Information processing device and information processing program

Abstract

To provide an information processing device further improving convenience when voice is converted into a text.SOLUTION: An information processing device 1 includes an audio data acquisition part 10 for acquiring audio data of voice uttered by a user, a text data generation part 11 for generating text data obtained by converting the voice relating to the audio data into a text, based on the voice data acquired by the voice data acquisition part 10, an additional information generation part 12 for generating additional information, the information relating to at least one of the voice data and the text data, and an information transmission part 13 for transmitting the text data and the additional information to a user terminal 3.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an information processing device and an information processing program. [Background technology]

[0002] There are known devices that acquire voice data of speech uttered by a user and analyze the acquired voice data. For example, Patent Document 1 discloses a voice recording device that divides sections based on breaks in speech and makes it easy to search for a desired speech. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2007-329794 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, simply recording the audio requires listening to the audio again to confirm the content of the audio, which is cumbersome. On the other hand, it is also possible to convert the audio into text (i.e., transcribe it), but even in that case, there are cases where simply converting the audio into text as it is does not provide sufficient convenience.

[0005] Therefore, an information processing device and an information processing program according to the present disclosure aim to further improve convenience when converting speech into text. [Means for solving the problem]

[0006] An information processing device (1) according to one embodiment of the present disclosure includes a voice data acquisition unit (10) that acquires voice data of a voice uttered by a user, a text data generation unit (11) that generates text data by converting the voice related to the voice data acquired by the voice data acquisition unit (10) into text, an additional information generation unit (12) that generates additional information related to at least one of the voice data and the text data, and an information transmission unit (13) that transmits the text data and the additional information to a user terminal (3).

[0007] An information processing program (P) according to one embodiment of the present disclosure causes a computer (C) to function as an audio data acquisition unit (10) that acquires audio data of a voice uttered by a user, a text data generation unit (11) that generates text data by converting the audio related to the audio data acquired by the audio data acquisition unit (10) into text, an additional information generation unit (12) that generates additional information related to at least one of the audio data and the text data, and an information transmission unit (13) that transmits the text data and the additional information to a user terminal (3).

[0008] At least one of these information processing device (1) and information processing program (P) makes it possible to effectively utilize the voice data of the voice uttered by the user, and to obtain added value that cannot be obtained by simply converting the voice into text as it is. Therefore, it is possible to further improve the convenience of converting voice into text.

[0009] The information processing device (1) according to one aspect of the present disclosure includes a task recognition unit (14) that recognizes a task that a user has based on at least one of voice data and text data, and the additional information generation unit (12) may generate additional information including answer information that is information related to an answer to the task recognized by the task recognition unit (14). This allows the user to obtain an answer to the task that the user has, thereby further improving convenience.

[0010] In the information processing device (1) according to an embodiment of the present disclosure, the additional information generating unit (12) may generate additional information including highlighting information for highlighting a portion of the text related to the text data in which a problem is described. This allows the user to easily visually recognize the problem.

[0011] In the information processing device (1) according to one aspect of the present disclosure, the information transmission unit (13) may transmit answer information regarding an answer to the assignment to the user terminal (3) when a predetermined operation is performed on a portion of the text that is highlighted by the highlighting information. This allows the answer to the assignment to be obtained by a simple operation.

[0012] An information processing device (1) according to an embodiment of the present disclosure includes a comment addition information receiving unit (15) that receives comment addition information, which is information related to adding a comment to an answer, and the additional information generating unit (12) may generate additional information including comment display information, which is information for displaying a comment related to the comment addition information on a user terminal (3) when the comment addition information is received by the comment addition information receiving unit (15). This allows the comment to be displayed on the answer, further improving convenience.

[0013] In the information processing device (1) according to one aspect of the present disclosure, when the comment addition information receiving unit (15) receives comment addition information, the additional information generating unit (12) may generate additional information including automatic response information that is information regarding an automatic response to a comment related to the comment addition information. This makes it possible to further obtain various information regarding the comment, thereby further improving convenience.

[0014] In the information processing device (1) according to one aspect of the present disclosure, the additional information generating unit (12) may generate additional information including vendor information, which is information about a vendor that can solve the problem recognized by the problem recognizing unit (14). This makes it possible to obtain not only an answer to the problem but also information about a vendor that can solve the problem.

[0015] In the information processing device (1) according to one aspect of the present disclosure, the voice data acquisition unit (10) may acquire voice data from a plurality of conferences, and the text data generation unit (11) may generate text data from the plurality of conferences based on the voice data from the plurality of conferences. This allows the voices from the plurality of conferences to be converted into text, further improving convenience.

[0016] The information processing device (1) according to one aspect of the present disclosure includes a feature extraction unit (17) that extracts features of voice data from a plurality of conferences or text data from a plurality of conferences, and the additional information generation unit (12) may generate additional information including feature information that is information related to the features extracted by the feature extraction unit (17). This makes it possible to easily analyze the features of each of the plurality of conferences.

[0017] In an information processing device (1) according to one aspect of the present disclosure, a feature extraction unit (17) further extracts superior features, which are excellent features, or inferior features, which are inferior features, from the extracted features, an additional information generation unit (12) generates additional information including superior feature information, which is information about superior features related to the first conference, which is a first conference, or inferior feature information, which is information about inferior features related to the first conference, and an information transmission unit (13) may transmit the additional information including the superior feature information or inferior feature information to a user terminal (3) of a user who holds a second conference, which is a second conference different from the first conference. This makes it possible to share particularly useful information such as superior feature information or inferior feature information with others.

[0018] In the information processing device (1) according to one aspect of the present disclosure, the additional information generating unit (12) generates additional information corresponding to each of the multiple conferences and generates comparison information that is information on a comparison result obtained by comparing the additional information corresponding to each of the multiple conferences, and the information transmitting unit (13) may transmit the comparison information to the user terminal (3). This makes it possible to share with others the information on the comparison result obtained by relatively comparing the multiple conferences, thereby further improving convenience.

[0019] In the information processing device (1) according to an embodiment of the present disclosure, the comparison information may include commonalities information, which is information on commonalities of the additional information corresponding to each of the multiple conferences. This allows the information on the comparison result focusing on the commonalities of the multiple conferences to be shared with others, thereby further improving convenience.

[0020] In the information processing device (1) according to an embodiment of the present disclosure, the comparison information may include common point information regarding a common point that a certain number or more of specific words are present in the additional information corresponding to each of the multiple conferences when the certain number or more of specific words are present in the multiple audio data or the multiple text data. This makes it possible to detect common points between the multiple conferences by a simple method.

[0021] The information processing device (1) according to one embodiment of the present disclosure includes a billing unit (18) that bills a user who receives the comparison information through a user terminal (3), and the amount of the bill may be determined according to at least one of the number of multiple conferences, the number of organizations holding multiple conferences, the number of industries or occupations of the organizations holding multiple conferences, and the number of items compared in the comparison information. This makes it possible to bill the user at a more appropriate amount.

