JP2021132317A - Remote conference support device and program - Google Patents

Abstract

To specify a destination person in response to a question inquired from an attendant at a remote conference.SOLUTION: A remote conference support device comprises: a speech production information acquisition part that acquires an attribute of a speaker of each speech production and a word contained in the speech production as an analysis result of sound data of two or more first attendants at a first base and one or two or more second attendants at a second base; a storage part that stores the speaker and the attribute, acquired by the speech production information acquisition part so as to be associated with each speech production; a destination person specification part that specifies a destination person in response to a question inquired from each of two or more first attendants on the basis of a comparison of the attribute of the word contained in the speech production in accordance with the question and the attribute stored in each speech production into the storage part when each second attendant performs the speech production in accordance with the question to the other attendant; and a transmission part that transmits a notification for requesting an answer to the destination person specified by the destination person specification part to a first communication terminal.SELECTED DRAWING: Figure 2

Description

The present invention relates to a teleconferencing support device and a program.

In recent years, with the spread of broadband and cloud environments and the development of communication tools accompanying the development of information and communication technology, video conferencing realized by sharing video and audio between bases remote from each other is spreading.

The following Patent Documents 1 to 3 disclose techniques related to such video conferencing. For example, Patent Document 1 discloses a technique for determining the target of utterance by an event performed together with the utterance of the speaker when a meeting is held between a plurality of bases. Further, Patent Document 2 is a technique for organizing conversations in a video conferencing system, in which the relevance of each utterance is evaluated based on keywords, and utterances containing the same keyword and close in time are candidates for relevance. The technology is disclosed. Further, Patent Document 3 is a dialogue system between a person and a computer, in which a person's name is extracted from a dialogue sentence and stored, and when the person's name reappears, the person's name is referred to by referring to a past dialogue. Techniques for determining a person are disclosed.

Japanese Unexamined Patent Publication No. 2017-17737 Japanese Unexamined Patent Publication No. 2000-78298 Japanese Unexamined Patent Publication No. 2004-334591

In a video conferencing system, an attendee may make an utterance with a question or confirmation to a remote attendee. However, in the utterance, the name of the attendee to whom the question is addressed may not be explicitly indicated. For example, it is difficult for attendees who meet each other for the first time to specify each other's names by utterance. As a result, it can be difficult for each attendee to know who the question is addressed to. The above-mentioned Patent Documents 1 to 3 also do not disclose a technique for identifying the destination of a question.

Therefore, the present invention has been made in view of the above problems, and an object of the present invention is a novel and novel one capable of identifying a destination of a question asked by an attendee at a remote conference. The purpose is to provide improved teleconferencing support devices and programs.

In order to solve the above problems, according to a certain viewpoint of the present invention, the voice data of two or more first attendees attending the remote conference transmitted from the first communication terminal provided at the first base. As a result of analyzing the voice data of one or more second attendees attending the remote conference transmitted from the second communication terminal provided at the second base, the speaker and the utterance of each utterance. An utterance information acquisition unit that acquires the attributes of the words included in the utterance, the speaker acquired by the utterance information acquisition unit, a storage unit that stores the attributes in association with each utterance, and the second attendee. When an utterance accompanied by a question to another attendee is made, the second or higher second or higher is based on a comparison between the attribute of the word included in the utterance accompanied by the question and the attribute memorized for each utterance in the storage unit. A destination identification unit that identifies the destination of the question from one attendee, and a transmission unit that transmits a notification requesting an answer to the destination specified by the destination identification unit to the first communication terminal. And, a remote conference support device is provided.

The destination identification unit compares the attribute of the word included in the utterance accompanied by the question with the attribute stored for each utterance in the storage unit for each utterance in which the attribute is stored in the storage unit. An evaluation value may be calculated based on the evaluation value, and the speaker associated with the utterance having the maximum evaluation value may be specified as the destination.

The evaluation value may be the number of attributes of each utterance stored in the storage unit that match the attributes of the words included in the utterance accompanied by the question.

