Information processing device and information processing method

Abstract

An information processing device (10) is provided with a calculation unit (12) for calculating a score to determine a feature of each participant on the basis of utterance content data indicating utterance content of each participant in a discussion, and a determination unit (13) for determining content of facilitation on the basis of the features of the participants based on the scores calculated by the calculation unit (12).

Description

Information processing device and information processing method

[0001] This disclosure relates to an information processing device and an information processing method.

[0002] The techniques of facilitation, which are methods for conducting meetings smoothly and improving their value to participants, are well known. In facilitation, a "good meeting" is one in which a conclusion is reached within the allotted time in a state of agreement with all participants. The role of the facilitator, who carries out the facilitation, is not to directly offer various ideas themselves, but rather to draw out the opinions of the participants in order to ensure that the discussion proceeds smoothly and to summarize them in a way that is acceptable to all participants. Implementing such facilitation requires multiple advanced skills, such as sensing the state of the discussion, exploring ideas in depth, presenting different perspectives, and organizing the discussion. As a result, there are problems with the concentration of the burden due to reliance on specific individuals with these skills, and there are also aspects where it is difficult to guarantee the quality of the meeting.

[0003] Patent Document 1, described below, describes a technique for preferentially selecting participants who possess extensive knowledge related to a topic that arises during a discussion (i.e., experts on that topic) as potential speakers, based on pre-prepared participant knowledge information.

[0004] Japanese Patent Publication No. 2022-113066

[0005] However, in order to aim for a good meeting, it is not enough to simply have experts on the topic at hand speak as described in Patent Document 1. Facilitation is needed that allows for smooth progress by limiting the speaking opportunities of disruptive participants who repeatedly make comments that hinder the progress of the discussion, and by ensuring that each participant speaks at a predetermined level or higher to improve the overall level of understanding among participants.

[0006] Therefore, this disclosure aims to automatically perform facilitation according to the characteristics of each participant, thereby efficiently conducting effective meetings.

[0007] The information processing device relating to this disclosure comprises a calculation unit that calculates a score for determining the characteristics of each participant based on speech content data showing the content of each participant's statements in a discussion, and a determination unit that determines the content of facilitation based on the characteristics of each participant based on the score calculated by the calculation unit.

[0008] According to this disclosure, facilitation can be automatically performed according to the characteristics of each participant, enabling efficient and effective meetings.

[0009] This is a configuration diagram showing one example of the configuration of an information processing device. This is a flowchart of the processing performed by the information processing device. This is a diagram explaining the method for calculating the degree of influence. This is a diagram explaining an example of processing by the decision unit. This is a configuration diagram showing another example of the configuration of the information processing device. This is a diagram showing an example of the hardware configuration of the information processing device.

[0010] Hereinafter, an embodiment of the information processing apparatus and information processing method relating to this disclosure will be described with reference to the drawings.

[0011] [Configuration of the Information Processing Device] Figure 1 shows a configuration diagram of the information processing device 10. As shown in Figure 1, the information processing device 10 includes an acquisition unit 11, a calculation unit 12, a determination unit 13, and an output unit 14 as components that realize the functions related to this disclosure. The functions of each unit will be described below.

[0012] The acquisition unit 11 is a functional unit that acquires speech content data indicating the content of each participant's statements from the audio data of the discussion, and includes an audio acquisition unit 11A and a speech recognition unit 11B. The "speech content data" is, for example, text data for each participant indicating the content of each participant's statements. The audio acquisition unit 11A acquires the audio data of the discussion collected by microphones set up in the conference room, the speech recognition unit 11B acquires audio data for each participant by identifying speakers based on existing technology using the acquired audio data, and acquires speech content data for each participant by converting the acquired audio data for each participant into text data.

[0013] The calculation unit 12 is a functional unit that calculates a score to determine the characteristics of each participant based on the acquired data of each participant's statements. Specifically, the calculation unit 12 calculates the following three scores for each participant based on the data of each participant's statements using the procedure described below: - Disruption score X, which is the degree to which a participant is a disruptor who repeatedly makes statements that hinder the progress of the discussion. - Expert score Y, which is the degree to which a participant is an expert in a field related to the discussion. - Speaking score Z, which is a score of the amount of speaking in the discussion. Therefore, the calculation unit 12 includes a disruption score calculation unit 12A for calculating the disruption score X, an expert score calculation unit 12B for calculating the expert score Y, and a speaking score calculation unit 12C for calculating the speaking score Z.