[0022] The information processing device (1) according to an embodiment of the present disclosure includes a billing unit (18) that bills a user who receives additional information through a user terminal (3), and the amount of the billing may be determined according to at least one of the amount of voice data, the amount of text data, and the amount of additional information. This makes it possible to bill the user at a more appropriate amount.

[0023] An information processing device (1) according to an embodiment of the present disclosure includes an evaluation unit (19) that evaluates each of a plurality of conferences, and an additional information generating unit (12) generates additional information including evaluation information related to the evaluation results of the evaluation, and the evaluation information may include evaluation transition information related to the transition of the evaluation results for each of the plurality of conferences. This makes it possible to appropriately evaluate the quality of the conferences and obtain the evaluation results in a suitable manner.

[0024] An information processing device (1) according to one embodiment of the present disclosure includes an evaluation unit (19) that evaluates each of a plurality of conferences, the evaluation unit (19) evaluates the conference by referring to characteristic information related to the conference, an additional information generating unit (12) generates additional information corresponding to each of the plurality of conferences based on the evaluation result by the evaluation unit (19) and generates comparison information that is information on a comparison result obtained by comparing the additional information corresponding to each of the plurality of conferences, and further includes a charging unit (18) that charges a user who receives the comparison information by a user terminal (3), and the amount of the charge may be determined according to the evaluation. This makes it possible to appropriately evaluate the quality of the conference, obtain the evaluation result in a suitable manner, and charge the user a more appropriate amount.

[0025] An information processing device (1) according to an embodiment of the present disclosure includes a viewpoint setting unit (20) that sets a viewpoint for analyzing a voice uttered by a user, and a text data generating unit (11) may generate text data summarized based on the viewpoint set by the viewpoint setting unit (20). This makes it possible to obtain text data summarized based on a desired viewpoint, thereby further improving convenience.

[0026] An information processing device (1) according to an embodiment of the present disclosure may include a classification item setting unit (21) that sets classification items that subdivide the viewpoints set by the viewpoint setting unit (20), and a text data classification unit (22) that classifies text data summarized based on the viewpoints according to the classification items that subdivide the viewpoints. This allows the text data to be classified based on its contents, thereby further improving convenience.

[0027] Note that the reference symbols in parentheses above are intended to indicate the reference symbols of components in the embodiments described below as an example of the present disclosure, and are not intended to limit the present disclosure to the aspects of the embodiments. Effect of the Invention

[0028] In this way, the information processing device and information processing program according to the present disclosure can further improve convenience when converting speech into text. [Brief description of the drawings]

[0029] [Figure 1] FIG. 1 is a block diagram showing an information processing apparatus according to the present embodiment. [Diagram 2] FIG. 2 is a diagram showing an example of a data structure related to the audio of a conference. [Diagram 3] FIG. 3 is an example of a display screen that displays text data and additional information. [Figure 4] FIG. 4 is an example of a display screen that displays text data and additional information. [Diagram 5] FIG. 5 is an example of a display screen that displays text data and additional information. [Figure 6] FIG. 6 is an example of a display screen that displays text data and additional information. [Figure 7] FIG. 7 is a flowchart showing the additional information generating and transmitting process. [Figure 8] FIG. 8 is a flowchart showing additional information generation and transmission processing in a plurality of conferences. [Figure 9] FIG. 9 is a flowchart showing the text data classification process. [Figure 10] FIG. 10 is a block diagram showing an information processing program according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] Hereinafter, exemplary embodiments will be described with reference to the drawings. In addition, the same or corresponding parts in each drawing are given the same reference numerals, and duplicated explanations will be omitted.

[0031] [Overall configuration] FIG. 1 is a block diagram showing an information processing device 1 according to the present embodiment. The information processing device 1 shown in FIG. 1 is a device that acquires voice data of a voice uttered by a user and analyzes the acquired voice data. Specifically, the information processing device 1 generates text data in which the voice related to the voice data is converted into text, based on the voice data of the voice uttered by the user. Then, the information processing device 1 generates additional information that is information related to at least one of the voice data and the text data, and transmits the text data and the additional information to a user terminal 3. The user terminal 3 (or a terminal capable of communicating with the user terminal 3) displays an image based on the text data and the additional information transmitted from the information processing device 1 on a display.

[0032] The information processing device 1 is configured to be able to communicate with a sound collection device 2 and a user terminal 3. The sound collection device 2 may be, for example, a microphone. As an example, the sound collection device 2 may collect the sound of a conference held by a user. The user terminal 3 may be, for example, a smartphone, a tablet, a notebook computer, or a desktop computer.

[0033] The information processing device 1 is composed of a computer C (server). The information processing device 1 includes, as physical components, a control arithmetic device, a storage device, and an input / output device. The control arithmetic device is composed of a controller such as a CPU (Central Processing Unit), and executes arithmetic processing and controls the storage device and the input / output device. The storage device includes, for example, a main storage device and an auxiliary storage device. The main storage device includes, for example, a RAM (Random Access Memory). The auxiliary storage device includes, for example, a ROM (Read Only Memory). The input / output device includes, for example, an input device that receives data from the outside and transmits it to the storage device, and an output device that outputs to the outside the calculation results that are calculated by the control arithmetic unit and stored in the storage device.

[0034] The information processing device 1 executes a predetermined process by, for example, loading a program stored in a ROM into a RAM and executing the program loaded into the RAM with a CPU. Specifically, the information processing device 1 realizes each function of the information processing device 1 described below by loading an information processing program P stored in a ROM into a RAM and executing the information processing program P loaded into the RAM with a CPU. Note that the computer C constituting the information processing device 1 may have a physical configuration different from the above-mentioned configuration.

[0035] Functionally, the information processing device 1 includes a voice data acquisition unit 10, a text data generation unit 11, an additional information generation unit 12, an information transmission unit 13, a problem recognition unit 14, a comment addition information receiving unit 15, a data analysis unit 16, a feature extraction unit 17, an accounting unit 18, an evaluation unit 19, a viewpoint setting unit 20, a classification item setting unit 21, and a text data classification unit 22.

[0036] The voice data acquisition unit 10 acquires voice data of a voice uttered by a user. For example, the voice data acquisition unit 10 may acquire voice data by receiving voice data of a voice collected by the sound collection device 2 from the sound collection device 2. Note that the voice data acquisition unit 10 may acquire voice data related to recorded voice, or may acquire voice data related to real-time voice.

[0037] The voice data acquisition unit 10 may acquire voice data in multiple conferences. The "multiple conferences" may be multiple conferences consisting of multiple organizations, or multiple conferences in one organization. The "organization" may be an organization (company, institution, etc.), a team, or a department. Alternatively, the "multiple conferences" may be multiple conferences in which a specific user participates. Alternatively, the "multiple conferences" may be "a conference in which a specific user participates and another conference in which the specific user does not participate."

