recognition text to generate a recorded meeting minutes document, and the meeting minutes document is generated If done, the step of transmitting the file for the meeting minutes document to the terminals of the plurality of users.

The present invention identifies voice data corresponding to each user among voice signals transmitted from terminals of users participating in a video conference, and converts voice data into voice recognition text based on voice recognition technology to record voice recognition text. By presenting a video conferencing system server capable of generating meeting minutes that, after generating a meeting minutes document, transmits a file for the created meeting minutes document to users' terminals, and an operating method thereof, it is possible to increase the convenience of users using the video meeting service. there is.

1 is a diagram showing the structure of a video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention.
2 is a diagram for explaining the operation of a video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention.
3 is a flowchart illustrating an operation method of a video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. These descriptions are not intended to limit the present invention to specific embodiments, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. While describing each drawing, like reference numerals are used for similar components, and unless otherwise defined, all terms used in this specification, including technical or scientific terms, refer to those of ordinary skill in the art to which the present invention belongs. It has the same meaning as is commonly understood by those who have it.

In this document, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated. In addition, in various embodiments of the present invention, each of the components, functional blocks or means may be composed of one or more sub-components, and the electrical, electronic, and mechanical functions performed by each component are electronic. A circuit, an integrated circuit, an ASIC (Application Specific Integrated Circuit), etc. may be implemented as various well-known devices or mechanical elements, and may be implemented separately or two or more may be integrated into one.

On the other hand, the blocks in the accompanying block diagram or steps in the flowchart are computer program instructions that are loaded in a processor or memory of equipment capable of data processing, such as a general-purpose computer, a special-purpose computer, a portable notebook computer, and a network computer, and perform specified functions. can be interpreted as meaning Since these computer program instructions may be stored in a memory provided in a computer device or in a computer-readable memory, the functions described in the blocks of the block diagram or the steps of the flowchart are produced as articles of manufacture containing instruction means for performing the same. it might be In addition, each block or each step may represent a module, segment, or portion of code comprising one or more executable instructions for executing the specified logical function(s). It should also be noted that, in some alternative embodiments, it is also possible for the functions recited in blocks or steps to be executed out of the prescribed order. For example, two blocks or steps shown one after another may be performed substantially simultaneously or in the reverse order, and in some cases, some blocks or steps may be omitted.

1 is a diagram showing the structure of a video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention.

The video conferencing system server 110 capable of generating meeting minutes according to an embodiment of the present invention includes a data identification unit 111, a storage processing unit 112, an event generation unit 113, a text generation unit 114, and a document generation unit. 115 and a file transfer unit 116 .

The data identification unit 111 provides sound data for a signal section in which a signal having a volume greater than or equal to a preset reference volume among sound signals transmitted from each of the terminals 141, 142, and 143 of a plurality of users participating in the video conference continues. It is identified as voice data corresponding to each of the plurality of users.

At this time, according to an embodiment of the present invention, the data identification unit 111 is configured to generate sound data for a signal section in which a signal having a volume equal to or higher than the reference volume among the sound signals is maintained for a time equal to or greater than a preset reference time. It can be identified by voice data corresponding to each of the users.

For example, it is assumed that the plurality of users are 'User 1, User 2, and User 3', the preset reference volume is '60 dB', and the preset reference time is '0.5 seconds'. At this time, when it is said that there is a signal section in which a signal having a volume of '60dB' or more among the sound signals transmitted from the terminal 141 of 'User 1' lasts for '2 seconds', the data identification unit 111 is the signal Sound data for the section may be identified as voice data corresponding to 'User 1'.

Whenever the voice data corresponding to each of the plurality of users is identified, the storage processing unit 112 stores the voice data corresponding to each of the plurality of users, identification information about the user corresponding to each voice data, and each voice The data is matched with information about the identified sequence and stored in the voice data storage unit.

For example, identification information for the plurality of users 'User 1, User 2, and User 3' is referred to as 'Identification Information 1, Identification Information 2, and Identification Information 3', respectively, and the voice data identified for 'User 1' 'Voice data 1, voice data 2, voice data 5, voice data 6', and the voice data identified for 'user 2' are called 'voice data 3, voice data 7', and 'user 3' is identified Assume that the received voice data is 'voice data 4'. Also, suppose that the voice data are identified in the order of 'voice data 1, voice data 2, voice data 3, voice data 4, voice data 5, voice data 6, and voice data 7' through the data identification unit 111 . . At this time, as shown in Table 1 below, the storage processing unit 112 adds 'voice data 1, voice data 2, voice data 3, voice data 4, voice data 5, voice data 6, and voice data 7' to each voice data. The identification information for the corresponding user and information on the order in which each voice data is identified may be matched with each other and stored in the voice data storage unit.

for each of multiple users.
Corresponding voice data corresponding to voice data
Identification information about you The order in which voice data was identified voice data 1 Identification 1 One voice data 2 Identification 1 2 voice data 3 Identification 2 3 voice data 4 Identification 3 4 voice data 5 Identification 1 5 voice data 6 Identification 1 6 voice data 7 Identification 2 7

The event generating unit 113 terminates the video conference when a termination request for terminating the video conference is received from the terminal of the first user, which is one of the plurality of users, and creates minutes for the video conference. It raises the event of making meeting minutes to perform.