[0014] Regarding the degree of disruption X, the disruption calculation unit 12A, for example, identifies the parts of each participant's statements that oppose (contradict) the ideas of other participants from the participant's statement data, and calculates the frequency of opposing (contradictive) statements as the degree of disruption X. Whether a participant's statement opposes (contradicts) the ideas of other participants may be determined by existing technology described in the paper "Collagree, a large-scale opinion aggregation system based on an online facilitation support mechanism - Social implementation toward citizen discussion for the next comprehensive plan of Nagoya City," by Yuma Imi et al., Transactions of the Information Processing Society of Japan 56.10(2015):1996-2010.

[0015] In the existing technology described above, seed words (words that clearly express agreement and words that clearly express disagreement) are selected, and each seed word is searched using a search engine as a query. The words (nouns, verbs, adjectives, and adverbs) contained in the 1000 snippets of the search results are registered in a dictionary separately for agreement and disagreement, thereby constructing a dictionary used for determining agreement and disagreement. The list of words registered as "agreement" in the constructed dictionary is called the "agreement impression word list PosList," and the list of words registered as "disagreement" is called the "disagreement impression word list NegList." Next, using the above dictionary, the co-occurrence probability P(t,PosList) between word t and words in the agreement impression word list PosList, and the co-occurrence probability P(t,NegList) between word t and words in the disagreement impression word list NegList are calculated. Furthermore, the internal division ratio S of the co-occurrence probability P(t,PosList) and the co-occurrence probability P(t,NegList) is calculated using the following equation (1). The obtained internal division ratio S means that the closer it is to 0, the more likely word t is to appear in an opposing context, and the closer it is to 1, the more likely word t is to appear in an agreeing context. Such an internal division ratio S is calculated for each word (noun, verb, adjective, and adverb) included in the utterance data, and the average of these internal division ratios S is calculated as the "degree of agreement" of a participant's overall utterances. Whether or not the obtained degree of agreement falls below a predetermined threshold value can be used to determine whether a participant's utterances are opposed (contradictory) to the ideas of other participants. Note that it is not mandatory to calculate the degree of disruption X using the above-mentioned existing technology, and it may be obtained by other means. For example, the disruption degree calculation unit 12A may use a machine learning model that uses the utterances of many people with a high degree of disruption as explanatory variables and the calculated degree of disruption of those people as the dependent variable to determine the disruption degree X of a participant from the utterances of that participant.

[0016] Regarding the expert level Y, the expert level calculation unit 12B calculates the expert level Y as the frequency with which each participant expresses opinions based on specialized knowledge and experience, based on the data of each participant's statements. The expert level Y may be calculated using, for example, one of the following two patterns (a) or (b).

[0017] (a) The expert level calculation unit 12B may determine the expert level Y by sending a "prompt to inquire about the frequency of statements based on new specific examples in the statement content data" and the statement content data to a large language model (LLM) built into the information processing device 10 or running on an external server, and the frequency of the response from the LLM. In this case, the frequency may be instructed to be a numerical value in the range of 0 to 100 (the larger the value, the greater the degree of expertise).

[0018] (b) The expert level calculation unit 12B may obtain an answer (degree of expertise) from the classification model by inputting the content of a participant's statements, which include statements containing information that only experienced or knowledgeable people would know, and statements containing information such as "experienced or knowledgeable person," into a classification model (a model that outputs the degree to which a person is an expert) that has been pre-trained as learning data, and then normalize the obtained degree to a number in the range of 0 to 100 (the larger the value, the greater the degree of expertise) to obtain the expert level Y.

[0019] Regarding the utterance score Z, the utterance score calculation unit 12C calculates a score indicating the amount of speaking time in the discussion so far from the content data of each participant's speech, and this score is called the utterance score Z. At this time, the utterance score Z may be calculated based on the speeches of each participant during the discussion, following the procedure below: (i) As a preprocessing step, the utterance score calculation unit 12C performs tokenization (word segmentation) and normalization (unification of character types, case conversion) on each speech. (ii) The utterance score calculation unit 12C calculates the utterance score for each speech from the information obtained in (i) above. For calculating the utterance score here, existing methods for calculating the importance of words appearing in a document, such as TF-IDF (Term Frequency-Inverse Document Frequency) and Okapi BM25, may be used. An example using TF-IDF will be described later with reference to Figure 3. The three scores calculated for each participant (disruptor score X, expert score Y, and utterance score Z) are passed to the determination unit 13.