[0038] The text data generating unit 11 generates text data by converting the voice related to the voice data acquired by the voice data acquiring unit 10 into text. The text data generating unit 11 may convert the voice into text (i.e., transcribe) using, for example, a known voice recognition function. The text data generating unit 11 may convert the voice related to the voice data into text as it is, or may summarize the voice related to the voice data into text.

[0039] When the voice data for a plurality of conferences is acquired by the voice data acquisition unit 10, the text data generation unit 11 may generate text data for the plurality of conferences based on the voice data for the plurality of conferences. In this case, the text data generation unit 11 may link the generated plurality of text data to each other.

[0040] Furthermore, when a viewpoint is set by the viewpoint setting unit 20 as described below, the text data generation unit 11 may generate text data based on the viewpoint set by the viewpoint setting unit 20. Specifically, the text data generation unit 11 may generate summarized text data based on the viewpoint set by the viewpoint setting unit 20.

[0041] The additional information generating unit 12 generates additional information. The "additional information" is information related to at least one of voice data and text data. Specifically, the additional information generating unit 12 may generate additional information based on an analysis result of at least one of voice data and text data analyzed by a data analyzing unit 16 described later. The additional information generating unit 12 may generate additional information based on prior information acquired in advance in addition to at least one of voice data and text data. The "prior information" may be, for example, the user's name, sex, age, company / department, occupation, date / time / location of a meeting, the number of users who participated in the meeting, information on past meetings, etc. (including statistical information on past meetings, etc.).

[0042] The additional information generating unit 12 may generate additional information including answer information. The "answer information" is information on an answer to a problem recognized by the problem recognizing unit 14 as described later. The additional information generating unit 12 may acquire answer information from a database provided in the information processing device 1, for example, or may acquire answer information by searching through a network. Alternatively, the additional information generating unit 12 may generate an answer to a problem by so-called AI. The "answer" is information for solving a problem. Specifically, the answer may be a direct answer for solving a problem, or an indirect answer for solving a problem. The "direct answer" may be an answer indicating specific information (numerical values ​​or names, etc.). Examples of direct answers include, for example, a numerical representation of the market size of the target service, or a representation of the name of the region to be entered. The "indirect answer" may be an answer indicating abstract information (such as the source of the specific information, the degree of the degree, etc.). Examples of indirect answers include the URL or name of a website that contains information about the market size of the target service, or the level of development (urban, rural, etc.) or climate (hot, normal, cold, etc.) of the area to be expanded into.

[0043] The additional information generating unit 12 may generate additional information including highlighting information. The "highlighting information" is information for highlighting a portion of the text related to the text data where a task is described. Specifically, the highlighting information may be information for decorating a portion of the text where a task is described with an underline, highlighting, filling in, bolding, coloring the characters, or the like, or may be information for providing a speech bubble or the like.

[0044] The additional information generating unit 12 may generate additional information including comment display information when the comment adding information receiving unit 15 receives the comment adding information as described later. The "comment display information" is information for displaying a comment related to the comment adding information on the user terminal 3 when the comment adding information receiving unit 15 receives the comment adding information as described later. The additional information generating unit 12 may generate additional information including automatic response information when the comment adding information receiving unit 15 receives the comment adding information as described later. The "automatic response information" is information regarding an automatic response to a comment related to the comment adding information when the comment adding information receiving unit 15 receives the comment adding information. More specifically, the automatic response information may be a response text generated by so-called AI to a comment. By repeating the comment and the response alternately in this manner, a dialogue (information exchange similar to a dialogue) between the user and the information processing device 1 is possible.

[0045] The additional information generating unit 12 may generate additional information including vendor information. The "vendor information" is information about a vendor that can solve the problem recognized by the problem recognizing unit 14 as described below. Specifically, the vendor information may be the name of the vendor, a website URL, a thumbnail image, or an introduction of the vendor. The "vendor" may be a research company, a consulting company, an education company, a marketing company, or the like, and the type and field of business are not particularly limited. The additional information generating unit 12 may obtain the vendor information from, for example, a database provided in the information processing device 1, or may obtain the vendor information by searching via a network.

[0046] The additional information generating unit 12 may generate additional information including feature information. The "feature information" is information about features extracted by the feature extracting unit 17 as described later. More specifically, the additional information generating unit 12 may generate additional information including superior feature information or inferior feature information. The "superior feature information" is information about superior features related to the target conference. The "superior feature" is a relatively superior feature, and a comparison target serving as a standard may be set arbitrarily. The additional information including superior feature information may be additional information showing superior points of the target conference. The "inferior feature information" is information about inferior features related to the target conference. The "inferior feature" is a relatively inferior feature, and a comparison target serving as a standard may be set arbitrarily. The additional information including inferior feature information may be additional information showing inferior points of the target conference. In addition to the superior feature and the inferior feature, the feature information may include intermediate feature information about intermediate features that are neither particularly superior nor particularly inferior.

[0047] When the voice data of multiple conferences is acquired by the voice data acquisition unit 10, the additional information generation unit 12 may generate additional information corresponding to each conference and comparative information for each conference. The "comparison information" is information on the comparison result obtained by comparing the additional information corresponding to each conference.

[0048] For example, the comparison information may include commonality information of each conference. The "commonality information" is information related to commonalities of the additional information corresponding to each conference. The "commonality information" refers to points (matters) that are recognized as being common to each other. More specifically, the comparison information may include commonality information related to a commonality that, when a specific word common to the additional information corresponding to each conference exists a predetermined number or more, the word exists in the additional information corresponding to each conference a predetermined number or more. Note that whether or not the word exists in the additional information corresponding to each conference a predetermined number or more may be determined by analyzing the additional information by the data analysis unit 16 described later.

[0049] Alternatively, the comparison information may include difference information for each conference. The "difference information" is information about differences in additional information corresponding to each conference. The "difference" refers to points (items) that are recognized as being different from each other. Alternatively, the comparison information may include similarity information for each conference. The "similar information" is information about similarities in additional information corresponding to each conference. The "similar points" refers to points (items) that are recognized as being similar to each other. Alternatively, the comparison information may include peculiar point information for each conference. The "peculiar point information" is information about peculiar points of additional information corresponding to each conference. The "peculiar point" refers to points (items) that are recognized as being particularly different compared to the population. In other words, the comparison information may include commonalities, differences, similarities, peculiar points, etc. for each conference extracted based on the comparison results obtained by comparing the additional information corresponding to each conference.

[0050] The additional information generating unit 12 may generate additional information including evaluation information when each conference is evaluated by the evaluation unit 19 as described below. "Evaluation information" is information related to the evaluation result by the evaluation unit 19. Furthermore, when the evaluation information includes evaluation transition information, the additional information generating unit 12 may generate additional information including the evaluation transition information. "Evaluation transition information" is information related to the transition of the evaluation results related to each conference. Specifically, when conferences are held repeatedly multiple times, the evaluation transition information may be the transition of the evaluation results tallied for each conference group that groups together a series of conferences. Alternatively, the evaluation transition information may be the transition of the evaluation results tallied for each conference held within a predetermined period (e.g., one week or one month).

