Information processing method, information processing program, and information processing device

Abstract

To provide an information processing method capable of conducting dialogue by using a graph document in which a dialogue content is compactly represented.SOLUTION: An information processing method outputs information for causing a display unit to display a dialogue content with a large language model as an editable graph document in which a document structure is graph-represented. The information processing method is also capable of conducting dialogue using a graph document in which the dialogue content is compactly expressed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing method, an information processing program, and an information processing device, and can be applied to, for example, an interactive system using a graph document. [Background technology]

[0002] In recent years, the performance of dialogue systems has improved with the development of language models, and various technologies have been developed.

[0003] For example, Patent Document 1 discloses a device that uses a language model to interactively search for a document to be searched for, and Patent Document 2 discloses a device that interactively issues instructions to edit a document and modifies the document.

[0004] Incidentally, Non-Patent Document 1, a public document from the Industrial Japanese Language Research Association, states that there are various advantages to using graph documents instead of text documents. A graph document represents a document structure as a graph, where a sentence of granularity is represented as one node, relationships between sentences are connected by edges, and labels that indicate the meaning of the relationships are assigned to the edges, thereby making it possible to represent the structure and meaning of a document. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2023-076413 [Patent Document 2] Japanese Patent Application Publication No. 2023-017938 [Non-patent literature]

[0006] [Non-Patent Document 1] "Industrial Japanese Language Research Association Document Creation Support Subcommittee Public Materials" [Retrieved April 17, 2024], [Online], INTERNET,<URL:https: / / tech-jpn.jp / wp-content / uploads / symposium / 13 / 13-2-2.pdf> Summary of the Invention [Problem to be solved by the invention]

[0007] By using a language model such as that described in Patent Document 1, a dialogue system can create a response sentence that is appropriate to a certain extent in response to an utterance from a user.

[0008] However, because there is a limit to the length of prompts used to create response sentences to be sent to a language model, if the dialogue history to be sent becomes long, it is necessary to delete old dialogue history before sending it. In this case, the content of the deleted dialogue history is not passed to the language model, which results in a dialogue that does not take into account the information in the deleted dialogue history.

[0009] Therefore, there is a demand for an information processing method, an information processing program, and an information processing device that can perform dialogue using a graph document. [Means for solving the problem]

[0010] The information processing method of the first invention is characterized in that it outputs information for displaying the contents of a dialogue with a large-scale language model on a display unit as an editable graph document in which the document structure is graphed.

[0011] The second information processing method of the present invention is characterized in that it outputs information for displaying on a display unit a screen having a field for displaying a dialogue history regarding dialogue content with a large-scale language model, and a field for displaying a graph document that graphs the document structure and shows the dialogue content.

[0012] The information processing method of the third invention is characterized by having a first step of generating a first prompt including information based on a first graphical document in which a document structure is graphed.

[0013] An information processing program according to a fourth aspect of the present invention is characterized in that it causes a computer to execute any one of the information processing methods according to the first to third aspects of the present invention.

[0014] An information processing device according to a fifth aspect of the present invention is characterized by executing the information processing program according to the fourth aspect of the present invention. [Effects of the Invention]

