Information processing system, program, and information processing method

Abstract

Provides summary information that makes it easier to understand what is being said. [Solution] An acquisition unit 101 acquires user speech information, and a dialogue unit 102 inputs the speech information into a generation model together with a prompt including a summary generation request for generating summary information including partial summary information of the speech information of the processing interval each time speech information of a specified processing interval is obtained, and an editing request for editing already generated summary information based on the newly obtained partial summary information of the processing interval, thereby acquiring first summary information including partial summary information of a first processing interval, and after acquiring the first summary information, acquiring second summary information including the partial summary information of the first processing interval and partial summary information of a second processing interval subsequent to the first processing interval, and the second summary information includes the partial summary information of the first processing interval edited based on the partial summary information of the second processing interval.

Description

[Technical field]

[0001] The present invention relates to an information processing system, a program, and an information processing method. [Background technology]

[0002] Conventionally, there is known a technology for automatically generating minutes of a meeting. Patent Document 1 discloses a system that detects a change in agenda based on auxiliary information of display data and creates agenda information for each agenda. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2015-232769 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is a demand for providing summary information that makes it easier to understand the contents of an utterance.

[0005] The present invention has been made in consideration of the above points, and has an object to provide an information processing system, a program, and an information processing method that are capable of presenting summary information that makes the content of an utterance easy to understand. [Means for solving the problem]

[0006] The information processing system of the present invention is an information processing system including an acquisition unit and a dialogue unit, The acquisition unit acquires user utterance information, the dialogue unit includes a summary generation request for generating summary information including partial summary information of the utterance information of a predetermined processing interval each time utterance information of the predetermined processing interval is obtained, and inputs the utterance information to a generation model together with a prompt including an editing request for editing already generated summary information based on the newly obtained partial summary information of the processing interval to obtain first summary information including the partial summary information of a first processing interval, and obtains second summary information including the partial summary information of the first processing interval and partial summary information of a second processing interval subsequent to the first processing interval after obtaining the first summary information; The partial summary information of the first processing section included in the second summary information is edited based on the partial summary information of the second processing section.

[0007] The information processing system of the present invention comprises: the prompt includes the edit request to modify the generated summary information based on the newly generated partial summary information; The second summary information may include partial summary information of the first processing section that has been changed based on partial summary information of the second processing section.

[0008] The information processing system of the present invention comprises: the prompt includes the edit request to delete the generated partial summary information based on the newly generated partial summary information; The second summary information may not include partial summary information of the first processing section.

[0009] The information processing system of the present invention comprises: the prompt includes a request to include, in the summary information, information indicating that the partial summary information has been deleted, when the partial summary information has been deleted; The second summary information may include information indicating that the partial summary information of the first processing section has been deleted.

[0010] The information processing system of the present invention comprises: When a user instructs display of the deleted partial summary information in the second summary information, the dialogue unit may obtain the deleted partial summary information of the first processing section by inputting a prompt including a request to add the deleted partial summary information to the generative model.

[0011] The information processing system of the present invention comprises: the prompt includes the edit request not to add the newly generated partial summary information to the summary information if the newly generated partial summary information has a different content from the previously generated summary information; If the content of partial summary information of a third processing interval that follows the second processing interval is different from the content of the second summary information, the third summary information generated after the second summary information may not include the partial summary information of the third processing interval.

[0012] The information processing system of the present invention comprises: the prompt includes the edit request to integrate newly generated partial summary information with previously generated partial summary information; In the second summary information, the partial summary information of the second processing section and the partial summary information of the first processing section may be integrated.

[0013] The information processing system of the present invention comprises: the prompt includes an edit request to integrate the newly generated partial summary information with the previously generated partial summary information if the newly generated partial summary information and the previously generated partial summary information are related in content; When the content of the partial summary information generated for the second processing interval is related to the content of the partial summary information of the first processing interval, the partial summary information of the second processing interval and the partial summary information of the first processing interval may be integrated in the second summary information.

[0014] The information processing system of the present invention comprises: the prompt includes a character limit for the summary information; The second summary information may be generated according to the character limit.

[0015] The information processing system of the present invention comprises: A display unit is further provided. the prompt includes a question generation request for generating a question to request a speaker to add missing information when information for the generation of the summary information is missing from the generation model; and The dialogue unit acquires the question sentence when the question sentence is generated, The presenting unit may present the question to a user.