[0051] When generating additional information including comparison information related to additional information corresponding to each conference and evaluation information related to the evaluation result of each conference, the additional information generation unit 12 may generate additional information that links characteristic information of each conference referred to when the evaluation unit 19 evaluates each conference with the evaluation information related to the conference, as described below.

[0052] The information transmission unit 13 transmits various information to an external terminal. For example, the information transmission unit 13 transmits text data, additional information, and comparison information to the user terminal 3. "Transmitting to the user terminal 3" is not limited to directly transmitting to the user terminal 3, and may include, for example, transmitting to a server accessible from the user terminal 3.

[0053] When additional information including highlighting information is generated by the additional information generating unit 12, and a predetermined operation is performed on a portion of the text that is highlighted by the highlighting information, the information transmitting unit 13 may transmit answer information regarding the answer to the assignment to the user terminal 3. At this time, the information transmitting unit 13 may acquire additional information including the answer information generated by the additional information generating unit 12, and transmit the additional information to the user terminal 3. Specifically, when the text is highlighted by decoration such as underlining, highlighting, filling in, bolding, coloring the characters, or a speech bubble, the answer information may be displayed on the user terminal 3 by operating the highlighted portion on the user terminal 3 (tapping, clicking, mouse-over, etc.).

[0054] When the additional information generating unit 12 generates additional information including superior feature information or inferior feature information, the information transmitting unit 13 may transmit the additional information including superior feature information or inferior feature information to the user terminal 3. For example, when the additional information generating unit 12 generates additional information including superior feature information that is information on superior features related to the first conference, which is a first conference, or inferior feature information that is information on inferior features related to the first conference, the information transmitting unit 13 may transmit the additional information to the user terminal 3 of a user who holds a second conference, which is a second conference different from the first conference. In this case, it is possible to make the user who holds the second conference aware of the superior features or inferior features of the first conference, so that the user who holds the second conference can refer to how to conduct an excellent conference or how to conduct a poor conference.

[0055] The problem recognition unit 14 recognizes a problem that the user has based on at least one of the voice data and the text data related to the conference. A "problem" is an event that is preferable for the user to solve. For example, a problem may be something that the user should know, something that the user should do, a problem in the user himself or the user's actions, a question that the user has, a point that the user should improve, etc. Specifically, a problem may be a market or demand for a target service (something that the user should know), a questionnaire survey (something that the user should do), a lack of resources (a problem in the user himself or the user's actions, etc.), which region is preferable to advance into (a question that the user has), strengthening sales power (a point that the user should improve), etc. The problem recognition unit 14 may recognize a problem that the user has by detecting a predetermined word included in the content of the user's remarks. Alternatively, the problem recognition unit 14 may recognize a problem that the user has based on a change or tone of the user's voice, etc.

[0056] The comment addition information receiving unit 15 receives the comment addition information when the additional information including answer information is generated by the additional information generating unit 12. "Comment addition information" is information regarding the addition of a comment to an answer. The comment addition information receiving unit 15 may receive the comment addition information from, for example, the user terminal 3. That is, it becomes possible for a user to input a comment in response to an answer by the information processing device 1. The comment may be, for example, the user's opinion or question.

[0057] The data analysis unit 16 analyzes the contents of the voice data and text data. The data analysis unit 16 may receive input of prior information for analyzing the voice data and text data, and analyze the contents of the received prior information. The prior information may be, for example, the user's name, gender, age, company / department, occupation, date / time / location of the meeting, the number of users who participated in the meeting, etc.

[0058] The data analysis unit 16 may also measure the number of times a specific word appears in the voice data or text data of each conference. Furthermore, the data analysis unit 16 may determine whether the measured number of times the specific word appears is equal to or greater than a predetermined number.

[0059] The data analysis unit 16 may also measure the number of times a specific word appears in the additional information corresponding to each conference. Furthermore, the data analysis unit 16 may determine whether the measured number of times the specific word appears is equal to or greater than a predetermined number.

[0060] The feature extraction unit 17 extracts features of the voice data in each conference or the text data in each conference. A "feature" is a tendency of the voice uttered by a user in a conference. For example, the feature may be extracted based on the frequency of a particular word, the length of time that laughter occurs, the bias of users who speak, the length of time between utterances, etc. Specifically, the feature may be a tendency that "a particular word is spoken frequently," a tendency that "there is a lot of laughter and it is harmonious," a tendency that "the user who speaks is biased toward one person," a tendency that "the gap between utterances is long and the conversation does not proceed smoothly," etc.

[0061] The feature extraction unit 17 may further extract superior or inferior features from the extracted features. In this case, the feature extraction unit 17 may determine whether the extracted feature is superior or inferior (or intermediate) in light of a preset judgment criterion.

[0062] The billing unit 18 bills the user for a usage fee or the like related to the use of the information processing device 1. When the additional information generating unit 12 generates additional information, the billing unit 18 may bill the user who receives the additional information by the user terminal 3. When the additional information generating unit 12 generates comparison information, the billing unit 18 may bill the user who receives the comparison information by the user terminal 3. The amount of the billing may be determined according to at least one of the number of meetings related to the comparison information, the number of organizations holding meetings related to the comparison information, the number of industries or occupations of the organizations holding meetings related to the comparison information, and the number of items compared in the comparison information. The "items compared" may be, for example, a balance or bias in the amount of speech of each user, a frequency or timing of pauses or silences, a frequency or timing of laughter, etc. The amount of the billing may be determined according to at least one of the amount of voice data, the amount of text data, and the amount of additional information.

[0063] Alternatively, when the evaluation unit 19 evaluates each conference as described below, and the evaluation unit 19 evaluates the conference by referring to characteristic information related to the conference, the amount of the charge may be determined according to the evaluation. More specifically, when the evaluation unit 19 evaluates each conference, and the evaluation unit 19 evaluates the conference by referring to characteristic information related to the conference, additional information corresponding to each conference is generated based on the evaluation result by the evaluation unit 19, and comparison information is generated, which is information on the comparison result of comparing the additional information corresponding to each conference, the amount of the charge may be determined according to the evaluation. Here, each conference may be evaluated based on the number of superior characteristics or inferior characteristics. As an example, the amount of the charge may be determined as follows: 10,000 yen for a user who receives comparative information of a conference rated A rank, 5,000 yen for a user who receives comparative information of a conference rated B rank, and 1,000 yen for a user who receives comparative information of a conference rated C rank.

[0064] The evaluation unit 19 evaluates the conference. When there are multiple conferences, the evaluation unit 19 may evaluate each conference. The evaluation unit 19 may evaluate each conference by referring to characteristic information related to the conference, or may evaluate the conference based on the results of a questionnaire administered to participants in the conference. The evaluation unit 19 may further evaluate the conference based on prior information related to the conference.