The destination identification unit may compare two or more utterances satisfying a predetermined condition among the utterances in which the attribute is stored in the storage unit.

The predetermined condition may include that the utterance is within a predetermined number of utterances from the latest utterance, or that the utterance is made within a predetermined time.

The destination identification unit does not have to specify the destination if the evaluation value of any utterance does not exceed a predetermined standard.

The attribute may include the part of speech of the word or the semantic classification of the word.

The remote conference support device further includes a receiving unit that receives the voice data of the two or more first attendees and the voice data of the one or two or more second attendees, and the utterance information acquisition unit , The speaker of each utterance and the attributes of the words included in the utterance may be acquired by analyzing the voice data received by the receiving unit.

The remote conference support device includes an utterance type determination unit that determines whether or not the utterance indicated by the voice data is an utterance accompanied by the question, based on the analysis result of the voice data acquired by the utterance information acquisition unit. Further, the destination identification unit may specify the destination with respect to the utterance determined by the utterance information acquisition unit to be an utterance accompanied by the question.

Further, in order to solve the above problems, according to another viewpoint of the present invention, the computer is used as two or more firsts to attend a remote conference transmitted from the first communication terminal provided at the first base. As a result of analysis of the voice data of the attendees and the voice data of one or more second attendees attending the remote conference transmitted from the second communication terminal provided at the second base, respectively. An utterance information acquisition unit that acquires the attributes of the utterance speaker and words included in the utterance, the speaker acquired by the utterance information acquisition unit, and a storage unit that stores the attributes in association with each utterance, and the above. When the second attendee makes an utterance accompanied by a question to another attendee, the attribute of the word included in the utterance accompanied by the question is compared with the attribute memorized for each utterance in the storage unit. , The first communication of the destination identification unit that identifies the destination of the question from the two or more first attendees and the notification requesting a reply from the destination specified by the destination identification unit. A program is provided to function as a transmitter to transmit to the terminal.

According to the present invention described above, it is possible to identify the recipient of a question asked by a certain attendee in a remote conference.

It is explanatory drawing which shows the structure of the remote conference system by one Embodiment of this invention. It is explanatory drawing which shows the structure of the cloud server 20 by one Embodiment of this invention. It is explanatory drawing which shows the specific example of the utterance made by each attendee. It is explanatory drawing which shows the specific example of the utterance analysis data stored in the storage part 240. It is explanatory drawing which shows the specific 1st specific example of a destination. It is explanatory drawing which shows the specific 2nd specific example of the addressee. It is explanatory drawing which shows the specific 3rd specific example of the addressee. It is explanatory drawing which shows the specific example of the display requesting an answer. It is a flowchart which shows the operation of the cloud server 20 by one Embodiment of this invention. It is a flowchart which shows the detail of the collection and analysis of voice data. It is a block diagram which showed the hardware configuration of the cloud server 20.

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In the present specification and the drawings, components having substantially the same functional configuration are designated by the same reference numerals, so that duplicate description will be omitted.

Further, in the present specification and the drawings, a plurality of components having substantially the same functional configuration may be distinguished by adding different alphabets after the same reference numerals. For example, a plurality of configurations having substantially the same functional configuration or logical significance are distinguished as necessary, such as remote conference terminals 10A and 10B. However, when it is not necessary to particularly distinguish each of the plurality of components having substantially the same functional configuration, only the same reference numerals are given to each of the plurality of components. For example, when it is not necessary to distinguish between the remote conference terminals 10A and 10B, each remote conference terminal is simply referred to as a remote conference terminal 10.

<1. Overview of teleconferencing system>
One embodiment of the present invention relates to a remote conference system that realizes a remote conference between remote bases. Hereinafter, an outline of the remote conference system according to the embodiment of the present invention will be described with reference to FIG.