[0015] According to the present invention, interactions can be carried out using graph documents. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a block diagram showing a configuration of a graph document dialogue system according to a first embodiment. [Figure 2] FIG. 2 is an explanatory diagram showing an example of a screen configuration of a graph document dialogue input / output unit according to the first embodiment; [Figure 3] FIG. 3 is an explanatory diagram showing an example of the configuration of a prompt template according to the first embodiment. [Figure 4] FIG. 2 is an explanatory diagram showing an example of a dialogue history according to the first embodiment. [Figure 5] FIG. 2 is an explanatory diagram showing an example of a graph document according to the first embodiment; [Figure 6] 4 is a flowchart showing a characteristic operation of the graph document interactive device (interaction control unit) according to the first embodiment. [Figure 7] 4 is a flowchart showing a characteristic operation of the graph document dialogue input / output unit according to the first embodiment. [Figure 8] FIG. 10 is a block diagram showing the configuration of a graph document dialogue system according to a second embodiment. [Figure 9] FIG. 11 is an explanatory diagram showing an example of the configuration of a prompt template for search according to the second embodiment. [Figure 10] FIG. 10 is an explanatory diagram showing an example of the configuration of a prompt template for a dialogue according to the second embodiment. [Figure 11] 10 is a flowchart showing a characteristic operation of a graph document interactive device (interaction control unit) according to the second embodiment. [Figure 12] 10 is a flowchart showing a characteristic operation of a graph document storage and search unit according to the second embodiment. [Figure 13] FIG. 10 is an explanatory diagram (part 1) showing an example of search results obtained by a search performed by a graph document storage and search unit according to the second embodiment. [Figure 14] FIG. 11 is an explanatory diagram (part 2) showing an example of search results obtained by a search performed by the graph document storage and search unit according to the second embodiment. [Figure 15] FIG. 10 is a block diagram showing the configuration of a graph document dialogue system according to a third embodiment. [Figure 16] 11 is a flowchart showing a characteristic operation of a graph document dialogue input / output unit according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0017] (A) First embodiment Hereinafter, a first embodiment of an information processing method, an information processing program, and an information processing device according to the present invention will be described in detail with reference to the drawings. In the following, an example in which the information processing system of the present invention is applied to a graph document processing system will be shown.

[0018] (A-1) Configuration of the First Embodiment FIG. 1 is a block diagram showing the configuration of a graph document dialogue system according to the first embodiment.

[0019] In FIG. 1, a graph document dialogue system 1 includes a graph document dialogue device 10, a graph document dialogue input / output unit 20 as an external device, and a large-scale language model 30.

[0020] In addition, in the graph document dialogue system 1, the graph document dialogue device 10, the graph document dialogue input / output unit 20, and the large-scale language model 30 can be connected via a network using various communication methods, whether wired or wireless. As a variant, the graph document dialogue device 10 may internally store the large-scale language model 30.

[0021] The graph document dialogue input / output unit 20 is a functional unit that can input user utterances, display user utterances and system utterances, and display and edit graph documents. The graph document dialogue input / output unit 20 can be realized by, for example, a PC, a tablet, a smartphone, etc.

[0022] FIG. 2 is an explanatory diagram showing an example of the screen configuration of the graph document dialogue input / output unit according to the first embodiment.

[0023] In FIG. 2, a graph document interactive input / output screen 200 has a graph document display / edit field 201 and an interactive history display / input field 202 .

[0024] The graph document display / edit field 201 allows the display and editing of the graph document. It is assumed that the graph document can be edited by adding nodes and edges on the screen, but it is also possible to only display the graph document without editing it. The edited graph document can be sent to the graph document interactive device 10 by, for example, pressing the send button 205, or can be sent to the graph document interactive device 10 at any time after editing is complete, but the trigger for sending the graph document is not particularly limited.

[0025] The dialogue display field 203 in the dialogue history display / input field 202 displays the dialogue between the user and the system. The dialogue display format is not particularly limited, but for example, in FIG. 2, a speech bubble from the right indicates a sentence spoken by the user, and a speech bubble from the left indicates a sentence spoken by the system. It is assumed that the dialogue can be input by the user entering any text in the text input field 204 at the bottom and pressing the send button 205.

[0026] The graph document interactive device 10 includes an interaction control unit 11 and a storage unit 12.

[0027] The graph document interactive device according to the embodiment may be configured as hardware, such as a dedicated IC chip equipped with the components shown in FIG. 1, or may be configured as software, centered around a CPU and a program executed by the CPU, but functionally it can be represented as shown in FIG. 1.

[0028] The dialogue control unit 11 is a functional unit that creates a response sentence (system utterance sentence) in cooperation with the large-scale language model 30 described later in response to a user utterance input via the graph document dialogue input / output unit 20, and controls the dialogue with the user.