[0065] The viewpoint setting unit 20 sets a viewpoint for analyzing the voice uttered by the user. A "viewpoint" is a main theme when analyzing the voice. The viewpoint may be, for example, marketing, sales, research and development, management, new business, etc. As an example, when marketing is set as the viewpoint, text data may be generated in which marketing-related content is mainly extracted from the entire voice. The viewpoint setting unit 20 may set the viewpoint by receiving information for selecting or specifying the viewpoint to be set from the user terminal 3.

[0066] The classification item setting unit 21 sets classification items. A "classification item" is an item that subdivides the viewpoint set by the viewpoint setting unit 20. A classification item may be a category or a topic. For example, when marketing is set as the viewpoint, the classification items may be inbound marketing, search engine marketing, content marketing, affiliate marketing, SNS marketing, email marketing, and the like. The classification item setting unit 21 may be capable of adding and deleting classification items after setting the classification items. The classification item setting unit 21 may set the classification items by receiving information from the user terminal 3 that selects or specifies the classification items to be set, and the like.

[0067] The text data classification unit 22 classifies the text data summarized based on the viewpoint set by the viewpoint setting unit 20 according to classification items that subdivide the viewpoint. The classification items may be the classification items set by the classification item setting unit 21, or may be classification items set in advance. The text data classification unit 22 may classify the text data and may also appropriately tag the text data, provide internal links, provide titles, etc.

[0068] [Data Structure] Next, a data structure related to the voice of a conference processed by the information processing device 1 will be described. FIG. 2 is a diagram showing an example of the data structure related to the voice of a conference. As shown in FIG. 2, data of the collected voice of a conference (here, video data in which images are also recorded in addition to the voice) is transcribed (converted into text) by the text data generating unit 11 according to a preset viewpoint. At this point, the text may be a summary of the voice, or may be a direct transcription without being summarized. At this time, the text is linked to a timeline (time). The transcribed text is classified into topics according to the classification items set by the classification item setting unit 21. At this time, a single topic is linked to a single or multiple texts. After that, the text classified into a topic is further classified into topic categories that are further subdivided. At this time, a single topic category is linked to a single or multiple topics. The text classified into a topic category is summarized for each topic category. Note that the data structure related to the voice of a conference processed by the information processing device 1 may be different from that described here.

[0069] [Display screen] Next, a display screen displayed on the display of the user terminal 3 based on the text data and additional information transmitted from the information processing device 1 to the user terminal 3 will be described. FIGS. 3 to 6 are examples of display screens that display the text data and additional information. In FIG. 3, texts linked to a timeline and a list in which each text is classified into topics are displayed. Topics corresponding to the contents of the transcribed text (transcription contents) are displayed by icons or the like, and texts can be narrowed down for each topic. In addition, by selecting the display of the timeline linked to the text, audio (video) can be played from the corresponding position. In addition, in FIG. 3, the contents finally summarized for each topic category are displayed. Furthermore, in FIG. 3, from the viewpoint of monetization, buttons for charging for "classifying topic categories" and "adding topics to transcription" are provided. The rules for this charging can be set arbitrarily, and for example, the first video may be free (automatic) and the second and subsequent videos may be charged. In FIG. 4, a list in which topics and topic categories (categories) are organized is displayed. In the display screen shown in FIG. 4, topics and topic categories can be arranged, added, deleted, etc. In the display screen shown in FIG. 5, information on what topics are often discussed in each conference is displayed in a list. Here, in the conference "A", the conference "B", and the conference "C", topics "1" and "2" belonging to topic category "1", and topics "3" and "4" belonging to topic category "2", which are far apart, are displayed in a table. In FIG. 6, when a specific topic (topic "A" in this case) is discussed in each of a plurality of conferences, texts related to the topic are automatically listed and displayed for each conference. Note that the display screen of the information processing device 1 may be different from that described here.

[0070] [Additional information generation and transmission process] Next, a description will be given of the additional information generation and transmission process executed by the information processing device 1. Fig. 7 is a flowchart showing the additional information generation and transmission process. The additional information generation and transmission process shown in Fig. 7 is executed after the sound of a conference is picked up by the sound collection device 2, for example.

[0071] In step S10, the voice data acquisition unit 10 of the information processing device 1 acquires voice data of a voice uttered by a user. The voice data acquisition unit 10 acquires the voice data, for example, by receiving voice data of a voice collected by the sound collection device 2 from the sound collection device 2. After that, the additional information generation and transmission process proceeds to step S12.

[0072] In step S12, the text data generating unit 11 of the information processing device 1 generates text data in which the voice related to the voice data is converted into text, based on the voice data acquired by the voice data acquiring unit 10. After that, the additional information generating and transmitting process proceeds to step S14.

[0073] In step S14, the problem recognition unit 14 of the information processing device 1 recognizes the problem the user is facing based on at least one of the voice data and the text data related to the conference. The problem recognition unit 14 may recognize the problem the user is facing by detecting a predetermined word included in the content of the user's remarks. Alternatively, the problem recognition unit 14 may recognize the problem the user is facing based on a change or tone of the user's voice. After that, the additional information generation and transmission process proceeds to step S16.

[0074] In step S16, the additional information generating unit 12 of the information processing device 1 acquires answer information related to the answer to the assignment. The additional information generating unit 12 may acquire the answer information from a database provided in the information processing device 1, for example, or may acquire the answer information by searching via a network. Alternatively, the additional information generating unit 12 may generate the answer to the assignment by so-called AI. After that, the additional information generating and transmitting process proceeds to step S18.

[0075] In step S18, the additional information generating unit 12 of the information processing device 1 acquires highlighting information. Specifically, the additional information generating unit 12 generates (acquires) highlighting information for decorating the portion of the text where the task is described with underlining, highlighting, filling in, bolding, coloring the characters, etc., or for providing a speech bubble, etc. After that, the additional information generating and transmitting process proceeds to step S20.

[0076] In step S20, the comment addition information receiving unit 15 of the information processing device 1 receives (acquires) comment addition information regarding the addition of a comment to an answer. The comment addition information receiving unit 15 receives the comment addition information from, for example, the user terminal 3. After that, the additional information generation and transmission process proceeds to step S22.

[0077] In step S22, the additional information generating unit 12 of the information processing device 1 generates (obtains) comment addition information for displaying the comment related to the comment addition information on the user terminal 3. After that, the additional information generating and transmitting process proceeds to step S24.

[0078] In step S24, the additional information generating unit 12 of the information processing device 1 acquires vendor information related to a vendor that can solve the problem. The additional information generating unit 12 may acquire the vendor information from, for example, a database provided in the information processing device 1, or may acquire the vendor information by searching via a network. After that, the additional information generating and transmitting process proceeds to step S26.

[0079] In step S26, the additional information generating unit 12 generates (obtains) additional information including automatic response information regarding an automatic response to the comment related to the comment addition information. For example, the additional information generating unit 12 may generate the automatic response information by a so-called AI. After that, the additional information generating and transmitting process proceeds to step S28.