[0020] Returning to Figure 1, the decision unit 13 is a functional unit that determines the content of the facilitation based on the characteristics of each participant based on the score calculated by the calculation unit 12, and has the following specific functions. The decision unit 13 assigns a predetermined weight (w) to each of the three scores. Ｘ ,w Ｙ ,w Ｚ The overall score is calculated for each participant using the following formula. For example, the overall score may be calculated using a weighted addition formula, and specific examples will be described later. Note that the above weights may be predetermined by prior machine learning or other means.

[0021] Furthermore, the determination unit 13 sets a predetermined threshold (t) for each score. Ｘ ,t Ｙ ,t Ｚ Using the above, the system determines whether a participant falls under the categories of disruptor, expert, or speaker based on whether each score exceeds the corresponding threshold, and any features exceeding the threshold are designated as the participant's "characteristics." However, for "speakers," the determination is based on whether the threshold is met, and if the threshold is not met, the participant is designated as a "non-speaker." Participants who do not have any features exceeding the threshold are designated as having "no characteristics." The above thresholds may be predetermined using machine learning or other methods.

[0022] Furthermore, the decision unit 13 selects the person with the highest overall score. If there are multiple people with the highest overall score, for example, the one with the lowest "speaking level" is selected. If the "speaking level" is also the same, one participant is randomly selected.

[0023] Furthermore, the decision unit 13 determines the content of the facilitation according to the characteristics of the selected participant. Alternatively, the content of the facilitation may be generated based on the response from the LLM (Learning Leadership Model) after querying it along with the participant's characteristic information. Specific examples of how the facilitation content is determined will be explained using specific numerical examples in the processing explanation described later.

[0024] The output unit 14 is a functional unit that outputs the content of the facilitation determined by the determination unit 13. In this case, "output" can take various forms, such as display output, print output, and data transmission to the information processing device 10.

[0025] [Regarding the processing performed in the information processing device] The processing performed in the information processing device 10 (processing related to the information processing method of this disclosure) will be described below in accordance with the flowchart in Figure 2. For example, when a user (operator) of the information processing device 10 inputs a predetermined execution start command, the processing in Figure 2 is started in the information processing device 10.

[0026] First, the voice acquisition unit 11A acquires audio data of the discussion collected by microphones set up in the conference room (step S1 in Figure 2). Then, the speech recognition unit 11B acquires audio data for each participant by identifying the speaker based on existing technology using the acquired audio data, and acquires content data of each participant's statements by converting the acquired audio data for each participant into text data based on existing speech recognition technology (step S2).

[0027] The calculation unit 12 calculates the three aforementioned scores for each participant based on the data of each participant's statements (steps S3A to S3C).

[0028] Regarding the degree of obstruction X, the obstruction calculation unit 12A calculates the degree of obstruction X using the existing technology described above (step S3A). For example, the obstruction calculation unit 12A uses the "dictionary used for determining agreement / disagreement" constructed in the procedure described above to determine the co-occurrence probability P(t,PosList) between the word t in the statement and a word in the agreement impression word list PosList, and the co-occurrence probability P(t,NegList) between the word t and a word in the opposition impression word list NegList, and then uses equation (1) described above to determine the internal division ratio S of the co-occurrence probability P(t,PosList) and the co-occurrence probability P(t,NegList). The closer the internal division ratio S is to 0, the more likely the word t is to appear in an opposing context, and the closer it is to 1, the more likely the word t is to appear in an agreement context. This internal division ratio S is calculated for each word (noun, verb, adjective, and adverb) included in the utterance data. The average of these internal division ratios S is calculated as the overall degree of agreement with a participant's utterances. Whether or not a participant's utterances are opposed to (contradict) the ideas of other participants is determined based on whether or not the degree of agreement falls below a predetermined threshold. Based on the frequency of opposing other participants' ideas and whether or not the opposition is repeated, the degree of disruption X is calculated.