The text generator 114 extracts voice data corresponding to each of the plurality of users from the voice data storage unit when the event generating event is generated by the event generator 113, and then extracts voice data corresponding to each of the plurality of users. For voice data corresponding to , by performing voice recognition based on a preset voice recognition model for converting voice data into text and converting voice data corresponding to each of the plurality of users into text, a plurality of voice recognition Create texts.

For example, when a termination request for terminating the video conference is received from the terminal 141 of 'User 1' among the plurality of users 'User 1, User 2, and User 3', It is assumed that the video conference ends and a meeting minutes event for the video conference occurs.

At this time, as shown in Table 1, 'voice data 1, voice data 2, voice data 5, voice data 6' corresponding to 'user 1', 'voice data 3, voice data 7' corresponding to 'user 2' and When it is assumed that 'voice data 4' corresponding to 'user 3' is stored in the voice data storage unit, the text generation unit 114 receives voice data corresponding to each of the plurality of users from the voice data storage unit. It is possible to extract 'voice data 1, voice data 2, voice data 3, voice data 4, voice data 5, voice data 6, and voice data 7'.

Then, the text generating unit 114 performs voice recognition on the voice data corresponding to each of the plurality of users based on a preset voice recognition model for converting the voice data into text, so that the plurality of users A plurality of speech recognition texts may be generated by converting speech data corresponding to each of the texts.

In this regard, the text generator 114 may generate 'voice recognition text 1' by converting 'voice data 1' corresponding to 'user 1' into text by performing voice recognition based on the voice recognition model. there is. In this way, the text generation unit 114 generates 'voice recognition text 1, voice recognition text 2, and voice recognition text from 'voice data 1, voice data 2, voice data 5, and voice data 6' corresponding to 'user 1'. 5, voice recognition text 6' may be generated, and 'voice recognition text 3, voice recognition text 7' may be generated from 'voice data 3, voice data 7' corresponding to 'user 2', and 'user 3 'Speech recognition text 4' may be generated from 'voice data 4' corresponding to '.

When the plurality of speech recognition texts are generated by the text generator 114, the document generation unit 115 generates the plurality of speech recognition texts according to the order in which voice data corresponding to each of the plurality of users is identified, A document of recorded meeting minutes is generated by sequentially arranging it together with identification information about the user corresponding to each speech recognition text.

Here, the identification information about the user means information that can identify each user, such as a name, an alias, an ID of each user. If the identification information is the name of each user, the document generating unit 115 may generate a recorded meeting minutes document by matching each voice recognition text with the corresponding user's name.

At this time, according to an embodiment of the present invention, the document generating unit 115 includes a counting unit 117 , a weight calculating unit 118 , a score calculating unit 119 , a selecting unit 120 , and a meeting minutes generating unit 121 . may include

When the plurality of speech recognition texts are generated by the text generator 114 , the counting unit 117 counts the number of characters of each of the plurality of speech recognition texts.

The weight calculation unit 118 counts the number of speech recognition texts corresponding to each of the plurality of users from the plurality of speech recognition texts, and then, from the total number of the plurality of speech recognition texts, each of the plurality of users A ratio of the number of speech recognition texts corresponding to ' is calculated as a weight for each of the plurality of users.

When the weight for each of the plurality of users is calculated by the weight calculator 118, the score calculator 119 determines the number of characters for each of the plurality of speech recognition texts for the user corresponding to each speech recognition text. By multiplying the weight, an importance score for each of the plurality of speech recognition texts is calculated.

The selection unit 120 checks the importance score calculated for each of the plurality of speech recognition texts, and selects as many speech recognition texts as the preset reference number in the order of the highest importance score among the plurality of speech recognition texts. Select as important text.

When the selection of the important text is completed, the meeting minutes generating unit 121 transmits the plurality of speech recognition texts to the user corresponding to each speech recognition text according to the order in which voice data corresponding to each of the plurality of users is identified. The meeting minutes documents are sequentially listed together with the identification information for the records, and the font format of the speech recognition texts selected as the important texts in the meeting minutes document is applied as a preset emphasis format.

Hereinafter, operations of the weight calculating unit 118 , the score calculating unit 119 , the selecting unit 120 , and the meeting minutes generating unit 121 will be described in detail by way of example.

First, as in the above-described example, 'speech recognition text 1, speech recognition text 2, speech recognition text 3, speech recognition text 4, speech recognition text 5, speech recognition text 6, and speech recognition text are generated by the text generator 114 . 7' is generated, and each of 'Voice Recognized Text 1, Speech Recognized Text 2, Speech Recognized Text 3, Speech Recognized Text 4, Speech Recognized Text 5, Speech Recognized Text 6 and Speech Recognized Text 7' is generated by the count unit 117. Assume that the number of characters in is counted as '15, 30, 25, 15, 25, 10, 20'.

In this case, the voice recognition text corresponding to 'user 1' is 'voice recognition text 1, voice recognition text 2, voice recognition text 5, and voice recognition text 6', and the voice recognition text corresponding to 'user 2' is 'voice recognition' Text 3 and voice recognition text 7', and the voice recognition text corresponding to 'user 3' is 'voice recognition text 4', so the weight calculation unit 118 calculates the weights of the plurality of users 'User 1, User 2, and User 3'. ' The number of speech recognition texts corresponding to each may be counted as '4, 2, 1'.