[0016] The information processing system of the present invention comprises: the prompt includes a request to add a timestamp to the summary information, the timestamp indicating an utterance timing corresponding to the summary information; The partial summary information may be provided with a time stamp.

[0017] The program of the present invention comprises: A program for causing a computer to function as an acquisition unit and an interaction unit, The acquisition unit acquires user utterance information, the dialogue unit includes a summary generation request for generating summary information including partial summary information of the utterance information of a predetermined processing interval each time utterance information of the predetermined processing interval is obtained, and inputs the utterance information to a generation model together with a prompt including an editing request for editing already generated summary information based on the newly obtained partial summary information of the processing interval to obtain first summary information including the partial summary information of a first processing interval, and obtains second summary information including the partial summary information of the first processing interval and partial summary information of a second processing interval subsequent to the first processing interval after obtaining the first summary information; The partial summary information of the first processing section included in the second summary information is edited based on the partial summary information of the second processing section.

[0018] The information processing method of the present invention comprises the steps of: An information processing method performed by a computer having a control unit, The control unit acquires user utterance information; a step of the control unit acquiring first summary information including the partial summary information of a first processing interval by inputting the speech information to a generative model together with a prompt including a summary generation request for generating summary information including partial summary information of the speech information of the processing interval each time speech information of a predetermined processing interval is acquired, and an editing request for editing already generated summary information based on the newly acquired partial summary information of the processing interval, and acquiring second summary information including the partial summary information of the first processing interval and partial summary information of a second processing interval subsequent to the first processing interval after acquiring the first summary information; Including, The partial summary information of the first processing section included in the second summary information is edited based on the partial summary information of the second processing section. Effect of the Invention

[0019] According to the information processing system, the program, and the information processing method of the present invention, it is possible to present summary information that makes the spoken content easy to understand. [Brief description of the drawings]

[0020] [Figure 1] 1 is an overall configuration diagram of a summary generation system. [Diagram 2] 13 is a flowchart showing the process of the summary generating device. [Figure 3A] FIG. 11 is a diagram illustrating an example of summary information. [Figure 3B] FIG. 11 is a diagram illustrating an example of summary information. [Figure 3C] FIG. 11 is a diagram illustrating an example of summary information.

[0021] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0022] 1 is a diagram showing the overall configuration of an information processing system 1 according to this embodiment. The information processing system 1 generates summary information for input speech information using a generative model. For example, the information processing system 1 generates a summary of the contents from speech information of a speaker at a lecture or speech information of a lecturer at a lecture, or generates minutes from speech information of participants at a conference. The speech information may be voice data or text data.

[0023] The information processing system 1 includes an information processing device 10, a generative model server device 20, and a user device 30. The information processing device 10 is an example of an information processing system. The information processing device 10, the generative model server device 20, and the user device 30 are connected to each other so as to be able to communicate with each other via a communication network 2 such as the Internet.

[0024] The information processing device 10 is a computer or the like, and acquires summary information from utterance information by utilizing a dialogue with a generative model 210 stored in a generative model server device 20, and presents the summary information. The information processing device 10 is configured with a computer or the like, and includes a control unit 100, a storage unit 110, and a communication unit 120.

[0025] The control unit 100 includes a processor such as a CPU (Central Processing Unit) and controls the operation of the information processing device 10. The storage unit 110 includes, for example, a hard disk drive (HDD), a random access memory (RAM), a read only memory (ROM), and a solid state drive (SSD). The storage unit 110 is not limited to being built into the information processing device 10, and may be a storage medium (for example, a USB memory) that is detachably attached to the information processing device 10. In this embodiment, the storage unit 110 stores various programs executed by the control unit 100 and various data.

[0026] The communication unit 120 includes a communication interface for wirelessly or wired communication with an external device. The control unit 100 transmits and receives data to and from the generative model server device 20 and the user device 30 via the communication unit 120.

[0027] The generation model server device 20 is a computer or the like. The generation model server device 20 stores a generation model 210 in which a question sentence (prompt) is input and an answer sentence is output. The generation model 210 is a learning model generated by machine learning, and generates an answer sentence according to the prompt. The generation model may be a Generative Pre-trained Transformer or a language model based thereon. Examples of the generation model 210 include ChatGPT, GPT-3, GPT-4 by OpenAI, and GPT-J by EleutherAI.