[0029] Furthermore, regarding the level of expertise Y, the level of expertise calculation unit 12B determines the level of expertise Y by, for example, sending a "prompt to inquire about the frequency of statements based on new, specific examples in the statement content data" and the statement content data, and receiving a response from LLM (step S3B). Alternatively, the level of expertise calculation unit 12B may obtain the level of expertise Y using a classification model that has been pre-trained using statements containing information that only experienced or knowledgeable individuals would know, and statements containing information such as "the person is experienced or knowledgeable," as training data.

[0030] Also, regarding the speech frequency Z, the speech frequency calculation unit 12C first performs tokenization (word segmentation) and normalization (unifying character types, converting between uppercase and lowercase) on the speech content data of each participant during the discussion as preprocessing. In the example shown in FIG. 3, for example, for the speech content data of person A, "I think the reason for the delay in the progress of this project is the lack of resources. In particular, the problem is that there are not enough members in the development team.", tokenization and normalization are performed, and the following processing results are obtained. "I", "this", "project", "progress", "delay", "reason", "resource", "lack", "think", "especially", "development team", "member", "lack", "problem". Similarly, tokenization and normalization are performed on the speech content data of person B and person C. Further, the speech frequency calculation unit 12C calculates the speech frequency Z of each participant from the data after tokenization and normalization (step S3C). As an example, the speech frequency Z of each participant may be calculated by the following formula (2) using the existing method TF-IDF for calculating the importance of words appearing in a document. Speech frequency Z = sum of TF-IDF of each word / number of words (2) The TF-IDF of each word can be calculated by an existing technique described, for example, on the website https: / / www.sejuku.net / blog / 26420. By the above formula (2), the speech frequencies of person A, person B, and person C are calculated respectively.

[0031] The three calculated scores are passed to the determination unit 13, and the determination unit 13 calculates the comprehensive score for each participant based on the three scores and the weights predetermined for each score (step S4). Explaining using the data example shown in FIG. 4, as the comprehensive score of person A, - The degree of progress blocker of person A "10" × weight W Ｘ "4" - The degree of expert of person A "30" × weight W Ｙ "5" - The speech frequency of person A "70" × weight W Ｚ "3" The comprehensive score "400" is calculated as the sum of the products of these three. Similarly, for person B and person C, the comprehensive scores "685" and "395" are calculated respectively.

[0032] Next, the determination unit 13 determines the characteristics of each participant based on the calculated three scores and the threshold values predetermined for each score (step S5). In the data example shown in FIG. 4, - For person A, the degree of disruption "10" < threshold value t Ｘ "90". - For person A, the degree of expertise "30" < threshold value t Ｙ "80". - For person A, the degree of speech "70" > threshold value t Ｚ "40". Thus, person A is neither a disruptor nor an expert, and since the degree of speech is higher than the threshold value t Ｚ , it is determined that person A is not a "non - speaker", and the determination result is "no characteristic".

[0033] Regarding person B, - For person B, the degree of disruption "5" < threshold value t Ｘ "90". - For person B, the degree of expertise "85" > threshold value t Ｙ "80". - For person B, the degree of speech "80" > threshold value t Ｚ "40". Thus, person B is not a disruptor, but since the degree of expertise is higher than the threshold value t Ｙ , person B is determined to be an "expert", and since the degree of speech is higher than the threshold value t Ｚ , it is determined that person B is not a "non - speaker", and the determination result is "expert".

[0034] Regarding person C, - For person C, the degree of disruption "80" < threshold value t Ｘ "90". - For person C, the degree of expertise "3" < threshold value t Ｙ "80". - For person C, the degree of speech "20" < threshold value t Ｚ "40". Thus, person C is neither a disruptor nor an expert, but since the degree of speech is lower than the threshold value t Ｚ , person C is determined to be a "non - speaker", and the determination result is "non - speaker".

[0035] Next, the determination unit 13 determines, based on the calculated overall score for each participant, the participant with the highest overall score as the single participant to speak at that timing (step S6). As described in the right column of FIG. 4, since the participant with the highest overall score is person B, the single participant to speak next is determined to be person B.

[0036] Then, based on the characteristics determined for the above-mentioned one participant, the determination unit 13 determines the content of the question to the one participant as follows, for example (step S7). - When the characteristic of the one participant is "obstructor", ask questions to dig deeper into the opinions and ideas that have emerged from the previous discussions. - When the characteristic of the one participant is "expert", ask questions to encourage digging deeper into the issues based on their own experience or presenting new perspectives. - When the characteristic of the one participant is "non-speaker", ask questions to confirm whether there are any points that the participant has not noticed based on the opinions of others. - When the one participant has "no characteristic", instead of asking questions with specific characteristics, present a perspective or share an example for comment.