[0080] In step S28, the additional information generating unit 12 of the information processing device 1 generates additional information including the above-mentioned answer information, highlighting information, comment addition information, comment display information, business information, and automatic response information. After that, the additional information generating and transmitting process proceeds to step S30.

[0081] In step S30, the information transmitting unit 13 of the information processing device 1 transmits the text data and the additional information to the user terminal 3. This ends the current additional information generation and transmission process.

[0082] [Additional information generation and transmission processing in multiple conferences] Next, the additional information generation and transmission process in multiple conferences will be described. Fig. 8 is a flowchart showing the additional information generation and transmission process in multiple conferences. The additional information generation and transmission process in multiple conferences shown in Fig. 8 is executed after the sounds of the multiple conferences are collected by the sound collection device 2, for example.

[0083] In step S40, the voice data acquisition unit 10 of the information processing device 1 acquires voice data in a plurality of conferences. The voice data acquisition unit 10 acquires the voice data, for example, by receiving voice data of voices collected by the sound collection device 2 from the sound collection device 2. After that, the additional information generation and transmission process in a plurality of conferences proceeds to step S42.

[0084] In step S42, the text data generating unit 11 of the information processing device 1 generates text data in which the voice related to the voice data is converted into text, for each of the voice data in the multiple conferences acquired by the voice data acquiring unit 10. After that, the additional information generating and transmitting process in the multiple conferences proceeds to step S44.

[0085] In step S44, the feature extraction unit 17 of the information processing device 1 extracts features of the voice data in each conference or the text data in each conference. In addition, the additional information generation unit 12 of the information processing device 1 generates (acquires) feature information related to the extracted features. After that, the additional information generation and transmission process for multiple conferences proceeds to step S46.

[0086] In step S46, the feature extraction unit 17 of the information processing device 1 further extracts superior features or inferior features from the extracted features. In addition, in association with this, the additional information generation unit 12 of the information processing device 1 generates (acquires) superior feature information or inferior feature information related to the extracted superior features or inferior features. After that, the additional information generation and transmission process for multiple conferences proceeds to step S48.

[0087] In step S48, the evaluation unit 19 of the information processing device 1 evaluates the multiple conferences. The evaluation unit 19 may evaluate each conference by referring to characteristic information related to the conference, or may evaluate the conference based on the results of a questionnaire administered to the participants of the conference. In addition, the additional information generation unit 12 of the information processing device 1 accordingly generates (obtains) evaluation information related to the evaluation results of the evaluation of each conference. Thereafter, the additional information generation and transmission process for the multiple conferences proceeds to step S50.

[0088] In step S50, the additional information generating unit 12 of the information processing device 1 associates the characteristic information of each conference referred to when evaluating each of the multiple conferences with the evaluation information related to the conference. After that, the additional information generating and transmitting process for the multiple conferences proceeds to step S52.

[0089] In step S52, the additional information generating unit 12 of the information processing device 1 generates additional information including the above-mentioned characteristic information (superior characteristic information and inferior characteristic information), comparison information, and evaluation information. As described above, the characteristic information and evaluation information of each conference are linked to each other. Thereafter, the additional information generating and transmitting process for multiple conferences proceeds to step S54.

[0090] In step S54, the additional information generating unit 12 of the information processing device 1 generates (obtains) comparison information regarding the comparison result obtained by comparing the additional information corresponding to each conference. After that, the additional information generating and transmitting process for the multiple conferences proceeds to step S56.

[0091] In step S56, the information transmitting unit 13 of the information processing device 1 transmits each piece of information, such as the text data, the additional information, and the comparison information, to the user terminal 3. After that, the additional information generating and transmitting process in multiple conferences proceeds to step S58.

[0092] In step S58, the billing unit 18 of the information processing device 1 determines the amount of the charge based on the above-mentioned information. For example, the billing unit 18 may determine the amount of the charge based on the characteristic information and the comparison information. After that, the additional information generation and transmission process for the multiple conferences proceeds to step S60.

[0093] In step S60, the billing unit 18 of the information processing device 1 bills the user for the determined amount. For example, the billing unit 18 may execute a process of debiting a savings account linked to the user, or may execute a process of issuing an invoice to the user. Alternatively, the billing unit 18 may present information to an administrator who operates the information processing device 1, requesting that the administrator bill the user. This completes the additional information generation and transmission process for the multiple conferences.

[0094] [Text data classification processing] Next, the text data classification process will be described. Fig. 9 is a flowchart showing the text data classification process. The text data classification process shown in Fig. 9 is executed after the sound of a conference is collected by the sound collection device 2, for example.

[0095] In step S70, the voice data acquisition unit 10 of the information processing device 1 acquires voice data of a voice uttered by a user. The voice data acquisition unit 10 acquires the voice data, for example, by receiving voice data of a voice collected by the sound collection device 2 from the sound collection device 2. After that, the text data classification process proceeds to step S72.

[0096] In step S72, the viewpoint setting unit 20 of the information processing device 1 sets a viewpoint for analyzing the speech. The viewpoint setting unit 20 may set a viewpoint by receiving information for selecting or specifying the viewpoint to be set from the user terminal 3. After that, the text data classification process proceeds to step S74.

[0097] In step S74, the classification item setting unit 21 of the information processing device 1 sets classification items with subdivided viewpoints. The classification item setting unit 21 may set classification items by receiving information for selecting or specifying the classification items to be set from the user terminal 3. Thereafter, the text data classification process proceeds to step S76.

[0098] In step S76, the text data generating unit 11 of the information processing device 1 generates text data in which the voice related to the voice data acquired by the voice data acquiring unit 10 is converted into text, based on the voice data. Specifically, the text data generating unit 11 generates text data summarized based on the viewpoint set by the viewpoint setting unit 20. Thereafter, the text data classification process proceeds to step S78.

[0099] In step S78, the text data classification unit 22 of the information processing device 1 classifies the text data summarized based on the viewpoint set by the viewpoint setting unit 20, according to the classification items set by the classification item setting unit 21. The text data classification unit 22 may also appropriately tag the text data, provide internal links, provide titles, etc., in addition to classifying the text data. This ends the current text data classification process.

[0100] [Information Processing Program] An information processing program P for causing a computer C to function as an information processing device 1 will be described. Fig. 10 is a block diagram showing the information processing program P according to this embodiment. As shown in Fig. 10, the information processing program P includes a main module MM, a voice data acquisition module M10, a text data generation module M11, an additional information generation module M12, an information transmission module M13, a task recognition module M14, a comment additional information reception module M15, a data analysis module M16, a feature extraction module M17, a billing module M18, an evaluation module M19, a viewpoint setting module M20, a classification item setting module M21, and a text data classification module M22.