[0028] The generative model server device 20 is used for large-scale natural language processing tasks, for example, automatically performing machine translation, sentence generation, document classification, question answering, and the like. The generative model 210 learns a huge amount of data and then makes predictions for new inputs. The generative model server device 20 hosts the generative model 210, calls the generative model 210 in response to a request, and returns the results. When the generative model server device 20 according to this embodiment receives a prompt from the information processing device 10, it performs calculation processing to generate an answer sentence. The generated answer sentence is then transmitted to the information processing device 10.

[0029] The user device 30 is an information processing device. The user device 30 may also be a portable device such as a smartphone, a PC, or a tablet. The user device 30 includes a control unit 310, a storage unit 320, a communication unit 330, an operation unit 340, and a display unit 350. The control unit 310, the storage unit 320, and the communication unit 330 are the same as the control unit 100, the storage unit 110, and the communication unit 120 of the information processing device 10, respectively. The communication unit 330 includes a communication interface that communicates with an external device wirelessly or via a wire. The operation unit 340 accepts user operations. Examples of the operation unit 340 include a keyboard and a mouse. The display unit 350 is, for example, a monitor, and displays various screens. The operation unit 340 and the display unit 350 may be integrated as a touch panel.

[0030] In this embodiment, it is assumed that an application for generating a summary is installed in the user device 30. It is assumed that information is transmitted and received to and from the information processing device 10 by this application.

[0031] Next, a configuration of the control unit 100 of the information processing device 10 will be described. The control unit 100 functions as an acquisition unit 101, a dialogue unit 102, and a presentation unit 103 by executing a program stored in the storage unit 110. Note that, in the following, the processes described as being performed by the acquisition unit 101, the dialogue unit 102, and the presentation unit 103 are processes performed by the control unit 100 by executing the program.

[0032] The acquiring unit 101 acquires speech information from which a summary is to be generated from the user device 30 via the communication unit 120 .

[0033] The dialogue unit 102 transmits a prompt to the generative model server device 20 via the communication unit 120, thereby acquiring an answer sentence obtained by the generative model 210 from the generative model server device 20. The dialogue unit 102 transmits, for example, a prompt requesting generation of a summary of the utterance information together with the utterance information. As a result, the dialogue unit 102 acquires summary information corresponding to the utterance information.

[0034] Specifically, the dialogue unit 102 sequentially inputs utterance information generated in real time, for example, while a conference is being held, to the generative model 210. The dialogue unit 102 then causes the generative model 210 to sequentially generate summary information for the utterance information obtained in a predetermined processing interval. Herein, the processing interval is a fixed period, for example, two minutes. It is assumed that the processing interval is variable and can be set by the user. Hereinafter, summary information corresponding to the processing interval is referred to as partial summary information. Then, when partial summary information for each of the multiple processing intervals is obtained, information summarizing these is generated as summary information in the generative model 210. Herein, the summary information is summary information for the entire processing interval obtained so far (the multiple processing intervals if multiple processing intervals have been obtained).

[0035] For example, when four minutes have passed since the start of the conference, partial summary information corresponding to two processing intervals is generated, and one piece of summary information is generated based on these. Then, when six minutes have passed since the start of the conference, partial summary information corresponding to a third processing interval is further generated, and summary information from the start of the conference to six minutes is generated based on the summary information already generated for the two processing intervals and the newly generated partial summary information. In other words, the summary information is updated every two minutes.

[0036] The presentation unit 103 presents the summary information obtained by the generative model 210 to the user. Specifically, the presentation unit 103 transmits the summary information to the user device 30 via the communication unit 120, and causes the display unit 350 to display the summary information. As another example, the user device 30 may include a speaker, and the presentation unit 103 may output audio data of the summary information from the speaker.

[0037] 2 is a flowchart showing processing by the information processing device 10. Here, an example will be described in which minutes (summary information) of a meeting held by multiple people are presented. Before the start of the meeting, the dialogue unit 102 transmits a prompt to the generative model server device 20 (step S100). The prompt transmitted to the generative model server device 20 is input to the generative model 210. Here, the prompt transmitted by the dialogue unit 102 will be described.