[0029] The storage unit 12 is a functional unit that stores data used by the dialogue control unit 11, and includes a prompt template 13, a dialogue history 14, and a current graph document 15.

[0030] The prompt template 13 is template data for forming an instruction sentence (prompt) for the large-scale language model 30 to generate a system utterance sentence.

[0031] FIG. 3 is an explanatory diagram illustrating an example of the configuration of a prompt template according to the first embodiment.

[0032] In FIG. 3, the prompt template 13 includes an overall prompt 13-1, a variable portion for each domain 13-2, a detailed prompt 13-3, a current graph document 13-4, and a dialogue history 13-5.

[0033] The general prompt 13-1 and the detailed prompt 13-3 are fixed and preset independently of the domain.

[0034] The general prompt 13-1 contains instructions to have a dialogue while creating a graph document, such as "Please have a dialogue with the user while summarizing the contents of the dialogue with the user in a graph document."

[0035] Detailed prompt 13-3 includes specific graph document formatting and notes. For example, it might say, "A graph document is a set of nodes and labeled directed edges. Choose edge labels from the following: 'Result,' 'Cause,' 'Background,' 'Example,' 'Conclusion,' 'Constraint,' 'Purpose,' and 'Adversity.' The node content should be a single, relatively long sentence."

[0036] The domain-specific variable part 13-2, whose instructions vary depending on the domain, must be determined before execution. For example, "You (large-scale language model 30) are a paper writer. Based on the information about the paper the user wants to write, please ask the user for the information necessary to write the paper. If necessary, please provide appropriate information. " is an instruction like this.

[0037] The current graph document 13-4 and the dialogue history 13-5 are filled with the values ​​of the current graph document 15 and the dialogue history 14 by the dialogue control unit 11 at the time of execution.

[0038] FIG. 4 is an explanatory diagram showing an example of a dialogue history according to the first embodiment. The dialogue history 14 shown in FIG. 4 shows the content displayed in the dialogue display field 203 of FIG. 2 in a predetermined data format. Note that while FIG. 4 shows the dialogue history 14 in JSON format, the data format used is not particularly limited. As the dialogue between the user and the system progresses, the dialogue history 14 becomes longer as dialogue content (user utterances and system utterances) is embedded. In other words, the dialogue history 14 stored in the storage unit 12 is updated as needed by instructions from the dialogue control unit 11.

[0039] Fig. 5 is an explanatory diagram showing an example of a current graph document according to the first embodiment. The current graph document 15 shown in Fig. 5 shows the content displayed in the graph document display / edit field 201 in Fig. 2 in a predetermined data format (JSON format as above).

[0040] As shown in Figure 5, the node details and edge details are listed in "nodes" and "edges," respectively. The format does not have to be exactly like this example, as long as the same content is listed.

[0041] The large-scale language model 30 is assumed to be a generally distributed language model or a language model that can be used via an API (Application Programming Interface), such as a generative AI such as ChatGPT. When a prompt is input, the large-scale language model 30 generates and outputs text data corresponding to the prompt (a system utterance in response to a user utterance, and a graph document in which the dialogue history is structured). Note that, although the first embodiment shows an example in which the large-scale language model 30 handles only text data, as a modified example, it may handle information other than text, such as images and sounds.

[0042] (A-2) Operation of the First Embodiment Next, the operation of the graph document dialogue system 1 according to the first embodiment having the above configuration will be described.

[0043] (A-2-1) Processing of the Graph Document Interactive Device 10 FIG. 6 is a flowchart showing a characteristic operation of the graph document interactive device (interaction control unit) according to the first embodiment.

[0044] <s101> The dialogue control unit 11 acquires a user utterance and a graph document from the graph document dialogue input / output unit 20. Initially, the user utterance sentence and the graph document may be empty. If the user utterance sentence is empty, the system starts with an utterance.