[0037] In the example of FIG. 4, the next participant to speak is determined to be Mr. B, and since the characteristic of Mr. B is "expert", the determination unit 13 determines the content of the question to Mr. B as something like "Based on your experience, Mr. B, etc., are there any points you feel are issues from the perspective of 〇〇?" This content of the question is to ask a question taking into account that Mr. B is an expert and is intended to be used to discover and dig deeper into the issues.

[0038] Returning to FIG. 2, in the next step S8, the output unit 14 outputs the facilitation content determined by the determination unit 13. As a result, the user of the information processing apparatus 10 can recognize the determined facilitation content.

[0039] According to the embodiment described above, facilitation can be automatically executed according to the characteristics of each participant, and a good meeting can proceed efficiently. For example, - Ask experts for unique ideas based on their experience and knowledge as needed. - Ensure smooth progress by restricting the speaking opportunities of participants determined to be obstructors. - Improve the satisfaction of all participants by ensuring that the speaking volume of each participant reaches a predetermined level or more. Thus, more appropriate facilitation according to the characteristics of each participant can be executed.

[0040] It should be noted that the information processing device 10 is not limited to the configuration shown in Figure 1, and other configurations can also be adopted. For example, the information processing device 10S shown in Figure 5 may have a configuration that does not include the acquisition unit 11 shown in Figure 1. In this case, the information processing device 10S can achieve the same functions as the embodiment described above and obtain the same effects by acquiring speech content data for each participant from an external server 20 equipped with the functional parts of the acquisition unit 11 (speech acquisition unit 20A, speech recognition unit 20B) shown in Figure 1.

[0041] Furthermore, in the above embodiment, an example was shown in steps S3A to S3C of Figure 2 in which three scores X, Y, and Z are calculated. However, it is not essential to calculate all three scores. At least one of the three scores may be calculated, and the obtained score may be used as information to determine the characteristics of each participant.

[0042] The gist of this disclosure is found in the following [1] to [7].

[0043] [1] An information processing device comprising: a calculation unit that calculates a score for determining the characteristics of each participant based on speech content data showing the content of each participant's statements in a discussion; and a determination unit that determines the content of facilitation based on the characteristics of each participant based on the score calculated by the calculation unit.

[0044] [2] The information processing apparatus according to [1], wherein the calculation unit calculates a score relating to at least one viewpoint.

[0045] [3] The information processing device according to [2], wherein the score includes at least one of the following: a degree of disruption, which is the degree to which a person is a disruptor, who repeatedly makes remarks that hinder the progress of the discussion; a degree of expertise, which is the degree to which a person is an expert in a field related to the discussion; or a degree of contribution, which is a score of the amount of contributions made in the discussion.

[0046] [4] The information processing apparatus according to [2] or [3], wherein the decision unit calculates a total score for each participant based on the calculated score for at least one viewpoint and a predetermined weight for each score, and determines one participant to speak based on the calculated total score for each participant.

[0047] [5] The information processing apparatus according to [4], wherein the determination unit determines the characteristics of each participant based on the calculated score for at least one viewpoint and a predetermined threshold for each score, and determines the content of a question to be asked of a participant based on the characteristics determined for that participant.

[0048] [6] An information processing device according to any one of [1] to [5], further comprising: an acquisition unit that acquires data on the content of each participant's statements from the audio data of the discussion; and an output unit that outputs the content of the facilitation determined by the determination unit.

[0049] [7] An information processing method comprising: an information processing device calculating a score for determining the characteristics of each participant based on speech content data showing the content of each participant's speech in a discussion; and an information processing device determining the content of facilitation based on the characteristics of each participant based on the calculated score.

[0050] [Explanation of terms, explanation of hardware configuration (Figure 6), etc.] The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired, wireless, etc.). A functional block may be realized by combining the above one device or the above multiple devices with software.

[0051] Functions include, but are not limited to, judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. As mentioned above, the method of implementation is not particularly limited.

[0052] For example, the information processing device in one embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure. Figure 6 is a diagram showing an example of the hardware configuration of the information processing device 10 according to one embodiment of the present disclosure. The information processing device 10 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0053] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the information processing device 10 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.