[0038] The prompt includes a summary generation request. The summary generation request includes a summary generation request for generating partial summary information of the utterance information of the processing section each time utterance information of the processing section is obtained. The summary generation request also includes a request for generating new summary information based on the already obtained summary information and the newly obtained partial summary information when new partial summary information of the processing section is obtained. Furthermore, the summary generation request includes information limiting the number of characters of the summary information.

[0039] The prompt also includes an editing request. The editing request is a request to edit already generated summary information. The editing request includes a request to change the already generated summary information based on the newly generated partial summary information. The editing request also includes a request to not add the newly generated partial summary information to the summary information if the content of the newly generated partial summary information differs from the content of the already generated summary information. The editing request also includes a request to integrate the newly generated partial summary information with the already generated partial summary information. More specifically, the editing request includes a request to integrate the newly generated partial summary information with the already generated partial summary information if the content of the newly generated partial summary information is related to that of the already generated partial summary information.

[0040] The prompt also includes a presentation request, which includes a request that if the partial summary information is deleted, the summary information include information indicating that the partial summary information has been deleted.

[0041] The prompt also includes a request to generate a question sentence, which includes a request to generate a question sentence that requests the speaker to add missing information when information for the generation model 210 to generate summary information is insufficient.

[0042] Examples of cases where information is insufficient include discrepancies in recognition between multiple speakers, inconsistencies in the content of speech information, and ambiguous expressions.

[0043] The prompt also includes a request to add a timestamp to the summary information. The timestamp may be information indicating the time when the utterance information was obtained or may be information indicating the elapsed time since the start of recording of the utterance information.

[0044] Furthermore, the prompt includes a reference request. The reference request includes a request to refer to background information for the speech information to be input. The background information may be related summary information or information input by the user in advance. The related summary information may be summary information generated in a past meeting that was held for the same agenda as the target meeting. The background information includes the agenda of the target meeting, the number of participants, attributes, etc.

[0045] After transmitting the prompt, or together with the prompt, the dialogue unit 102 transmits premise information to the generative model server device 20 (step S102). The prompt and premise information are input to the generative model 210. Next, when the conference starts and recording of utterance information begins, the dialogue unit 102 sequentially acquires utterance information from the user device 30 in real time and transmits this sequentially to the generative model server device 20 (step S104).

[0046] The generative model 210 sequentially receives the speech information, generates partial summary information for each processing section in response to the prompt, and generates summary information based on the partial summary information. The summary information is transmitted from the generative model server device 20 to the information processing device 10.

[0047] When the dialogue unit 102 receives the summary information (Y in step S106), the presentation unit 103 presents the summary information to the user (step S108). Specifically, the presentation unit 103 causes the display unit 350 of the user device 30 to display the summary information. Next, the control unit 100 checks whether acquisition of the utterance information has been completed (step S110). If acquisition of the utterance information has not been completed (N in step S110), the control unit 100 advances the process to step S106. If acquisition of the utterance information has been completed (Y in step S110), the control unit 100 terminates the process.

[0048] Figures 3A, 3B, and 3C are diagrams showing examples of summary information. Figure 3A is a diagram showing an example of summary information obtained in the first processing section. Here, the processing section is assumed to be two minutes long.

[0049] The summary information shown in FIG. 3A is the summary information generated from the speech information of the first processing section. The summary information of the first processing section is equal to the partial summary information of the first processing section. The summary information of the first processing section includes four items of "main items" (item 1-1) to (item 1-4), and also includes detailed content for each item. This information is the partial summary information of the first processing section generated in response to a summary generation request included in the prompt. In addition, in the generation of the partial summary information of the first processing section, the premise information is referenced in response to a reference request. In response to the fact that the number, attributes, and names of the participants are clear in the premise information, the names of the participants and the like are described in the summary information of the first processing section, as shown in FIG. 3A. In this way, although the amount of information in the speech information is small in the first processing section, the premise information is referenced, and therefore summary information supplementing the content of the speech information is generated.

[0050] Furthermore, in response to a request for time stamping, a time stamp is added to each main item. For example, a time stamp of "0 minutes 40 seconds after start" is added to (item 1-1). Since a time stamp is added in this way, the user can check the corresponding speech information by relying on the time stamp.

[0051] In the summary information shown in FIG. 3A, a question to a conference participant (speaker) is included in the "Question" item in response to a question generation request. For example, (Question 1-1) is a question to clarify an ambiguous expression. Also, (Question 1-2) is a question to clarify an unclear content.