Then, the weight calculation unit 118 calculates a ratio of the number of speech recognition texts corresponding to each of the plurality of users to the total number of the plurality of speech recognition texts as a weight for each of the plurality of users. can

In relation to this, since the total number of the plurality of speech recognition texts is '7' and the number of speech recognition texts corresponding to 'User 1' is '4', the weight calculator 118 is The weight for the voice recognition text may be calculated as '0.57', which is a ratio of '4', which is the number of voice recognition texts corresponding to 'user 1', from '7', which is the total number of the plurality of speech recognition texts. In this way, the weight calculator 118 may calculate the weights for each of 'User 1, User 2, and User 3' as '0.57, 0.29, and 0.14'.

In this way, when the weights for each of 'User 1, User 2, and User 3' are calculated as '0.57, 0.29, 0.14' by the weight calculation unit 118, the score calculation unit 119 controls the plurality of speech recognition texts. By multiplying the number of characters in each of the speech recognition texts by a weight for a user corresponding to each speech recognition text, an importance score for each of the plurality of speech recognition texts may be calculated.

In relation to 'Voice Recognized Text 1', the user corresponding to 'Voice Recognized Text 1' is 'User 1', and the number of characters of 'Speech Recognized Text 1' is set to '15' by the counting unit 117 . was counted, and the weight for 'user 1' was calculated as '0.57' by the weight calculator 118, so the score calculator 119 calculates the number of characters '15' and 'user 1' of the 'voice recognition text 1'. By multiplying by '0.57', which is a weight for , the importance score for 'speech recognition text 1' can be calculated as '8.55'. In this way, the score estimator 119 calculates 'speech recognition text 1, speech recognition text 2, speech recognition text 3, speech recognition text 4, speech recognition text 5, speech recognition text 6, and speech recognition text 7' for each The importance score can be calculated as '8.55, 17.10, 7.25, 2.10, 14.25, 5.70, 5.80'.

In this way, the importance score for each of 'Speech Recognized Text 1, Speech Recognized Text 2, Speech Recognized Text 3, Speech Recognized Text 4, Speech Recognized Text 5, Speech Recognized Text 6, and Speech Recognized Text 7' was '8.55, 17.10, 7.25. , 2.10, 14.25, 5.70, 5.80', the selector 120 selects 'Voice Recognition Text 1, Speech Recognized Text 2, Speech Recognized Text 3, Speech Recognized Text 4, Speech Recognized Text 5, Speech Recognized Text 6' , from among the speech recognition texts 7', the speech recognition texts corresponding to the preset reference number in the order of the highest importance score may be selected as important texts.

In this regard, when the reference number is '3', the importance score of each voice recognition text is 'Voice recognition text 2, voice recognition text 5, voice recognition text 1, voice recognition text 3, voice recognition text 7, Since the voice recognition text 6 and the voice recognition text 4 were calculated to be high in the order, the selector 120 selects the '3' voice recognition texts 'speech recognition text 2, voice recognition text 5, Speech recognition text 1' may be selected as the important text.

In this way, when 'Voice Recognized Text 2, Speech Recognized Text 5, and Speech Recognized Text 1' are selected as the important text by the selection unit 120, the meeting minutes generating unit 121 is configured as shown in FIG. 'Speech recognition text 1, speech recognition text 2, speech recognition text 3, speech recognition text 4, speech recognition text 5, speech recognition text 6, speech recognition text 7' according to the identification order of each speech recognition text, each speech recognition Generate the above meeting minutes document recorded sequentially along with identification information for the user corresponding to the text, but apply the font format of 'Speech Recognized Text 2, Speech Recognized Text 5, Speech Recognized Text 1' as a preset highlighting format. can

At this time, when the preset emphasis form is 'underline', the meeting minutes generating unit 121 uses the font of 'Voice Recognized Text 2, Speech Recognized Text 5, and Speech Recognized Text 1' as shown in the figure 210. The format can be applied as 'underline', which is the above-mentioned highlighting format.

In this way, when the meeting minutes document is generated by the document generating unit 115 , the file transmitting unit 116 transmits a file for the meeting minutes document to the terminals 141 , 142 , and 143 of the plurality of users.

At this time, according to an embodiment of the present invention, the file transmission unit 116 includes an encryption key storage unit 122 , a query message transmission unit 123 , a password generation unit 124 , an operation value calculation unit 125 , and encryption. It may include a key extraction unit 126 , an encryption unit 127 , and a transmission unit 128 .

First, n (n is a natural number greater than or equal to 2) preset encryption keys are stored in the encryption key storage unit 122 . Here, different integer values of 0 or more and n-1 or less are assigned to each of the n encryption keys.

For example, when n is '10', ten encryption keys as shown in Table 2 below may be stored in the encryption key storage unit 122 .

10 encryption keys integer value encryption key 1 0 encryption key 2 One encryption key 3 2 encryption key 4 3 encryption key 5 4 encryption key 6 5 encryption key 7 6 encryption key 8 7 encryption key 9 8 encryption key 10 9

When the meeting minutes document is generated through the document generating unit 115 , the inquiry message transmitting unit 123 inquires whether to perform security setting for the meeting minutes document to the terminals 141 , 142 , 143 of a plurality of users. send a query message.

When the password generation unit 124 receives a security setting command instructing to perform security setting for the meeting minutes document in response to the inquiry message from the terminal of the second user, which is one of the plurality of users, k (k is a natural number greater than or equal to 2) Randomly generates a password composed of integers of digits.