[0101] The main module MM is a module that comprehensively controls the computer C. Functions realized by executing each of the voice data acquisition module M10, the text data generation module M11, the additional information generation module M12, the information transmission module M13, the task recognition module M14, the comment additional information reception module M15, the data analysis module M16, the feature extraction module M17, the billing module M18, the evaluation module M19, the viewpoint setting module M20, the classification item setting module M21, and the text data classification module M22 are similar to the functions of each of the voice data acquisition unit 10, the text data generation unit 11, the additional information generation unit 12, the information transmission unit 13, the task recognition unit 14, the comment additional information reception unit 15, the data analysis unit 16, the feature extraction unit 17, the billing unit 18, the evaluation unit 19, the viewpoint setting unit 20, the classification item setting unit 21, and the text data classification unit 22. Furthermore, the information processing program P may not include at least some of the modules mentioned above other than the main module MM, the voice data acquisition module M10, the text data generation module M11, the additional information generation module M12, and the information transmission module M13.

[0102] [Action and Effects] As described above, the information processing device 1 includes a voice data acquisition unit 10 that acquires voice data of voice uttered by a user, a text data generation unit 11 that generates text data by converting the voice related to the voice data acquired by the voice data acquisition unit 10 into text, an additional information generation unit 12 that generates additional information that is information related to at least one of the voice data and the text data, and an information transmission unit 13 that transmits the text data and the additional information to the user terminal 3.

[0103] The information processing program P causes the computer C to function as an audio data acquisition unit 10 that acquires audio data of speech uttered by a user, a text data generation unit 11 that generates text data that converts the audio related to the audio data acquired by the audio data acquisition unit 10 into text based on the audio data, an additional information generation unit 12 that generates additional information that is information related to at least one of the audio data and the text data, and an information transmission unit 13 that transmits the text data and the additional information to the user terminal 3.

[0104] According to at least one of the information processing device 1 and the information processing program P, it is possible to effectively utilize the voice data of the voice uttered by the user, and obtain added value that cannot be obtained by simply converting the voice into text as it is. Therefore, it is possible to further improve the convenience when converting voice into text.

[0105] The information processing device 1 includes a task recognition unit 14 that recognizes a task that the user has based on at least one of voice data and text data, and the additional information generation unit 12 may generate additional information including answer information that is information related to an answer to the task recognized by the task recognition unit 14. This allows the user to obtain an answer to the task that the user has, thereby further improving convenience.

[0106] In the information processing device 1, the additional information generating unit 12 may generate additional information including highlighting information for highlighting a portion in which a problem is described in the text related to the text data. This allows the user to easily visually recognize the problem.

[0107] In the information processing device 1, when a predetermined operation is performed on a portion of the text that is highlighted by the highlighting information, the information transmitting unit 13 may transmit answer information regarding the answer to the assignment to the user terminal 3. This allows the answer to the assignment to be obtained by a simple operation.

[0108] The information processing device 1 includes a comment addition information receiving unit 15 that receives comment addition information, which is information related to adding a comment to an answer, and when the comment addition information receiving unit 15 receives the comment addition information, the additional information generating unit 12 may generate additional information including comment display information, which is information for displaying a comment related to the comment addition information on the user terminal 3. This allows the comment to be displayed in response to the answer, further improving convenience.

[0109] In the information processing device 1, when the comment addition information receiving unit 15 receives the comment addition information, the additional information generating unit 12 may generate additional information including automatic response information that is information regarding an automatic response to the comment related to the comment addition information. This makes it possible to further obtain various information regarding the comment, thereby further improving convenience.

[0110] In the information processing device 1, the additional information generating unit 12 may generate additional information including vendor information, which is information about a vendor that can solve the problem recognized by the problem recognizing unit 14. This makes it possible to obtain not only an answer to the problem but also information about a vendor that can solve the problem.

[0111] In the information processing device 1, the voice data acquisition unit 10 may acquire voice data in a plurality of conferences, and the text data generation unit 11 may generate text data in a plurality of conferences based on the voice data in the plurality of conferences. This allows the voices in a plurality of conferences to be converted into text, further improving convenience.

[0112] The information processing device 1 includes a feature extraction unit 17 that extracts features of the voice data in a plurality of conferences or the text data in a plurality of conferences, and the additional information generation unit 12 may generate additional information including feature information that is information related to the features extracted by the feature extraction unit 17. This makes it possible to easily analyze the features of each of the plurality of conferences.

[0113] In the information processing device 1, the feature extraction unit 17 further extracts superior features, which are excellent features, or inferior features, which are inferior features, from the extracted features, the additional information generation unit 12 generates additional information including superior feature information, which is information about superior features related to the first conference, which is the first conference, or inferior feature information, which is information about inferior features related to the first conference, and the information transmission unit 13 may transmit the additional information including the superior feature information or inferior feature information to the user terminal 3 of a user who holds a second conference, which is a second conference different from the first conference. This makes it possible to share particularly useful information such as superior feature information or inferior feature information with others.

[0114] In the information processing device 1, the additional information generating unit 12 generates additional information corresponding to each of the multiple conferences, and generates comparison information that is information on a comparison result obtained by comparing the additional information corresponding to each of the multiple conferences, and the information transmitting unit 13 transmits the comparison information to the user terminal 3. This makes it possible to share with others the information on the comparison result obtained by relatively comparing the multiple conferences, thereby further improving convenience.

[0115] In the information processing device 1, the comparison information may include commonalities between the additional information corresponding to each of the multiple conferences, or commonalities between the text data in the multiple conferences. This allows the information on the comparison result focusing on the commonalities between the multiple conferences to be shared with others, further improving convenience.

[0116] In the information processing device 1, the comparison information may include common point information regarding the common point that a certain number or more of specific words are present in the additional information corresponding to each of the multiple conferences when the certain number or more of specific words are present in the multiple voice data or the multiple text data. This makes it possible to detect common points between the multiple conferences by a simple method.

[0117] The information processing device 1 includes a billing unit 18 that bills the user who receives the comparison information through the user terminal 3, and the amount of the bill may be determined according to at least one of the number of multiple conferences, the number of organizations holding multiple conferences, the number of industries or occupations of the organizations holding multiple conferences, and the number of items compared in the comparison information. This makes it possible to bill the user at a more appropriate amount.

[0118] The information processing device 1 includes a billing unit 18 that bills the user who receives the additional information through the user terminal 3, and the amount of the bill is determined according to at least one of the amount of voice data, the amount of text data, and the amount of the additional information. This makes it possible to bill the user at a more appropriate amount.

[0119] The information processing device 1 includes an evaluation unit 19 that evaluates each of the multiple conferences, and the additional information generating unit 12 generates additional information including evaluation information related to the evaluation results of the evaluation, and the evaluation information may include evaluation transition information related to the transition of the evaluation results related to each of the multiple conferences. This makes it possible to appropriately evaluate the quality of the conferences and obtain the evaluation results in a suitable manner.