[0052] In this way, when the utterance information contains ambiguous or unclear contents, a question for confirming these contents is included in the summary information. The question included in the summary information may be a question that requests the speaker to add the missing information when the information for the generative model 210 to generate partial summary information is insufficient, and the specific content is not limited to that of the embodiment.

[0053] As another example, suppose that speaker A says that he failed to synthesize compound X, and speaker B says that he succeeded in synthesizing compound X. In this case, a question such as "Did you succeed in synthesizing compound X?" is generated. In this way, when there is a discrepancy or contradiction in the contents of the spoken information, a question may be generated to resolve the discrepancy or contradiction.

[0054] It should be noted that the presentation of the question is not limited to being displayed on the display unit 350. As another example, if the user device 30 is equipped with a speaker, the question may be output as voice from the speaker.

[0055] Fig. 3B is a diagram showing an example of summary information corresponding to a second processing interval following the first processing interval. In Fig. 3B, the parts that have been changed or added from the summary information of the first processing interval shown in Fig. 3A are underlined. In response to a summary generation request, the summary information of the second processing interval is generated based on the summary information of the first processing interval and partial summary information of the second processing interval.

[0056] In the "Summary" section, the following content has been added: "It was shared that a good yield (85%) had been achieved. However, Mr. Sato asked a question about the status of separation and purification, to which Mr. Yamada reserved his answer." Furthermore, in the "Major Items" section, "(Item 2-1) Status of separation and purification" has been newly added to the summary information. These correspond to the partial summary information of the second processing section.

[0057] For example, if new summary information were to be generated from the speech information of a processing section obtained up to now, including the new processing section, each time speech information of a new processing section was obtained, a large discrepancy in content could occur between the summary information obtained each time a processing section was added. In contrast, in the information processing system 1 of this embodiment, new summary information is generated based on summary information that has already been generated and newly generated partial summary information. This makes it possible to prevent a large discrepancy in content from occurring between the summary information generated up to now and the newly generated summary information.

[0058] Furthermore, when an answer is given to a question shown in the summary information of the first processing section in a meeting in the second processing section, it is marked as "resolved" as in (Question 1-1) of "Question" shown in Fig. 3B. Furthermore, the resolved content is also reflected in "Summary", "Main Items", and "Details".

[0059] In this way, the summary information is updated every two minutes, and the participants in the meeting can check the content of the questions as appropriate during the meeting. Therefore, the meeting can proceed while clarifying any unclear points.

[0060] The summary information shown in Fig. 3C is an example of the summary information corresponding to the ninth processing interval. In Fig. 3C, the parts that have been changed or added from the summary information of the second processing interval shown in Fig. 3B are underlined. Also, the parts that have been deleted from the summary information of the second processing interval are struck through.

[0061] In the summary information of the ninth processing section, (item 1-3) of the "main items" included in the summary generation request has been deleted, and (item 4-1), (item 5-1), and (item 6-1) have been newly added. The longer the utterance information, the greater the amount of information in the summary information. However, the amount of information is limited according to the limit on the number of characters entered as the prompt. In response to this, partial summary information included in the summary information may be deleted as appropriate.

[0062] Also, in (item 6-1), the time stamps "9 minutes 19 seconds after start" and "17 minutes 34 seconds after start" are added. This indicates that the partial summary information generated in response to the speech information "17 minutes 34 seconds after start" is integrated with (item 6-1) "Technical study of reaction temperature management", which is the partial summary information generated in response to the speech information "9 minutes 19 seconds after start". In this case, for example, the "Details" column may include the contents corresponding to the speech information "9 minutes 19 seconds after start" and the contents corresponding to the speech information "17 minutes 34 seconds after start".

[0063] In this way, unnecessary information is deleted or integrated in the summary information, which makes it possible to prevent the summary information from becoming too long. Note that two pieces of partial summary information may be integrated only when the contents of both pieces of partial summary information are related to each other. This makes it possible to obtain summary information that is easier to read.

[0064] The partial summary information may be edited in response to an editing request. For example, the partial summary information obtained in a certain processing section P may be changed in response to the partial summary information obtained in a processing section Q subsequent to the processing section P. More specifically, assume that the partial summary information "yield 80%" is obtained in a certain processing section P. In contrast, if speech information "the yield was 70%, not 80%" is obtained in a subsequent processing section Q, the partial summary information in the certain processing section P is changed from "yield 80%" to "yield 70%."