[0045] <S102、S103> The dialogue control unit 11 adds the acquired user utterance to the end of the dialogue history 14. Similarly, the dialogue control unit 11 stores the acquired graph document in the current graph document 15.

[0046] <s104> The dialogue control unit 11 creates a prompt by embedding the current graph document 15 in the place of the current graph document 13-4 in the prompt template 13 and embedding the dialogue history 14 in the place of the dialogue history 13-5.

[0047] <s105> The dialogue control unit 11 transmits the prompt created in step S104 to the large-scale language model 30. In the large-scale language model 30, a graph document and a system utterance are generated based on the prompt.

[0048] <s106> The dialogue control unit 11 acquires the graph document and the system utterance sentence from the large-scale language model 30 .

[0049] <S107、S108> The dialogue control unit 11 stores the graph document acquired in step S106 in the current graph document 15. Similarly, the dialogue control unit 11 adds the acquired system utterance to the end of the dialogue history 14.

[0050] <s109> Then, the dialogue control unit 11 transmits the current graph document 15 and the dialogue history 14 to the graph document dialogue input / output unit 20 .

[0051] After the process of step S109, the process returns to step S101 and repeats the series of processes. After that, the process may be ended at any point by shutting down the system, etc.

[0052] (A-2-2) Processing of the Graph Document Dialogue Input / Output Unit 20 FIG. 7 is a flowchart showing the characteristic operation of the graph document dialogue input / output unit according to the first embodiment.

[0053] <s201> The graph document dialogue input / output unit 20 displays information by creating a graph document display / edit column 201 on the left side of the screen and a dialogue history display / input column 202 on the right side, as shown in the example screen in Figure 2. Initially, both the graph document and the dialogue history are empty.

[0054] <s202> When the user presses the send button 205, the graph document dialogue input / output unit 20 transmits the user utterance (the text entered in the text input field 204) and the graph document to the dialogue control unit 11. In addition, the graph document dialogue input / output unit 20 empties the text input field 204 at the same time as transmitting.

[0055] <s203> Thereafter, the graph document dialogue input / output unit 20 acquires the dialogue history and the graph document from the dialogue control unit 11 .

[0056] <s204> The graph document dialogue input / output unit 20 reflects the acquired dialogue history and graph document in the graph document display / edit field 201 and the dialogue history display / input field 202, and makes it possible to input a user utterance.

[0057] After the process of step S204, the process returns to step S202 and repeats the series of processes. After that, the process may be ended at any point by shutting down the system, etc.

[0058] (A-3) Effects of the First Embodiment The graph document dialogue system 1 allows dialogue using the large-scale language model 30 while displaying and storing dialogue content in the form of a graph document. In other words, at any point in time, the content of the dialogue up to that point is displayed and stored in the form of a graph document, allowing the user to check the outcome of the dialogue. Furthermore, by specifying any node displayed in the graph document and engaging in dialogue with that node, a dialogue can be conducted for that node. In this case, when sending a user utterance to the large-scale language model 30, the ID (or IDs) of the specified node are also added, thereby informing the large-scale language model 30 of the node to be dialogued and clearly indicating that the dialogue is for that node, and appropriate system utterances and graph documents can be obtained.

[0059] For example, suppose a user is having a conversation about a new idea and comes up with a technology necessary to realize that idea. The user can specify the node that describes the technology and have the large-scale language model 30 provide other ideas for this node. The large-scale language model 30 then generates multiple new ideas based on the other nodes connected to the specified node and their relationships, giving the user the effect of brainstorming alone. Similarly, by having the large-scale language model 30 provide the next step for the specified node, the user can achieve the effect of having an expert ask them appropriate, probing questions.