FIG. 1 is an explanatory diagram showing a configuration of a remote conference system according to an embodiment of the present invention. As shown in FIG. 1, the remote conference system according to the embodiment of the present invention includes a remote conference terminal 10A provided at the base A, a remote conference terminal 10B provided at the base B, and a cloud server 20. The remote conference terminal 10A, the remote conference terminal 10B, and the cloud server 20 are connected by the network 12. The network 12 may include a public line network such as a telephone line network, the Internet, and a satellite communication network, a LAN (Local Area Network), a WAN (Wide Area Network), and the like. Further, the network 12 may include a dedicated line network such as IP-VPN (Internet Protocol-Virtual Private Network).

Base A and Base B are remote from each other. In FIG. 1, attendees A1 and A2 are shown as attendees at the teleconference at the base A, and attendees B1 and B2 are shown as attendees at the teleconferencing at the base B. There is. The meaning of remoteness is not limited to the fact that the base A and the base B are located far apart, the base A and the base B may exist on different floors of the same building, and the base A and the base B may exist. It may exist in a separate room on the same floor.

(Terminal for remote conference)
The remote conference terminal 10 is a communication terminal shared by the attendees of the remote conference at each base. For example, the base A is an example of the first base, and the remote conference terminal 10A shared by the base A is an example of the first communication terminal. Similarly, the base B is an example of a second base, and the remote conference terminal 10B shared by the base B is an example of a second communication terminal.

The remote conference terminal 10 has various functions for realizing a remote conference. For example, the remote conference terminal 10 has an imaging function of capturing an image of a base where the remote conference terminal 10 is located and acquiring video data of the base, and attendees existing at the base where the remote conference terminal 10 is located. Sound collection function that collects the voice of the other base and acquires voice data, a function that communicates video data and voice data with the remote conference terminal 10 of another base, video data received from the remote conference terminal 10 of another base It has a display function for displaying, and a voice output function for outputting voice data received from another base remote conference terminal 10.

Specifically, the remote conference terminal 10A transmits the video data and audio data of the base A to the remote conference terminal 10B, and the remote conference terminal 10B displays the video data and outputs the audio data. Further, the remote conference terminal 10A receives the video data and audio data of the base B from the remote conference terminal 10B, displays the video data, and outputs the audio data. As a result, the attendees A1 and A2 existing at the base A and the attendees B1 and B2 existing at the base B can talk with each other while watching each other's images.

Further, the remote conference terminal 10 according to the embodiment of the present invention transmits the voice data acquired by the sound collecting function to the cloud server 20. Further, when the remote conference terminal 10 receives the reply request notification, which will be described in detail later, from the cloud server 20, the remote conference terminal 10 displays or outputs the reply request notification by voice.

Although the remote conference terminal 10 shows a desktop PC (Personal Computer) in FIG. 1, the remote conference terminal 10 may be used for other information processing such as a notebook PC, a tablet terminal, and a terminal having a large display. It may be a device.

(Cloud server)
The cloud server 20 is an example of a remote conference support device that supports remote conferences. The cloud server 20 receives voice data from the remote conference terminal 10A and the remote conference terminal 10B, and analyzes the voice data. When the voice data is an utterance that involves asking someone, such as a question or confirmation, the cloud server 20 identifies the recipient of the question and sends a response request notification requesting an answer to the recipient to the remote conference terminal 10A. Alternatively, it is transmitted to the remote conference terminal 10B. Hereinafter, the configuration and operation of such a cloud server 20 will be sequentially described in detail.

Although one server is shown as the cloud server 20 in FIG. 2, the functions of the cloud server 20 described below may be distributed and implemented in a server group composed of a plurality of servers.

<2. Cloud server configuration>
FIG. 2 is an explanatory diagram showing a configuration of a cloud server 20 according to an embodiment of the present invention. As shown in FIG. 2, the cloud server 20 according to the embodiment of the present invention includes a communication unit 220, a voice data analysis unit 230, a storage unit 240, an utterance type determination unit 250, and a destination identification unit 260.

(Communication Department)
The communication unit 220 communicates various data with the remote conference terminal 10. For example, the communication unit 220 functions as a receiving unit for receiving voice data from the remote conference terminal 10A and the remote conference terminal 10B, and transmits a response request notification to the remote conference terminal 10A or the remote conference terminal 10B. It has a function as a transmitter.