[0065] Also, suppose that partial summary information "no yield data was obtained" is obtained in a certain processing section P. In contrast, if speech information "it was a mistake to say that no yield data was obtained; the yield was 80%" is obtained in the subsequent processing section R, the partial summary information "no yield data was obtained" is deleted.

[0066] The prompt editing request may include a request not to add newly generated partial summary information to the summary information if the content of the newly generated partial summary information differs from the content of the previously generated summary information. Correspondingly, for example, if the content of the partial summary information for a certain processing interval T differs from the content of the summary information corresponding to a processing interval S prior to this processing interval T, the partial summary information for processing interval T is not included in the summary information corresponding to this processing interval T. This makes it possible to prevent, for example, topics that deviate from the main topic of the meeting, casual conversation, and the like from being included in the summary information.

[0067] Furthermore, when partial summary information is deleted from the summary information in response to a prompt, the summary information may include information indicating that the partial summary information has been deleted, such as "The contents of ... have been deleted." This allows the user to understand that the partial summary information has been deleted.

[0068] Furthermore, the deleted contents may be redisplayed in response to a request from a user (conference participant). For example, when a conference participant utters "Please display the contents of the deleted ...", the dialogue unit 102 inputs a prompt including a request to add partial summary information of the deleted processing section to the generation model 210. In this case, the generation model 210 adds the partial summary information of the deleted processing section to the summary information of the processing section following the processing section including the utterance "Please display the contents of the deleted ...". In this way, the deleted partial summary information can also be presented to the conference participant in response to the desire of the conference participant. Note that the method of presenting the deleted partial summary information is not limited to the embodiment. As another example, the deleted partial summary information may be displayed on the display unit 350 in the form of a list of deleted contents as information separate from the summary information.

[0069] In addition, the summary information is updated each time a processing section elapses. Therefore, the participants in the conference can check the questions during the conference. Therefore, if an answer to a question is spoken during the conference, the answer can be reflected in the summary information.

[0070] As described above, according to the information processing system 1 of this embodiment, it is possible to present summary information that makes the contents of an utterance easy to understand.

[0071] The above embodiment is one example for carrying out the present invention, and various other embodiments can be adopted. For example, various modifications and changes are possible within the scope of the gist of the present invention described in the claims, such as applying one modified example to another modified example. For example, some of the configurations of the above embodiment may be omitted, and the order of processing may be changed or omitted.

[0072] As a first such modified example, the dialogue unit 102 may present information on time management to the user when the premise information or the opening utterance information includes the scheduled time required for the utterance information of a meeting, etc. For example, when the meeting time is one hour, a guide such as "30 minutes have passed" or "10 minutes left until the scheduled end time" may be presented. Furthermore, when the agenda is known, the dialogue unit 102 may present a guide to assist the progress of the meeting, such as "30 minutes have passed, but no conclusions have been reached on agenda items V and W."

[0073] As a second modified example, the limit on the number of characters in the summary information may be changeable during the conference. For example, there may be a desire to make the number of characters in the summary information longer or shorter depending on the update status of the summary information during the conference. In such a case, the number of characters in the summary information can be changed by inputting a prompt to change the number of characters to the generative model 210 via the dialogue unit 102 during the conference.

[0074] According to the information processing system, the program, and the information processing method of the present embodiment, which are configured as described above, the information processing system is an information processing system 1 including an acquisition unit 101 and a dialogue unit 102, in which the acquisition unit 101 acquires user utterance information, and the dialogue unit 102 inputs the utterance information to the generation model 210 together with a prompt including a summary generation request for generating summary information including partial summary information of the utterance information of the processing interval each time utterance information of a predetermined processing interval is acquired, and an editing request for editing already generated summary information based on the newly acquired partial summary information of the processing interval, thereby acquiring first summary information including partial summary information of a first processing interval, and after acquiring the first summary information, acquiring second summary information including partial summary information of the first processing interval and partial summary information of a second processing interval subsequent to the first processing interval, and the partial summary information of the first processing interval included in the second summary information is edited based on the partial summary information of the second processing interval. In this way, since the partial summary information of the first processing interval has been edited in the second summary information, the utterance content is easy to understand.