When the first password is generated with the k-digit password, the operation value calculation unit 125 performs a modulo operation in which the first password is a dividend and n is a divisor to obtain the first operation value. Calculate.

Here, the modulo operation refers to an operation of dividing a dividend by a divisor to calculate a remainder thereof.

When the first operation value is calculated, the encryption key extraction unit 126 extracts a first encryption key to which the first operation value is assigned as an integer value among the n encryption keys from the encryption key storage unit 122 . .

When the first encryption key is extracted, the encryption unit 127 encrypts the file for the meeting minutes document with the first encryption key.

When the file for the meeting minutes document is encrypted, the transmitter 128 transmits the encrypted file for the meeting minutes document and the first password to the terminals 141 , 142 , 143 of a plurality of users.

At this time, each of the terminals 141, 142, and 143 of the plurality of users receives the first password and the encrypted file for the meeting minutes document from the video conferencing system server 110, and during the preset password display time, the At the same time as displaying the first password on the screen, a guide message guiding that the first password is a password for decrypting the meeting minutes document may be displayed.

Hereinafter, the query message transmission unit 123, the password generation unit 124, the calculation value calculation unit 125, the encryption key extraction unit 126, the encryption unit 127, the transmission unit 128, and a plurality of users Operations of the terminals 141, 142, and 143 will be described in detail with an example.

First, as in the above example, when it is said that the meeting minutes document is generated through the document generating unit 115, the message transmitting unit 123 transmits the terminal ( 141, 142, and 143), a query message for inquiring whether to perform security setting for the meeting minutes document may be transmitted.

In this case, the terminals 141 , 142 , and 143 of 'User 1, User 2, and User 3' may display the inquiry message on the screen when the inquiry message is received from the video conferencing system server 110 .

In this way, after the inquiry message is displayed on the screen of the terminals 141, 142, and 143 of 'User 1, User 2, and User 3', from 'User 2' to the terminal of 'User 2' in response to the inquiry message. When the security setting request for the meeting minutes document is approved at 142, the terminal 142 of 'User 2' sends a security setting command instructing to perform security setting for the meeting minutes document video conferencing system server 110 can be sent to

In this way, when the security setting command is received from the terminal 142 of 'User 2' to the video conferencing system server 110, the password generator 124 may randomly generate a password of k-digits.

At this time, it is said that k is '4', and '1230' is generated as a password of '4' digits by the password generating unit 124. The calculator 125 may calculate a first calculated value of '0' by performing a modulo operation using '1230', which is the '4' digit password, as a dividend, and '10' as a divisor.

Then, the encryption key extraction unit 126 may extract the first encryption key to which the first operation value is assigned as an integer value among the ten encryption keys from the encryption key storage unit 122 . In relation to this, in the encryption key storage unit 122 in which the ten encryption keys are stored as shown in Table 2, the first encryption key to which '0', which is the first operation value, is assigned as an integer value is 'encryption key 1' Since it is stored as , the encryption key extraction unit 126 may extract 'encryption key 1', which is the first encryption key, from the encryption key storage unit 122 .

In this way, when 'encryption key 1' is extracted as the first encryption key, the encryption unit 127 may encrypt the file for the meeting minutes document with 'encryption key 1'.

Then, the transmitter 128 may transmit the encrypted file for the meeting minutes document and the first password '1230' to the terminals 141, 142, and 143 of 'User 1, User 2, and User 3'.

At this time, each of the terminals 141, 142, and 143 of 'User 1, User 2, and User 3' receives the encrypted file for the meeting minutes document from the video conferencing system server 110 and the first password '1230'. , while displaying the first password '1230' on the screen for a preset password display time, a guide message guiding that '1230' is a password for decrypting the meeting minutes document may be displayed. In this regard, when the preset password display time is '1 minute', each of the terminals 141, 142, and 143 of 'User 1, User 2, and User 3' is the first password for '1 minute'. At the same time as displaying '1230' on the screen, a guide message guiding that '1230' is a password for decrypting the meeting minutes document may be displayed.

Through this, 'User 1, User 2, and User 3' understands '1230' as a password for decrypting the meeting minutes document, so that they can be utilized when they want to decrypt the encrypted file for the meeting minutes document later.

At this time, according to an embodiment of the present invention, the video conferencing system server 110 further includes a transmission request unit 129 , a decryption calculation unit 130 , a decryption extraction unit 131 , and an encryption key transmission unit 132 . can do.

After the encrypted file for the meeting minutes document is transmitted to the terminals 141, 142, and 143 of the plurality of users, the transmission request unit 129 is configured to receive the third As an execution command instructing to execute the encrypted file for the meeting minutes document is applied from the user's terminal, when a decryption request command for the meeting minutes document is received from the third user's terminal, the third user's terminal Request to transmit a password for decrypting the meeting minutes document.

When the first password is received from the terminal of the third user as the first password is input by the third user to the terminal of the third user by the third user, the decryption calculation unit 130 may withdraw the first password , and by performing a modulo operation in which n is a divisor, the first operation value is calculated.

When the first operation value is calculated, the decryption extraction unit 131 extracts the first encryption key to which the first operation value is assigned as an integer value among the n encryption keys from the encryption key storage unit 122 . .

When the first encryption key is extracted, the encryption key transmission unit 132 transmits the first encryption key to the third user's terminal, and tells the first encryption key to decrypt the encrypted file for the meeting minutes document. Sends a control command to indicate.