(Voice data analysis department)
The voice data analysis unit 230 is an example of an utterance information acquisition unit, and as an analysis result of voice data received by the communication unit 220, the speaker of each utterance, the words included in each utterance, the attributes of the words, and the like are used. Acquire utterance analysis data. The voice data analysis unit 230 extracts characteristic words included in each utterance by analyzing the voice data received by the communication unit 220 by natural language processing, and determines the attributes of the words by artificial intelligence. You may. The attributes of a word include the part of speech of the word and the semantic classification, which is a semantic classification of the word. For example, the part of speech of the word "next month" is "general noun" and the semantic classification is "time". The voice data is analyzed by another server, and the r20 may acquire the utterance analysis data as a result of the analysis. In this case, the r20 does not have to have the voice data analysis function.

(Memory)
The storage unit 240 stores various data used for the operation of the cloud server 20. For example, the storage unit 240 may store the names and voice features of each attendee. Further, the storage unit 240 according to the embodiment of the present invention stores the utterance analysis data acquired by the voice data analysis unit 230. Hereinafter, a specific example of the utterance analysis data stored in the storage unit 240 will be described with reference to FIGS. 3 and 4.

FIG. 3 is an explanatory diagram showing a specific example of utterances made by each attendee. In the example shown in Fig. 3, attendee A1 makes an utterance V1 saying "XX will be released next month." Then attendee A2 says "XX will be on the shelves next month only in Kanto." The utterance V2 is made, and then the attendee B1 makes the utterance V3 "When will XX be lined up in stores nationwide?" In this case, for example, the utterance analysis data shown in FIG. 4 is acquired and stored in the storage unit 240.

FIG. 4 is an explanatory diagram showing a specific example of the utterance analysis data stored in the storage unit 240. As shown in FIG. 4, the utterance analysis data is data in which the utterance ID, the speaker, the word, the part of speech, and the semantic classification are associated with each utterance. For example, in the utterance analysis data shown in FIG. 4, the speaker of the utterance V1 is the attendee A1, and the words XX (part of speech: proper nomenclature, meaning classification: article) and release (part of speech: general nomenclature, meaning classification) are released from the utterance V1. : Event) and next month (part of speech: general nomenclature, semantic classification: time) are extracted.

(Utterance type judgment unit)
The utterance type determination unit 250 determines whether or not each utterance is an utterance accompanied by a question, based on the utterance analysis data stored in the storage unit 240. The method for determining whether or not each utterance is an utterance accompanied by a question is not particularly limited. For example, the utterance type determination unit 250 may determine that the utterance is an utterance accompanied by a question when the content of the utterance can be replaced with a sentence of 5W1H. Alternatively, the utterance type determination unit 250 compares the correct answer data, which is an utterance accompanied by a question, with the content of the utterance, and if the correct answer data matches the content of the utterance, or if the correct answer data and the content of the utterance are similar, the relevant case is found. It may be determined that the utterance is an utterance accompanied by a question.

(Destination identification department)
The destination identification unit 260 identifies the destination of the question for the utterance determined by the utterance type determination unit 250 to be an utterance accompanied by a question. For example, the destination identification unit 260 has the meaning classification of the words included in the utterance accompanied by the question for each utterance in which the utterance analysis data is stored in the storage unit 240, and each utterance stored in the storage unit 240. The evaluation value may be calculated based on the comparison with the meaning classification of the word, and the speaker associated with the utterance having the maximum evaluation value may be specified as the destination. Hereinafter, specific specific examples of the recipient will be described with reference to FIGS. 5 to 7.

FIG. 5 is an explanatory diagram showing a specific first specific example of the destination. More specifically, in FIG. 5, it is determined that the utterance V3 by the attendee B1 shown in FIG. 3 is an utterance accompanied by a question, and the utterance analysis data shown in FIG. 4 is acquired for the utterance V3. A specific example of the destination is shown.