[0075] Furthermore, according to the information processing system, program, and information processing method of this embodiment, the prompt includes an editing request to change the generated summary information based on newly generated partial summary information, and the second summary information includes partial summary information of the first processing interval that has been changed based on the partial summary information of the second processing interval. In this way, the partial summary information of the first processing interval has been edited in the second summary information, making it easier to understand the spoken content.

[0076] Furthermore, according to the information processing system, program, and information processing method of this embodiment, the prompt includes an editing request for deleting the generated partial summary information based on the newly generated partial summary information, and the second summary information does not include the partial summary information of the first processing section. In this way, since the second summary information does not include the partial summary information of the first processing section, it is possible to prevent the summary information from becoming redundant.

[0077] Furthermore, according to the information processing system, program, and information processing method of the present embodiment, the prompt includes a request for including, in the summary information, information indicating that the partial summary information has been deleted when the partial summary information has been deleted, and the second summary information includes information indicating that the partial summary information of the first processing section has been deleted, thereby enabling the user to understand that the partial summary information has been deleted.

[0078] Furthermore, according to the information processing system, program, and information processing method of the present embodiment, when a user issues a display instruction for the deleted partial summary information in the second summary information, the dialogue unit inputs a prompt including a request to add the deleted partial summary information to the generative model, thereby acquiring the partial summary information of the deleted first processing interval, thereby making it possible to prevent the summary information from becoming redundant.

[0079] Furthermore, according to the information processing system, program, and information processing method of this embodiment, the prompt includes an editing request for not adding the newly generated partial summary information to the summary information if the content of the newly generated partial summary information differs from the content of the already generated summary information, and if the content of the partial summary information of a third processing interval after the second processing interval differs from the content of the second summary information, the third summary information generated after the second summary information does not include the partial summary information of the third processing interval. This makes it possible to prevent unnecessary information from being included in the summary information.

[0080] Furthermore, according to the information processing system, program, and information processing method of the present embodiment, the prompt includes an editing request for integrating newly generated partial summary information with already generated partial summary information, and in the second minutes information, the partial summary information of the second processing section and the partial summary information of the first processing section are integrated, thereby making it possible to generate summary information that is easier to understand.

[0081] Furthermore, according to the information processing system, program, and information processing method of this embodiment, the prompt includes an editing request for integrating newly generated partial summary information with already generated partial summary information when the contents of the newly generated partial summary information and the already generated partial summary information are related to each other, and when the contents of the partial summary information generated for the second processing interval are related to the contents of the partial summary information of the first processing interval, the partial summary information of the second processing interval and the partial summary information of the first processing interval are integrated in the second summary information. This makes it possible to generate summary information that is easier to understand.

[0082] According to the information processing system, the program, and the information processing method of the present embodiment, the prompt includes a character limit for the summary information, and the second summary information is generated according to the character limit, thereby preventing the summary information from becoming too long.

[0083] Moreover, according to the information processing system, the program, and the information processing method of the present embodiment, a presentation unit is further provided, and the prompt includes a question generation request for generating a question requesting a speaker to add missing information when information for the generative model to generate summary information is insufficient, and when the question is generated, the dialogue unit acquires the question, and the presentation unit presents the question to the user, thereby making it possible to obtain better summary information.

[0084] According to the information processing system, the program, and the information processing method of the present embodiment, the prompt includes a request to add a timestamp to the summary information, which indicates the timing of the speech corresponding to the summary information, and the timestamp is added to the partial summary information, thereby enabling the user to know which part of the speech information the partial summary information corresponds to. [Explanation of symbols]

[0085] 1. Information Processing Systems 10. Information processing device 20 Generative model server device 30 User device 100 Control section 101 Acquisition Department 102 Dialogue Section 103 Presentation section 110 Storage section 120 Communications Department 210 Generative Model 310 Control section 320 Storage section 330 Communications Department 340 Operation section 350 Display section

Claims

1. An information processing system including an acquisition unit and a dialogue unit, The acquisition unit acquires user utterance information, the dialogue unit includes a summary generation request for generating summary information including partial summary information of the utterance information of a predetermined processing interval each time utterance information of the predetermined processing interval is obtained, and inputs the utterance information to a generation model together with a prompt including an editing request for editing already generated summary information based on the newly obtained partial summary information of the processing interval, thereby obtaining first summary information including partial summary information of a first processing interval, and after obtaining the first summary information, obtaining second summary information including the partial summary information of the first processing interval and partial summary information of a second processing interval subsequent to the first processing interval; an information processing system, wherein partial summary information of the first processing section included in the second summary information is edited based on the partial summary information of the second processing section.