At this time, when the third user's terminal receives the first encryption key and the control command from the video conferencing system server 110 , the encrypted meeting minutes document is encrypted based on the first encryption key according to the control command. By decrypting the file, the original file for the meeting minutes document is restored, and then the original file for the meeting minutes document is executed to display the meeting minutes document on the screen.

Hereinafter, the operations of the transmission request unit 129, the decryption calculation unit 130, the decryption extraction unit 131, the encryption key transmission unit 132, and the third user's terminal will be described in detail with an example. .

First, as in the above example, after the encrypted file for the meeting minutes document and the first password '1230' are transmitted to the terminals 141, 142, and 143 of 'User 1, User 2, and User 3', When an execution command instructing to execute the encrypted file for the meeting minutes document is approved by 'User 3' in the terminal 143 of 'User 3', the terminal 143 of 'User 3' is a video conferencing system A decryption request command for the meeting minutes document may be transmitted to the server 110 .

In this way, when a decryption request command for the meeting minutes document is received from the terminal 143 of 'User 3' to the video conferencing system server 110, the transmission request unit 129 sends the request to the terminal 143 of 'User 3'. You may request to transmit a password for decrypting the meeting minutes document.

At this time, when a password transmission request is received from the video conferencing system server 110, the terminal 143 of 'User 3' may display a message requesting input of a password for decrypting the meeting minutes document on the screen. .

In this way, after a message requesting input of a password is displayed on the screen of the terminal 143 of 'User 3', in response to the message, the terminal 143 of 'User 3' by 'User 3' is displayed. When the first password '1230' is input, the terminal 143 of 'User 3' may transmit the first password '1230' to the video conferencing system server 110 .

At this time, when '1230', which is the first password, is received from the terminal 143 of 'User 3', the decryption calculator 130 performs a modulo operation in which '1230' is a dividend and n is a divisor, A first calculated value may be calculated. In this case, when n is '10' as in the above-described example, the decoding calculator 130 may calculate '0' as the first operation value.

In this way, when '0' is calculated as the first operation value, the decryption extraction unit 131 determines that the first operation value '0' is allocated as an integer value from the encryption key storage unit 122 as shown in Table 2 above. 'Encryption key 1' may be extracted with the first encryption key.

Then, the encryption key transmission unit 132 transmits 'encryption key 1' to the terminal 143 of 'user 3', and controls to decrypt the encrypted file for the meeting minutes document with 'encryption key 1'. command can be sent.

At this time, when the 'encryption key 1' and the control command are received from the video conferencing system server 110, the terminal 143 of 'user 3' writes to the meeting minutes document based on the 'encryption key 1' according to the control command. After the original file for the meeting minutes document is restored by decrypting the encrypted file for the meeting minutes, the original file for the meeting minutes document is executed to display the meeting minutes document on the screen.

Here, the encrypted file for the meeting minutes document is the first extracted based on the first password '1230', which is randomly generated according to the security setting command received from the terminal 142 of 'User 2'. Since it is a file encrypted with 'encryption key 1', which is an encryption key, if the encrypted file for the meeting minutes document is decrypted on the basis of 'encryption key 1' in the terminal 143 of 'user 3', the The original file can be restored normally.

As a result, the video conferencing system server 110 according to the present invention identifies voice data corresponding to each of the users from among the voice signals transmitted from the terminals of the users participating in the video conference, and based on the voice recognition technology, the voice data Conversion to voice recognition text to generate a meeting minutes document in which the voice recognition text is recorded, and then transmitting the file for the created meeting minutes document to the terminals of the users, it is possible to increase the convenience of users using the video conferencing service. .

3 is a flowchart illustrating an operation method of a video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention.

In step S310, sound data for a signal section in which a signal having a volume greater than or equal to a preset reference volume among sound signals transmitted from each terminal of a plurality of users participating in the video conference is maintained is provided to each of the plurality of users. Identified by voice data.

In step S320, whenever voice data corresponding to each of the plurality of users is identified, voice data corresponding to each of the plurality of users is provided, identification information for a user corresponding to each voice data, and each voice data is matched with information on the identified sequence and stored in the voice data storage unit.

In step S330, when a termination request for terminating the video conference is received from the terminal of the first user, which is one of the plurality of users, the video conference is terminated and minutes are prepared for the video conference. Creates an event to create meeting minutes for

In step S340, when the event of creating the meeting minutes occurs, after extracting voice data corresponding to each of the plurality of users from the voice data storage unit, for the voice data corresponding to each of the plurality of users, voice data A plurality of voice recognition texts are generated by performing voice recognition based on a preset voice recognition model for converting .

In step S350, when the plurality of speech recognition texts are generated, the plurality of speech recognition texts are provided for the user corresponding to each speech recognition text according to the order in which voice data corresponding to each of the plurality of users are identified. Create a document of recorded meeting minutes by listing them sequentially with identification information.

In step S360, when the meeting minutes document is generated, a file for the meeting minutes document is transmitted to the terminals of the plurality of users.

At this time, according to an embodiment of the present invention, in step S310, sound data for a signal section in which a signal having a volume equal to or greater than the reference volume among the sound signals is maintained for a time period equal to or greater than a preset reference time is transmitted to the plurality of users. It can be identified by voice data corresponding to each.