[0120] The information processing device 1 includes an evaluation unit 19 that evaluates each of the multiple conferences, the evaluation unit 19 evaluates the conference by referring to characteristic information related to the conference, the additional information generation unit 12 generates additional information corresponding to each of the multiple conferences based on the evaluation result by the evaluation unit 19 and generates comparison information which is information related to the comparison result obtained by comparing the additional information corresponding to each of the multiple conferences, and further includes a charging unit 18 that charges a user who receives the comparison information by a user terminal 3, and the amount of the charge is determined according to the evaluation. This makes it possible to appropriately evaluate the quality of the conferences and obtain the evaluation result in a suitable manner, and to charge the user a more appropriate amount.

[0121] The information processing device 1 may include a viewpoint setting unit 20 that sets a viewpoint for analyzing the voice uttered by the user, and the text data generating unit 11 may generate text data summarized based on the viewpoint set by the viewpoint setting unit 20. This makes it possible to obtain text data summarized based on a desired viewpoint, thereby further improving convenience.

[0122] The information processing device 1 may include a classification item setting unit 21 that sets classification items that subdivide the viewpoints set by the viewpoint setting unit 20, and a text data classification unit 22 that classifies text data summarized based on the viewpoints according to the classification items that subdivide the viewpoints. This allows the text data to be classified based on its contents, further improving convenience.

[0123] [Variations] The above-described embodiment can be embodied in various forms that are modified or improved based on the knowledge of a person skilled in the art. For example, in the above-described embodiment, the screen displays shown in Figures 2 to 5 are merely examples, and screen displays different from these may be adopted. [Explanation of symbols]

[0124] 1. Information processing device 2. Sound recording device 3. User terminal 10 Audio data acquisition unit 11 Text data generation section 12 Additional information generation unit 13 Information transmission section 14 Issue recognition section 15 Comment Additional Information Receiving Section 16 Data Analysis Department 17 Feature Extraction Unit 18 Billing Department 19 Evaluation Section 20. Viewpoint Setting Section 21 Classification item setting section 22 Text Data Classification Unit C. Computer P Information Processing Program

Claims

1. An information processing device that acquires voice data of voices uttered by users who are participating in multiple conferences consisting of multiple groups, and analyzes the acquired voice data, a voice data acquisition unit that acquires the voice data in each of the conferences; a text data generation unit that generates text data by converting the voice related to the voice data acquired by the voice data acquisition unit into text, based on the voice data acquired by the voice data acquisition unit; an additional information generating unit that generates additional information related to at least one of the audio data and the text data; an information transmitting unit that transmits the text data and the additional information to a user terminal of the user; a feature extraction unit that extracts features of the voice data or the text data; a billing unit that bills the user for a usage fee related to the use of the information processing device; Equipped with the additional information generation unit generates the additional information corresponding to each of the conferences and generates comparison information that is information regarding a comparison result obtained by comparing the additional information corresponding to each of the conferences; the information transmission unit transmits the comparison information to the user terminal; the billing unit bills the user who receives the comparison information via the user terminal; the additional information includes feature information that is information about the features extracted by the feature extraction unit, and the feature information includes a frequency of occurrence of a specific word; the comparison information includes commonality information regarding a commonality that, when a predetermined number or more of specific words are present in the additional information corresponding to each of the meetings, the specific words are present in the additional information corresponding to each of the meetings, and The amount of the charge is determined according to the number of the groups holding the meetings.

1. An information processing device comprising:

2. a problem recognition unit that recognizes a problem that the user has based on at least one of the voice data and the text data; The additional information generating unit generates the additional information including answer information that is information about an answer to the assignment recognized by the assignment recognizing unit.

2. The information processing apparatus according to claim 1, wherein:

3. The additional information generating unit generates the additional information including highlighting information that is information for highlighting a portion in the text related to the text data where the problem is described.

3. The information processing apparatus according to claim 2, wherein:

4. The information sending unit sends the answer information regarding the answer to the assignment to the user terminal when a predetermined operation is performed on a portion of the text that is highlighted by the highlighting information.

4. The information processing apparatus according to claim 3,

5. a comment addition information receiving unit that receives comment addition information that is information regarding adding a comment to the answer, When the comment addition information receiving unit receives the comment addition information, the additional information generating unit generates the additional information including comment display information that is information for displaying the comment related to the comment addition information on the user terminal.

3. The information processing apparatus according to claim 2, wherein:

6. When the comment addition information receiving unit receives the comment addition information, the additional information generating unit generates the additional information including automatic response information that is information regarding an automatic response to the comment related to the comment addition information.

6. The information processing apparatus according to claim 5,

7. The additional information generating unit generates the additional information including vendor information, which is information about a vendor that can solve the problem recognized by the problem recognizing unit.

3. The information processing apparatus according to claim 2, wherein:

8. The feature extraction unit further extracts superior features, which are superior features, or inferior features, which are inferior features, from the extracted features; the additional information generation unit generates the additional information including superior feature information, which is information about the superior feature related to a first conference among the plurality of conferences, or inferior feature information, which is information about the inferior feature related to the first conference; The information transmitting unit transmits the additional information including the superior feature information or the inferior feature information to the user terminal of the user who is holding a second conference separate from the first conference.

2. The information processing apparatus according to claim 1, wherein:

9. The amount of the charge is further determined according to at least one of the number of the plurality of meetings, the number of industries or occupations of the organizations holding the plurality of meetings, and the number of items compared in the comparison information.

2. The information processing apparatus according to claim 1, wherein:

10. The amount of the charge is further determined according to at least one of the amount of the voice data, the amount of the text data, and the amount of the additional information.

2. The information processing apparatus according to claim 1, wherein:

11. An evaluation unit for evaluating each of the meetings, the additional information generation unit generates the additional information including evaluation information related to the evaluation result by the evaluation unit; The evaluation information includes evaluation transition information regarding transitions of the evaluation results for each of the meetings.

2. The information processing apparatus according to claim 1, wherein:

12. An evaluation unit for evaluating each of the meetings, the evaluation unit evaluates each of the conferences by referring to the characteristic information related to each of the conferences; the additional information generation unit generates the additional information corresponding to each of the conferences based on the evaluation result by the evaluation unit, and generates comparison information which is information on a comparison result obtained by comparing the additional information corresponding to each of the conferences; The amount of the charge is determined according to the evaluation.

2. The information processing apparatus according to claim 1, wherein:

13. A viewpoint setting unit that sets a viewpoint for analyzing the voice uttered by the user, The text data generating unit generates the summarized text data based on the viewpoint set by the viewpoint setting unit.

2. The information processing apparatus according to claim 1, wherein:

14. A classification item setting unit that sets classification items that subdivide the viewpoints set by the viewpoint setting unit; a text data classification unit that classifies the text data summarized based on the viewpoint according to the classification items that subdivide the viewpoint.

14. The information processing apparatus according to claim 13,

15. A computer is caused to function as the voice data acquisition unit, the text data generation unit, the additional information generation unit, the information transmission unit, the feature extraction unit, and the billing unit that constitute the information processing device according to claim 1. An information processing program characterized by:

Images