In this case, as shown in FIG. 5, in the utterance V1, the meaning classification "article" of the word "XX" matches the meaning classification "article" of the word "XX" included in the utterance V3, and the word "next month". The meaning classification "time" of is consistent with the meaning classification "time" of the word "when" included in the utterance V3. Therefore, the destination identification unit 260 sets "2", which is the number of meaning classifications of the words included in the utterance V1 to match the meaning classifications of the words included in the utterance V3 accompanied by the question, with respect to the utterance V1. Calculated as an evaluation value.

Further, in the utterance V2, the meaning classification "article" of the word "XX" matches the meaning classification "article" of the word "XX" included in the utterance V3, and the meaning classification "time" of the word "next month" is the utterance V3. The meaning classification "time" of the word "when" included in is matched, and the meaning classification "district" of the word "Kanto" is matched with the meaning classification "district" of the word "nationwide" included in the utterance V3. Therefore, the destination identification unit 260 sets "3", which is the number of meaning classifications of the words included in the utterance V2, which matches the meaning classification of the words included in the utterance V3 accompanied by the question, to the utterance V2. Calculated as an evaluation value.

In the example shown in FIG. 5, since the evaluation value “3” of the utterance V2 is the maximum, the destination identification unit 260 identifies the attendee A2 associated with the utterance V2 as the destination.

FIG. 6 is an explanatory diagram showing a specific second specific example of the destination. More specifically, in FIG. 6, it is determined that the utterance V3 by the attendee B1 shown in FIG. 3 is an utterance accompanied by a question, and the utterance analysis data shown in FIG. 4 is acquired for the utterance V3. A specific example of the destination is shown. On the other hand, it is assumed that the utterance analysis data shown in FIG. 6 has been acquired for the utterance V1 and the utterance V2.

In the example shown in FIG. 6, the evaluation value of the utterance V1 and the evaluation value of the utterance V2 are both the maximum "3". When a plurality of utterances have the same maximum evaluation value in this way, the destination identification unit 260 identifies all the attendees associated with the plurality of utterances as the destination or the candidate of the destination. .. Therefore, in the example shown in FIG. 6, both attendee A1 and attendee A2 are identified as recipients.

FIG. 7 is an explanatory diagram showing a specific third specific example of the destination. More specifically, in FIG. 7, it is determined that the utterance V3 by the attendee B1 shown in FIG. 3 is an utterance accompanied by a question, and the utterance analysis data shown in FIG. 4 is acquired for the utterance V3. A specific example of the destination is shown. On the other hand, it is assumed that the utterance analysis data shown in FIG. 7 has been acquired for the utterance V1 and the utterance V2.

In the example shown in FIG. 7, the evaluation value of the utterance V1 and the evaluation value of the utterance V2 are both “0”. The destination identification unit 260 does not specify the destination when the evaluation value of any utterance does not exceed a predetermined standard, for example, when the evaluation value of any utterance does not exceed "1". Therefore, in the example shown in FIG. 7, neither the attendee A1 nor the attendee A2 is specified as the destination.

(Specific example of response request notification)
When the destination is specified by the destination identification unit 260, the communication unit 220 transmits a reply request notification to the destination to the remote conference terminal 10 of the base where the destination exists. The teleconferencing terminal 10 that has received the response request notification requests the recipient to answer the question by displaying or outputting voice. Here, with reference to FIG. 8, an example in which an answer is requested by display will be described.

FIG. 8 is an explanatory diagram showing a specific example of a display requesting an answer. FIG. 8 shows a dialogue screen 40 displayed by the remote conference terminal 10A. The dialogue screen 40 includes images of attendees B1 and B2 existing at the base B. Further, the dialogue screen 40 includes a system message 42 as a display requesting the attendee A1 to answer. The system message is, for example, the message "This is a question to Mr. A1" indicating that the question was asked to attendee A1, and "Mr. A1, please answer." Includes the message. Based on the system message 42, the attendee A1 can grasp that the utterance V3 is a question to himself / herself and can answer the question.

<3. Cloud server operation>
The configuration of the cloud server 20 according to the embodiment of the present invention has been described above. Subsequently, with reference to FIGS. 9 and 10, the operation of the cloud server 20 according to the embodiment of the present invention will be arranged.