[0060] Furthermore, since there is generally a limit to the length of prompts sent to the large-scale language model 30, if the dialogue history to be sent becomes long, it is necessary to delete old dialogue history before sending it, in which case the content of the deleted dialogue history is not passed to the large-scale language model 30, resulting in a dialogue that does not take into account the information in the deleted dialogue history.In this embodiment, the content of the dialogue is compactly represented in a graph document, so the dialogue takes into account the information in the deleted dialogue history, making it possible to obtain more accurate system utterances.

[0061] In this case, as described in Non-Patent Document 1, a graph document can express the content of a dialogue in a structured form, and is also very well organized. Therefore, the large-scale language model 30 refers not only to the dialogue history but also to the graph document in which the dialogue content is properly organized, and the system makes utterances that are in line with the graph document, which has the effect of enabling a more accurate dialogue that is more focused on the dialogue content.

[0062] Furthermore, the graphical document containing the dialogue content can be converted as needed into presentation materials, documents, specifications, proposals, patent documents, papers, procedure manuals, programs, and other forms of expression required by the user. This allows these to be created by utilizing the knowledge held by the large-scale language model 30 in the dialogue.

[0063] (B) Second embodiment Hereinafter, a second embodiment of an information processing method, an information processing program, and an information processing device according to the present invention will be described in detail with reference to the drawings. In the following, an example in which the information processing system of the present invention is applied to a graph document processing system will be shown.

[0064] (B-1) Configuration of the second embodiment FIG. 8 is a block diagram showing the configuration of a graph document dialogue system according to the second embodiment.

[0065] 8, the graph document interaction system 1A includes a graph document interaction device 10A, the above-mentioned graph document interaction input / output unit 20, and the above-mentioned large-scale language model 30. The following description of the graph document interaction device 10A will focus on the differences from the first embodiment.

[0066] The graph document interaction device 10A includes a graph document storage and search unit 41 in addition to the configuration of the above-mentioned interaction control unit 11 and memory unit 12. The memory unit 12 also stores a graph document group 42 and a search prompt template 43 in addition to a prompt template 13A for interaction, a dialogue history 14, and a current graph document 15.

[0067] The dialogue control unit 11 uses the large-scale language model 30 to create a search query statement for searching for a reference graph document from the graph document group 42 managed by the graph document storage and search unit 41 based on the dialogue content.

[0068] FIG. 9 is an explanatory diagram showing an example of the configuration of a prompt template for search according to the second embodiment.

[0069] In FIG. 9, a prompt template 43 for search includes an overall prompt 43-1, a variable part for each domain 43-2, a current graph document 43-3, and a dialogue history 43-4.

[0070] The overall prompt 43-1 contains instructions to create a search query statement required to search for a reference graph document from the dialogue content. The domain-specific variable part 43-2 contains instructions such as the field and purpose of the dialogue, the contents of which change depending on the domain. The current graph document 43-3 and dialogue history 43-4 are filled with the values ​​of the current graph document 15 and dialogue history 14 by the dialogue control unit 11 at runtime.

[0071] FIG. 10 is an explanatory diagram showing an example of the configuration of a prompt template for a dialogue according to the second embodiment.

[0072] 10, prompt template 13A has search results 13-6 in addition to the components of prompt template 13 described above. Search results obtained by a graph document storage and search unit 41 (described later) are embedded in search results 13-6.

[0073] The graph document group 42 is a plurality of graph documents managed (stored) by the graph document storage and search unit 41 .

[0074] The graph document storage and search unit 41 vectorizes the contents of the graph fragments (such as one node, one node and one edge connected to that node, or two connected nodes and one edge) of each graph document in the graph document group 42 it holds, making them searchable.

[0075] The graph document storage and search unit 41 performs a search in two stages. First, it creates a list of graph documents or graph document fragments with content similar to the search query statement (see Figure 12, which will be described later). Specifically, the graph document storage and search unit 41 uses the vector representation of the character string to perform a vector search using a method such as approximate nearest neighbor search. In addition to converting the text representation of an entire graph document into a vector representation, it also stores vectors of graph document fragments (such as only the content of one node, only the label of the edge connecting the node content, or only the content of two connecting nodes and the labels of their edges) so that searches can be performed using graph document fragments. This results in the vector search results shown in Figure 13.