2. the prompt includes the edit request to modify the generated summary information based on the newly generated partial summary information; 2 . The information processing system according to claim 1 , wherein the second summary information includes partial summary information of the first processing section that has been changed based on partial summary information of the second processing section.

3. the prompt includes the edit request to delete the generated partial summary information based on the newly generated partial summary information; The information processing system according to claim 1 , wherein the second summary information does not include partial summary information of the first processing section.

4. the prompt includes a request to include, in the summary information, information indicating that the partial summary information has been deleted, when the partial summary information has been deleted; The information processing system according to claim 3 , wherein the second summary information includes information indicating that the partial summary information of the first processing section has been deleted.

5. 4. The information processing system of claim 3, wherein when a user instructs display of the deleted partial summary information in the second summary information, the dialogue unit obtains the partial summary information of the deleted first processing section by inputting a prompt including a request to add the deleted partial summary information to the generation model.

6. the prompt includes the edit request not to add the newly generated partial summary information to the summary information if the newly generated partial summary information has a different content from the previously generated summary information; 2. The information processing system of claim 1, wherein if the content of partial summary information of a third processing section that follows the second processing section is different from the content of the second summary information, the third summary information generated after the second summary information does not include the partial summary information of the third processing section.

7. the prompt includes the edit request to integrate newly generated partial summary information with previously generated partial summary information; The information processing system according to claim 1 , wherein in the second summary information, partial summary information of the second processing section and partial summary information of the first processing section are integrated.

8. the prompt includes a request to integrate the newly generated partial summary information with the previously generated partial summary information if the newly generated partial summary information and the previously generated partial summary information are related in content; 8. An information processing system as described in claim 7, wherein when the content of the partial summary information generated for the second processing section is related to the content of the partial summary information of the first processing section, in the second summary information, the partial summary information of the second processing section and the partial summary information of the first processing section are integrated.

9. the prompt includes a character limit for the summary information; The information processing system according to claim 1 , wherein the second summary information is generated in accordance with the character limit.

10. A display unit is further provided. the prompt includes a question generation request for generating a question to request a speaker to add missing information when information for the generation of the summary information is missing from the generation model; and The dialogue unit acquires the question sentence when the question sentence is generated, The information processing system according to claim 1 , wherein the presenting unit presents the question to a user.

11. the prompt includes a request to add a timestamp to the summary information, the timestamp indicating an utterance timing corresponding to the summary information; 2. The information processing system according to claim 1, wherein a time stamp is added to the partial summary information.

12. A program for causing a computer to function as an acquisition unit and an interaction unit, The acquisition unit acquires user utterance information, the dialogue unit includes a summary generation request for generating summary information including partial summary information of the utterance information of a predetermined processing interval each time utterance information of the predetermined processing interval is obtained, and inputs the utterance information to a generation model together with a prompt including an editing request for editing already generated summary information based on the newly obtained partial summary information of the processing interval, thereby obtaining first summary information including partial summary information of a first processing interval, and after obtaining the first summary information, obtaining second summary information including the partial summary information of the first processing interval and partial summary information of a second processing interval subsequent to the first processing interval; a program in which partial summary information of the first processing section included in the second summary information is edited based on the partial summary information of the second processing section.

13. An information processing method performed by a computer having a control unit, The control unit acquires user utterance information; a step of the control unit acquiring first summary information including the partial summary information of a first processing interval by inputting the speech information to a generation model together with a prompt including a summary generation request for generating summary information including partial summary information of the speech information of the processing interval each time speech information of a predetermined processing interval is acquired, and an editing request for editing already generated summary information based on the newly acquired partial summary information of the processing interval, and acquiring second summary information including the partial summary information of the first processing interval and partial summary information of a second processing interval subsequent to the first processing interval after acquiring the first summary information; Including, An information processing method, wherein partial summary information of the first processing section included in the second summary information is edited based on the partial summary information of the second processing section.

Images