[0054] Each function in the information processing device 10 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003.

[0055] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control units, arithmetic units, registers, etc.

[0056] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. Although it has been explained that the various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0057] The memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may also be called a register, cache, main memory, etc. The memory 1002 can store executable programs (program code), software modules, etc., for carrying out a wireless communication method according to one embodiment of the present disclosure.

[0058] The storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of the memory 1002 and the storage 1003.

[0059] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include, for example, a high-frequency switch, duplexer, filter, frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0060] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0061] Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0062] Furthermore, the information processing device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0063] The notification of information is not limited to the embodiments described herein and may be carried out by other means. For example, the notification of information may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.

[0064] Each aspect / embodiment described in this disclosure refers to LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (xG (where x is, for example, an integer or decimal)), FRA (Future Radio Access), NR (new Radio), New radio access (NX), Future generation radio access (FX), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, may apply to at least one system utilizing UWB (Ultra-WideBand), Bluetooth®, or other appropriate systems, and to next-generation systems extended, modified, generated, or defined based thereon. Alternatively, multiple systems may be applied in combination (e.g., a combination of at least one of LTE and LTE-A with 5G).

[0065] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements using exemplary order and are not limited to the specific order presented.

[0066] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0067] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0068] Each aspect / embodiment described in this disclosure may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0069] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0070] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0071] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technology (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0072] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0073] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc.

[0074] The terms “system” and “network” as used in this disclosure are interchangeable.

[0075] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information. For example, wireless resources may be indicated by an index.

[0076] The names used for the parameters described above are not restrictive in any way. Furthermore, the formulas and other expressions using these parameters may differ from those expressly disclosed in this disclosure. Various channels (e.g., PUCCH, PDCCH, etc.) and information elements can be identified by any suitable name, and therefore, the various names assigned to these various channels and information elements are not restrictive in any way.

[0077] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0078] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0079] Any reference to elements using the designations “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the first and second elements do not imply that only two elements may be employed, or that the first element must precede the second element in any way.

[0080] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0081] In this disclosure, if articles are added through translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0082] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different."

[0083] 10, 10S... Information processing device, 11... Acquisition unit, 11A, 20A... Voice acquisition unit, 11B, 20B... Voice recognition unit, 12... Calculation unit, 12A... Obstruction degree calculation unit, 12B... Expert degree calculation unit, 12C... Speaking degree calculation unit, 13... Decision unit, 14... Output unit, 20... External server, 1001... Processor, 1002... Memory, 1003... Storage, 1004... Communication device, 1005... Input device, 1006... Output device, 1007... Bus.

Claims

1. An information processing device comprising: a calculation unit that calculates a score for determining the characteristics of each participant based on statement content data showing the content of each participant's statements in a discussion; and a determination unit that determines the content of facilitation based on the characteristics of each participant based on the score calculated by the calculation unit.

2. The information processing apparatus according to claim 1, wherein the calculation unit calculates a score relating to at least one viewpoint.

3. The information processing device according to claim 2, wherein the score includes at least one of the following: a degree of disruption, which is the degree to which a person is a disruptor, who repeatedly makes remarks that hinder the progress of the discussion; a degree of expertise, which is the degree to which a person is an expert in a field related to the discussion; or a degree of contribution, which is a score representing the amount of contributions made in the discussion.

4. The information processing apparatus according to claim 2, wherein the decision unit calculates a total score for each participant based on the calculated score for at least one viewpoint and a predetermined weight for each score, and determines which participant will speak based on the calculated total score for each participant.

5. The information processing apparatus according to claim 4, wherein the determination unit determines the characteristics of each participant based on the calculated score for at least one viewpoint and a predetermined threshold for each score, and determines the content of a question to be asked of a participant based on the characteristics determined for that participant.

6. The information processing apparatus according to claim 1, further comprising: an acquisition unit that acquires data on the content of each participant's statements from the audio data of the discussion; and an output unit that outputs the content of the facilitation determined by the determination unit.

7. An information processing method comprising: a step of an information processing device calculating a score for determining the characteristics of each participant based on speech content data showing the content of each participant's statements in a discussion; and a step of the information processing device determining the content of facilitation based on the characteristics of each participant based on the calculated score.

Images