[0076] Furthermore, based on the vector search results, the graph document storage and search unit 41 also includes in the final search results the nodes connected to the included nodes with specific labels. For example, a final search result such as that shown in FIG. 14 is created, including the nodes connected with labels such as "reference," "overview," and "function." By using this as the final search result, not only the vector search result but also information about the nodes, such as their reference destinations, can be included in the prompt, improving the results returned by the large-scale language model 30. Generally, the large-scale language model 30 tends to generate incorrect content when the prompt does not contain the information necessary to answer. Therefore, by providing sufficient necessary information in the prompt, the results returned by the large-scale language model 30 can be made more accurate.

[0077] (B-2) Operation of the Second Embodiment Next, the operation of the graph document dialogue system 1A according to the second embodiment having the above configuration will be described.

[0078] (B-2-1) Processing of the Graph Document Interactive Device 10A Fig. 11 is a flowchart showing the characteristic operations of the graph document interactive device (interaction control unit) according to the second embodiment. Note that the processes of steps S101 to S103 and steps S105 to S109 in Fig. 11 are the same as those explained in Fig. 6 above, and therefore detailed explanations will be omitted. The following explanation will focus on the processes of steps S301 to S307, which are specific to the second embodiment.

[0079] <s301> After the above-mentioned step S103, the dialogue control unit 11 creates a search prompt by embedding the current graph document 15 in the current graph document 43-3 position of the search prompt template 43 shown in Figure 9, and embedding the dialogue history 14 in the dialogue history 43-4 position.

[0080] <s302> The dialogue control unit 11 transmits the search prompt created in step S301 above to the large-scale language model 30. In the large-scale language model 30, a search query sentence is created based on the search prompt.

[0081] <s303> The dialogue control unit 11 acquires a search query sentence from the large-scale language model 30 .

[0082] <s304> The dialogue control unit 11 sends the acquired search query statement to the graph document storage and search unit 41, causing it to search the graph document group 42.

[0083] <s305> The dialogue control unit 11 acquires the search results shown in FIG.

[0084] <s306> The dialogue control unit 11 creates a dialogue prompt by embedding the current graph document 15 in the current graph document 13-4 position of the dialogue prompt template 13A shown in Figure 10, embedding the dialogue history 14 in the dialogue history 13-5 position, and embedding the search results obtained in the above-mentioned step S305 in the search result 13-6 position.

[0085] <s307> After the above steps S105 to S108, the dialogue control unit 11 transmits the current graph document 15 to the graph document storage and search unit 41, and stores it in the graph document group 42 in the storage unit 12.

[0086] The subsequent processing is the same as that in the first embodiment, and therefore a description thereof will be omitted. Similarly, the processing of the graph document interactive input / output unit 20 is the same as that in the first embodiment, and therefore a description thereof will be omitted.

[0087] (B-2-2) Processing of the graph document storage and search unit 41 FIG. 12 is a flowchart showing the characteristic operation of the graph document storage and search unit according to the second embodiment.

[0088] <s401> The graph document storage and search unit 41 acquires, via the dialogue control unit 11, the search query statement generated by the large-scale language model 30 in step S302 described above.

[0089] <s402> The graph document storage and search unit 41 converts the search query statement into a vector, searches the graph document group 42 in the memory unit 12 for graph fragments with vectors close to the vector of the search query statement, and creates a list of vector search results as shown in Figure 13.

[0090] <s403> The graph document storage and search unit 41 adds to the list the graph fragments connected to the nodes included in the list created in step S103 above by specific labels that should be included in the search results, such as “reference,” “overview,” and “function,” to create a final search result list as shown in FIG. 14, and sends this list to the dialogue control unit 11.

[0091] (B-3) Effects of the Second Embodiment In addition to the effects of the first embodiment, the second embodiment provides the following effects.