FIG. 9 is a flowchart showing the operation of the cloud server 20 according to the embodiment of the present invention. As shown in FIG. 9, first, the cloud server 20 collects and analyzes voice data (S310). Then, when the utterance type determination unit 250 determines the utterance type indicated by the voice data (S320) and the utterance type is not an utterance accompanied by a question (S330 / No), the process from S310 is repeated.

On the other hand, when the type of utterance is an utterance accompanied by a question (S330 / Yes), the process proceeds to S340. That is, the destination identification unit 260 identifies the destination of the question based on the voice analysis data of each utterance stored in the storage unit 240 (S340). Then, when one destination is specified (S350 / person), the communication unit 220 transmits a reply request notification to one destination (S360). When a plurality of recipients are identified (S350 / plurality), the communication unit 220 transmits a response request notification to the plurality of recipients (S370). On the other hand, if the recipient is not specified (S350 / 0 people), the reply request notification is not transmitted. However, since the utterance is an utterance in which a question is being asked to someone, the communication unit 220 may send a notification indicating that the question is being made. After that, the process from S310 is repeated while the function is continued (S380 / Yes).

FIG. 10 is a flowchart showing details of voice data collection and analysis. First, when the communication unit 220 waits for the reception of voice data (S311) and the communication unit 220 receives the voice data (S312 / Yes), the voice data analysis unit 230 analyzes the voice data by, for example, natural language processing (S313). .. Then, the storage unit 240 stores the utterance analysis data including the speaker of each utterance, the word included in each utterance, the attribute of the word, and the like obtained by the analysis (S314). After that, the process from S311 is repeated while the function is continued (S315 / Yes). At the same time, the process from S320 described with reference to FIG. 9 proceeds.

<4. Action effect>
As described above, according to the embodiment of the present invention, when an utterance accompanied by a question is made in a remote conference, the attendees who should answer the question can be easily grasped. For this reason, it is possible to suppress the occurrence of exchanges for confirming the respondents, save the time and effort for the speaker to confirm the name of the recipient in advance, and as a result, the efficiency of the remote conference is realized. ..

Further, in one embodiment of the present invention, the evaluation value is calculated based on the number of matches of the meaning classification of the words included in the utterance, not the number of matches of the words included in the utterance. Therefore, even if the utterance accompanied by the question does not include the same word as the word used in the past utterance, it is possible to appropriately calculate the evaluation value and identify the destination.

<5. Modification example>
The embodiment of the present invention has been described above. Hereinafter, some modifications of the above-described embodiment will be described. In addition, each modification described below may be applied alone to the above-described embodiment, or may be applied in combination to the above-described embodiment. Further, each modification may be applied in place of the configuration described in the above-described embodiment, or may be additionally applied to the configuration described in the above-described embodiment.

(First modification)
In the above, the example in which the destination identification unit 260 calculates the number of matches of the semantic classification as the evaluation value has been described, but the calculation of the evaluation value may be performed by another method. For example, the destination identification unit 260 may weight the matching semantic classifications and calculate the total value of the weights as an evaluation value. In this case, it is expected that a more appropriate evaluation value will be calculated by increasing the weight of the semantic classification of characteristic words.

(Second modification)
Further, in the above, the example in which the destination identification unit 260 calculates the evaluation value of each utterance based on the same standard has been described, but the evaluation value of each utterance may be calculated based on a different standard. For example, considering that an attendee makes an utterance that asks the other attendee in connection with the utterance of another attendee in the past, the utterance that is the source of the question is the utterance that asks the question. There is a high possibility that it is being done nearby in time. Therefore, the destination identification unit 260 may calculate the evaluation value by giving a larger weight to the utterance newer in time. With such a configuration, it is possible to improve the specific accuracy of the destination.