In addition, according to an embodiment of the present invention, when the plurality of speech recognition texts are generated in step S350, counting the number of characters of each of the plurality of speech recognition texts, from the plurality of speech recognition texts After counting the number of speech recognition texts corresponding to each of the plurality of users, the ratio of the number of speech recognition texts corresponding to each of the plurality of users to the total number of the plurality of speech recognition texts calculating a weight for each of the users; when the weight for each of the plurality of users is calculated, multiplying the number of letters in each of the plurality of speech recognition texts by a weight for the user corresponding to each speech recognition text , calculating an importance score for each of the plurality of speech recognition texts, checking the importance score calculated for each of the plurality of speech recognition texts, and the importance score of the plurality of speech recognition texts is high Selecting speech recognition texts as many as a preset reference number as important texts in order, and when selection of the important texts is completed, the plurality of speech recognition texts are identified in the order in which voice data corresponding to each of the plurality of users are identified Accordingly, the meeting minutes documents are sequentially listed and recorded together with the identification information for the user corresponding to each voice recognition text, and the font format of the voice recognition texts selected as the important text in the meeting minutes document is set in a preset emphasis format. may include the step of applying

In addition, according to an embodiment of the present invention, in step S360, preset n (n is a natural number greater than or equal to 2) encryption keys (each of the n encryption keys has different integer values of 0 or more and n-1 or less) When the meeting minutes document is generated through the steps of maintaining the encryption key storage unit in which the stored encryption key is stored (S350), the terminal of the plurality of users is inquired of whether to perform security settings for the meeting minutes document. When a security setting command instructing to perform security setting for the meeting minutes document is received in response to the inquiry message from a terminal of a second user, which is one of the plurality of users, A module for randomly generating a password composed of an integer of k (k is a natural number of 2 or more) digits, and when a first password is generated with the k-digit password, the first password is a dividend, and n is a divisor calculating a first calculated value by performing an operation with extracting an encryption key; when the first encryption key is extracted, encrypting a file for the meeting minutes document with the first encryption key; and when the file for the meeting minutes document is encrypted, to the terminals of the plurality of users It may include transmitting an encrypted file for the meeting minutes document and the first password.

At this time, when each of the terminals of the plurality of users receives the encrypted file for the meeting minutes document and the first password from the video conferencing system server, displaying the first password on the screen for a preset password display time; At the same time, a guide message guiding that the first password is a password for decrypting the meeting minutes document may be displayed.

At this time, according to an embodiment of the present invention, in the method of operating the video conferencing system server, after the encrypted file for the meeting minutes document is transmitted to the terminals of the plurality of users, the first 3 When an execution command for instructing to execute the encrypted file for the meeting minutes document is applied by the user in the terminal of the third user, and a decryption request command for the meeting minutes document is received from the terminal of the third user, requesting to transmit a password for decrypting the meeting minutes document to the terminal of the third user, as the first password is inputted to the terminal of the third user by the third user When the first password is received from extracting the first encryption key to which the first operation value is assigned as an integer value from among the n encryption keys from an encryption key storage unit; 3 The method may further include transmitting a control command instructing to decrypt the encrypted file for the meeting minutes document with the first encryption key while transmitting to the user's terminal.

In this case, when the third user's terminal receives the first encryption key and the control command from the video conferencing system server, the encrypted file for the meeting minutes document is encrypted based on the first encryption key according to the control command. By decrypting, after restoring the original file for the meeting minutes document, the original file for the meeting minutes document is executed to display the meeting minutes document on the screen.

The operation method of the video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention has been described above with reference to FIG. 3 . Here, the operating method of the video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention may correspond to the configuration of the operation of the video conferencing system server 110 capable of generating meeting minutes described with reference to FIG. 1 , A more detailed description thereof will be omitted.

The method of operating a video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention may be implemented as a computer program stored in a storage medium for execution through combination with a computer.

In addition, the method of operating a video conferencing system server capable of generating meeting minutes according to an embodiment of the present invention may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the present invention, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, in the present invention, specific matters such as specific components, etc., and limited embodiments and drawings have been described, but these are only provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , various modifications and variations are possible from these descriptions by those of ordinary skill in the art to which the present invention pertains.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and not only the claims described below, but also all of the claims and all equivalents or equivalent modifications to the claims will be said to belong to the scope of the spirit of the present invention. .

110: video conferencing system server capable of generating meeting minutes
111: data identification unit 112: storage processing unit
113: event generating unit 114: text generating unit
115: document generation unit 116: file transfer unit
117: count unit 118: weight calculation unit
119: score calculation unit 120: selection unit
121: meeting minutes generating unit 122: encryption key storage unit
123: query message transmission unit 124: password generation unit
125: calculation value calculation unit 126: encryption key extraction unit
127: encryption unit 128: transmission unit
129: transmission request unit 130: decryption calculation unit
131: decryption extraction unit 132: encryption key transmission unit
141, 142, 143: terminals of a plurality of users

Claims (12)