(Third variant)
In relation to the second variant, it is unlikely that the utterance that asks the question and the utterance that is made at a time lag are the source of the question. Therefore, the destination identification unit 260 may use two or more utterances satisfying a predetermined condition as the evaluation value calculation target among the utterances in which the utterance analysis data is stored in the storage unit 240. Predetermined conditions include that the utterance is within a predetermined number of utterances from the latest utterance, or that the utterance is made within a predetermined time. With such a configuration, it is possible to improve the specific accuracy of the destination.

<6. Hardware configuration>
An embodiment and a modification of the present invention have been described above. The information processing such as the analysis of the voice data and the identification of the destination described above is realized by the cooperation between the software and the hardware of the cloud server 20 described below. The hardware configuration described below can also be applied to the remote conference terminal 10.

FIG. 11 is a block diagram showing the hardware configuration of the cloud server 20. The cloud server 20 includes a CPU (Central Processing Unit) 201, a ROM (Read Only Memory) 202, a RAM (Random Access Memory) 203, and a host bus 204. The cloud server 20 includes a bridge 205, an external bus 206, an interface 207, an input device 208, a display device 209, an audio output device 210, a storage device (HDD) 211, a drive 212, and a network interface. It is equipped with 215.

The CPU 201 functions as an arithmetic processing device and a control device, and controls the overall operation in the cloud server 20 according to various programs. Further, the CPU 201 may be a microprocessor. The ROM 202 stores programs, calculation parameters, and the like used by the CPU 201. The RAM 203 temporarily stores a program used in the execution of the CPU 201, parameters that are appropriately changed in the execution, and the like. These are connected to each other by a host bus 204 composed of a CPU bus or the like. By the collaboration between the CPU 201, ROM 202 and RAM 203 and the software, functions such as the voice data analysis unit 230, the utterance type determination unit 250, and the destination identification unit 260 described with reference to FIG. 2 can be realized.

The host bus 204 is connected to an external bus 206 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 205. It is not always necessary to separately configure the host bus 204, the bridge 205, and the external bus 206, and these functions may be implemented in one bus.

The input device 208 includes input means for the user to input information such as a mouse, a keyboard, a touch panel, a button, a microphone, a sensor, a switch, and a lever, and an input that generates an input signal based on the input by the user and outputs the input signal to the CPU 201. It is composed of a control circuit and the like. By operating the input device 208, the user of the cloud server 20 can input various data to the cloud server 20 and instruct the processing operation.

The display device 209 includes, for example, a liquid crystal display (LCD) device, a projector device, an OLED (Organic Light Emitting Diode) device, and a display device such as a lamp. Further, the audio output device 210 includes an audio output device such as a speaker and headphones.

The storage device 211 is a data storage device configured as an example of the storage unit of the cloud server 20 according to the present embodiment. The storage device 211 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deleting device that deletes the data recorded on the storage medium, and the like. The storage device 211 is composed of, for example, an HDD (Hard Disk Drive) or SSD (Solid Stage Drive), or a memory having an equivalent function. The storage device 211 drives the storage and stores programs and various data executed by the CPU 201.

The drive 212 is a reader / writer for a storage medium, and is built in or externally attached to the cloud server 20. The drive 212 reads the information recorded in the removable storage medium 24 such as the mounted magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 203 or the storage device 211. The drive 212 can also write information to the removable storage medium 24.

The network interface 215 is, for example, a communication interface composed of a communication device or the like for connecting to the network 12. Further, the network interface 215 may be a wireless LAN (Local Area Network) compatible communication device or a wire communication device that performs wired communication.

<7. Supplement>
Although the preferred embodiments of the present invention have been described in detail with reference to the accompanying drawings, the present invention is not limited to such examples. It is clear that a person having ordinary knowledge in the field of technology to which the present invention belongs can come up with various modifications or modifications within the scope of the technical ideas described in the claims. , These are also naturally understood to belong to the technical scope of the present invention.

For example, each step in the processing of the cloud server 20 of the present specification does not necessarily have to be processed in chronological order in the order described as a flowchart. For example, each step in the processing of the cloud server 20 may be processed in an order different from the order described in the flowchart, or may be processed in parallel.

Further, a computer for causing the hardware such as the CPU, ROM, and RAM built in the remote conference terminal 10 and the cloud server 20 to exhibit the same functions as the configurations of the remote conference terminal 10 and the cloud server 20 described above. Programs can also be created. A storage medium for storing the computer program is also provided.

10 Remote conference terminal 20 Cloud server 220 Communication unit 230 Voice data analysis unit 240 Storage unit 250 Speech type determination unit 260 Destination identification unit

Claims (10)

Voice data of two or more first attendees attending the remote conference transmitted from the first communication terminal provided at the first base, and transmitted from the second communication terminal provided at the second base. As a result of analyzing the voice data of one or more second attendees attending the remote conference, the utterance information acquisition unit for acquiring the speaker of each utterance and the attributes of the words included in the utterance, and the utterance information acquisition unit.
The speaker acquired by the utterance information acquisition unit, a storage unit that stores the attributes in association with each utterance, and a storage unit.
When the second attendee makes an utterance accompanied by a question to another attendee, the attribute of the word included in the utterance accompanied by the question is compared with the attribute memorized for each utterance in the storage unit. Based on the addressee identification unit that identifies the addressee of the question from the two or more first attendees,
A transmission unit that transmits a notification requesting a reply to the destination person specified by the destination person identification unit to the first communication terminal, and a transmission unit.
A remote conference support device equipped with. The destination identification unit compares the attribute of the word included in the utterance accompanied by the question with the attribute stored for each utterance in the storage unit for each utterance in which the attribute is stored in the storage unit. The remote conference support device according to claim 1, wherein an evaluation value is calculated based on the evaluation value, and the speaker associated with the utterance having the maximum evaluation value is specified as the destination. The remote conference support device according to claim 2, wherein the evaluation value is the number of attributes of each utterance stored in the storage unit that match the attributes of the words included in the utterance accompanied by the question. .. The remote according to claim 2 or 3, wherein the destination identification unit targets two or more utterances satisfying a predetermined condition among the utterances whose attributes are stored in the storage unit as the comparison target of the attributes. Conference support device. The remote conference support device according to claim 4, wherein the predetermined condition includes an utterance within a predetermined number of utterances from the latest utterance or an utterance made within a predetermined time. The remote conference support device according to any one of claims 2 to 5, wherein the destination identification unit does not specify the destination when the evaluation value of any utterance does not exceed a predetermined standard. The teleconferencing support device according to any one of claims 1 to 5, wherein the attribute includes a part of speech of a word or a semantic classification of a word. The teleconferencing support device further includes a receiving unit that receives the voice data of the two or more first attendees and the voice data of the one or more second attendees.
The utterance information acquisition unit acquires the attributes of the speaker of each utterance and the words included in the utterance by analyzing the voice data received by the utterance unit, according to any one of claims 1 to 7. The teleconference support device described. The remote conference support device has an utterance type determination unit that determines whether or not the utterance indicated by the voice data is an utterance accompanied by the question, based on the analysis result of the voice data acquired by the utterance information acquisition unit. Further prepare
The remote conference support device according to claim 8, wherein the destination identification unit identifies the destination with respect to an utterance determined by the utterance information acquisition unit to be an utterance accompanied by the question. Computer,
Voice data of two or more first attendees attending the remote conference transmitted from the first communication terminal provided at the first base, and transmitted from the second communication terminal provided at the second base. As a result of analyzing the voice data of one or more second attendees attending the remote conference, the utterance information acquisition unit for acquiring the speaker of each utterance and the attributes of the words included in the utterance, and the utterance information acquisition unit.
The speaker acquired by the utterance information acquisition unit, a storage unit that stores the attributes in association with each utterance, and a storage unit.
When the second attendee makes an utterance accompanied by a question to another attendee, the attribute of the word included in the utterance accompanied by the question is compared with the attribute memorized for each utterance in the storage unit. Based on the addressee identification unit that identifies the addressee of the question from the two or more first attendees,
A transmission unit that transmits a notification requesting a reply to the destination person specified by the destination person identification unit to the first communication terminal, and a transmission unit.
A program to function as.

Images