In the video conferencing system server capable of generating meeting minutes,
Identifying sound data for a signal section in which a signal having a volume equal to or greater than a preset reference volume among sound signals transmitted from each terminal of a plurality of users participating in the video conference is maintained as voice data corresponding to each of the plurality of users data identification unit;
Whenever voice data corresponding to each of the plurality of users is identified, the voice data corresponding to each of the plurality of users is displayed in the order in which identification information for a user corresponding to each voice data and each voice data are identified. a storage processing unit for matching information with each other and storing the information in the voice data storage unit;
When a termination request for terminating the video conference is received from the terminal of the first user, which is one of the plurality of users, the video conference is terminated, and a meeting minutes event for creating minutes for the video conference is performed. an event generating unit to generate;
When the meeting minutes event occurs, extracting voice data corresponding to each of the plurality of users from the voice data storage unit, and then converting voice data into text for voice data corresponding to each of the plurality of users a text generator for generating a plurality of speech recognition texts by performing speech recognition based on a preset speech recognition model for converting speech data corresponding to each of the plurality of users into text;
When the plurality of speech recognition texts are generated, the plurality of speech recognition texts are sequentially arranged along with identification information about a user corresponding to each of the speech recognition texts according to an order in which voice data corresponding to each of the plurality of users is identified. a document generating unit for generating a document of recorded meeting minutes by listing; and
When the meeting minutes document is generated, a file transmission unit for transmitting a file for the meeting minutes document to the terminals of the plurality of users
including,
The document generator
a count unit for counting the number of characters of each of the plurality of speech recognition texts when the plurality of speech recognition texts are generated;
After counting the number of speech recognition texts corresponding to each of the plurality of users from the plurality of speech recognition texts, the number of speech recognition texts corresponding to each of the plurality of users is obtained from the total number of the plurality of speech recognition texts. a weight calculator for calculating a ratio of the number of users as a weight for each of the plurality of users;
When the weight for each of the plurality of users is calculated, by multiplying the number of characters of each of the plurality of speech recognition texts by the weight for the user corresponding to each speech recognition text, a scoring unit that calculates the importance score;
A line for checking the importance score calculated for each of the plurality of speech recognition texts, and selecting, as important texts, a preset reference number of speech recognition texts in the order of the highest importance score among the plurality of speech recognition texts government; and
When the selection of the important text is completed, the plurality of speech recognition texts are sequentially displayed along with identification information about a user corresponding to each speech recognition text in an order in which voice data corresponding to each of the plurality of users are identified. A meeting minutes generating unit that generates the listed meeting minutes document, but applies the font format of the speech recognition texts selected as the important text in the meeting minutes document as a preset emphasis format
A video conferencing system server capable of generating meeting minutes, including. According to claim 1,
The data identification unit
A video conferencing system capable of generating meeting minutes for identifying sound data for a signal section in which a signal having a volume equal to or greater than the reference volume among the sound signals lasts for a time equal to or greater than a preset reference time as audio data corresponding to each of the plurality of users server. delete According to claim 1,
The file transfer unit
an encryption key storage unit in which preset n (n is a natural number equal to or greater than 2) encryption keys, each of which is assigned a different integer value of 0 or more and n-1 or less;
a query message transmitting unit that, when the meeting minutes document is generated through the document generating unit, transmits a query message inquiring whether to perform security setting for the meeting minutes document to the terminals of the plurality of users;
When a security setting command instructing to perform security setting for the meeting minutes document is received from the terminal of the second user, which is one of the plurality of users, in response to the inquiry message, k (k is a natural number equal to or greater than 2) ) a password generator for randomly generating a password composed of integers of digits;
an operation value calculator for calculating a first operation value by performing a modulo operation with the first password as a dividend and n as a divisor when the first password is generated using the k-digit password;
an encryption key extraction unit for extracting a first encryption key to which the first operation value is assigned among the n encryption keys from the encryption key storage unit when the first operation value is calculated;
an encryption unit for encrypting a file for the meeting minutes document with the first encryption key when the first encryption key is extracted; and
When the file for the meeting minutes document is encrypted, a transmission unit for transmitting the encrypted file for the meeting minutes document and the first password to the terminals of the plurality of users
including,
Each of the terminals of the plurality of users is
When the encrypted file for the meeting minutes document and the first password are received from the video conferencing system server, the first password is displayed on the screen for a preset password display time, and the first password is the meeting minutes document Video conferencing system server capable of generating meeting minutes, characterized in that it displays a guide message guiding that it is a password for decryption. 5. The method of claim 4,
After the encrypted file for the meeting minutes document and the first password are transmitted to the terminals of the plurality of users, by a third user who is any one of the plurality of users, the meeting minutes document in the terminal of the third user As an execution command instructing to execute an encrypted file for a transmission requesting unit requesting to transmit;
When the first password is received from the terminal of the third user as the first password is input to the terminal of the third user by the third user, the first password is the dividend, and n is the divisor a decoding calculator configured to calculate the first calculated value by performing a modulo operation;
a decryption extraction unit for extracting the first encryption key to which the first operation value is assigned as an integer value among the n encryption keys from the encryption key storage unit when the first operation value is calculated; and
When the first encryption key is extracted, while transmitting the first encryption key to the terminal of the third user, an encryption for transmitting a control command instructing to decrypt the encrypted file for the meeting minutes document with the first encryption key key transmitter
include more
The third user's terminal is
When the first encryption key and the control command are received from the video conferencing system server, by decrypting the encrypted file for the meeting minutes document based on the first encryption key according to the control command, the original for the meeting minutes document After restoring the file, the video conference system server capable of generating meeting minutes, characterized in that by executing the original file for the meeting minutes document to display the meeting minutes document on the screen. A method of operating a video conferencing system server capable of generating meeting minutes, the method comprising:
Identifying sound data for a signal section in which a signal having a volume equal to or greater than a preset reference volume among sound signals transmitted from each terminal of a plurality of users participating in the video conference is maintained as voice data corresponding to each of the plurality of users step;
Whenever voice data corresponding to each of the plurality of users is identified, the voice data corresponding to each of the plurality of users is displayed in the order in which identification information for a user corresponding to each voice data and each voice data are identified. storing the information in a voice data storage unit by matching with each other;
When a termination request for terminating the video conference is received from the terminal of the first user, which is one of the plurality of users, the video conference is terminated, and a meeting minutes event for creating minutes for the video conference is performed. generating;
When the meeting minutes event occurs, extracting voice data corresponding to each of the plurality of users from the voice data storage unit, and then converting voice data into text for voice data corresponding to each of the plurality of users generating a plurality of speech recognition texts by performing speech recognition based on a preset speech recognition model for converting speech data corresponding to each of the plurality of users into text;
When the plurality of speech recognition texts are generated, the plurality of speech recognition texts are sequentially arranged along with identification information about a user corresponding to each of the speech recognition texts according to an order in which voice data corresponding to each of the plurality of users is identified. Listing as to generate a recorded meeting minutes document; and
When the meeting minutes document is generated, transmitting a file for the meeting minutes document to the terminals of the plurality of users
including,
The step of generating the meeting minutes document is
counting the number of characters of each of the plurality of speech recognition texts when the plurality of speech recognition texts are generated;
After counting the number of speech recognition texts corresponding to each of the plurality of users from the plurality of speech recognition texts, the number of speech recognition texts corresponding to each of the plurality of users is obtained from the total number of the plurality of speech recognition texts. calculating a ratio occupied by the number as a weight for each of the plurality of users;
When the weight for each of the plurality of users is calculated, by multiplying the number of characters of each of the plurality of speech recognition texts by the weight for the user corresponding to each speech recognition text, the calculating an importance score;
checking the importance score calculated for each of the plurality of speech recognition texts, and selecting, as important texts, a preset reference number of speech recognition texts in the order of the highest importance score among the plurality of speech recognition texts; ; and
When the selection of the important text is completed, the plurality of speech recognition texts are sequentially displayed along with identification information for a user corresponding to each speech recognition text in an order in which voice data corresponding to each of the plurality of users are identified. generating the meeting minutes document listed and recorded, and applying the font format of the speech recognition texts selected as the important text in the meeting minutes document as a preset emphasis format
Method of operation of a video conferencing system server capable of generating meeting minutes comprising a. 7. The method of claim 6,
The step of identifying
A video conferencing system capable of generating meeting minutes for identifying sound data for a signal section in which a signal having a volume equal to or greater than the reference volume among the sound signals lasts for a time equal to or greater than a preset reference time as audio data corresponding to each of the plurality of users How the server works. delete 7. The method of claim 6,
The sending step is
maintaining an encryption key storage unit in which preset n (n is a natural number equal to or greater than 2) encryption keys, each of which is assigned a different integer value of 0 or more and n-1 or less;
transmitting a query message for inquiring whether to perform security setting for the meeting minutes document to the terminals of the plurality of users when the meeting minutes document is generated through the step of generating the meeting minutes document;
When a security setting command instructing to perform security setting for the meeting minutes document is received from the terminal of the second user, which is one of the plurality of users, in response to the inquiry message, k (k is a natural number equal to or greater than 2) ) randomly generating a password consisting of an integer of digits;
calculating a first calculated value by performing a modulo operation using the first password as a dividend and n as a divisor when a first password is generated using the k-digit password;
when the first operation value is calculated, extracting a first encryption key to which the first operation value is assigned from among the n encryption keys from the encryption key storage unit;
when the first encryption key is extracted, encrypting the file for the meeting minutes document with the first encryption key; and
When the file for the meeting minutes document is encrypted, transmitting the encrypted file for the meeting minutes document and the first password to the terminals of the plurality of users
including,
Each of the terminals of the plurality of users is
When the encrypted file for the meeting minutes document and the first password are received from the video conferencing system server, the first password is displayed on the screen for a preset password display time, and the first password is the meeting minutes document A method of operating a video conferencing system server capable of generating meeting minutes, characterized in that displaying a guide message guiding that it is a password for the decryption of 10. The method of claim 9,
After the encrypted file for the meeting minutes document and the first password are transmitted to the terminals of the plurality of users, by a third user who is any one of the plurality of users, the meeting minutes document in the terminal of the third user As an execution command instructing to execute an encrypted file for requesting to transmit;
When the first password is received from the terminal of the third user as the first password is input to the terminal of the third user by the third user, the first password is the dividend, and n is the divisor calculating the first calculated value by performing a modulo operation;
extracting the first encryption key to which the first operation value is assigned as an integer value among the n encryption keys from the encryption key storage unit when the first operation value is calculated; and
When the first encryption key is extracted, transmitting a control command instructing to decrypt the encrypted file for the meeting minutes document with the first encryption key while transmitting the first encryption key to the terminal of the third user
include more
The third user's terminal is
When the first encryption key and the control command are received from the video conferencing system server, by decrypting the encrypted file for the meeting minutes document based on the first encryption key according to the control command, the original for the meeting minutes document After restoring the file, the original file for the meeting minutes document is executed, and the meeting minutes document is displayed on a screen. A computer-readable recording medium recording a computer program for executing the method of any one of claims 6, 7, 9, or 10 through combination with a computer. A computer program stored in a storage medium for executing the method of any one of claims 6, 7, 9 or 10 in combination with a computer.

Images