[0092] In the graphical document dialogue system 1A, dialogue can be carried out by appropriately using information on other accumulated graphical documents.

[0093] For example, if the accumulated graph documents include terms and conditions for a certain service or internal organizational rules, the user can make inquiries about those terms and conditions or rules. The large-scale language model 30 can generate an answer using graph fragments that have content similar to the content of the question posed by the user. If the clauses of the terms and conditions or rules are stored as nodes in the graph, a vector search can be used to search for clauses with content similar to the question. Furthermore, by including nodes linked with labels such as "reference," "overview," and "function" in the search results, the information necessary for the large-scale language model 30 to generate text can be included in the prompt, thereby preventing the large-scale language model from outputting plausible lies (hallucinations).

[0094] For example, if you are having a conversation to deepen your ideas, you can find out whether anyone else has a similar idea, whether there are other ideas based on similar technology, or whether there are any attempts to apply the same technology in different areas.

[0095] (C) Third embodiment Hereinafter, an information processing method, an information processing program, and an information processing device according to a third embodiment of the present invention will be described in detail with reference to the drawings. In the following, an example in which the information processing system of the present invention is applied to a graph document processing system will be described.

[0096] (C-1) Configuration of the third embodiment FIG. 15 is a block diagram showing the configuration of a graph document dialogue system according to the third embodiment.

[0097] 15, the graph document dialogue system 1B includes the above-mentioned graph document dialogue device 10A, a plurality of graph document dialogue input / output units 20A (20A-1 to 20A-n), and the above-mentioned large-scale language model 30. The following description will focus on the differences between the graph document dialogue input / output unit 20A and the first and second embodiments.

[0098] The third embodiment differs from the first and second embodiments in that it includes a plurality of graph document dialogue input / output units 20A. Each graph document dialogue input / output unit 20A is connected to a graph document dialogue device 10A (dialogue control unit 11).

[0099] Each graph document interactive input / output unit 20A can operate simultaneously, allowing multiple users using them to share a single graph document and interactively create graph documents in cooperation with each other.

[0100] (C-2) Operation of the Third Embodiment Next, the operation of the graph document dialogue system 1B according to the third embodiment having the above configuration will be described. Since the third embodiment is characterized by the operation of the graph document dialogue input / output unit 20A, the following description will mainly focus on the operation of the graph document dialogue input / output unit 20A.

[0101] When a user utterance and a graph document are transmitted from a connected graph document dialogue input / output unit 20A, the graph document dialogue device 10A (dialogue control unit 11) executes the series of processes shown in Fig. 11. When a user utterance and a graph document are transmitted from any of the graph document dialogue input / output units 20A, the graph document dialogue device 10A executes the same processes as above. In other words, the process shown in Fig. 11 is repeated every time a user utterance and a graph document are transmitted from the graph document dialogue input / output unit 20A.

[0102] FIG. 16 is a flowchart showing the characteristic operation of the graph document dialogue input / output unit according to the third embodiment.

[0103] <s501> The graph document dialogue input / output unit 20A displays information by creating a graph document display / edit column 201 on the left side of the screen and a dialogue history display / input column 202 on the right side, as shown in the example screen in Figure 2. Initially, both the graph document and the dialogue history are empty.

[0104] <s502> The graph document dialogue input / output unit 20A waits until the graph document displayed in the graph document display / edit field 201 is modified, or until the graph document and dialogue history are sent from the dialogue control unit 11, or until the send button 205 on the screen is pressed.

[0105] <s503> The graph document interactive input / output unit 20A determines whether the graph document has been modified. If the graph document has been modified, the graph document interactive input / output unit 20A proceeds to step S504, and if the graph document has not been modified, the graph document interactive input / output unit 20A proceeds to step S505.

[0106] <s504> If the graph document dialogue input / output unit 20 determines in the above step S503 that the graph document has been corrected, it transmits the corrected graph document to the dialogue control unit 11, and returns to the above step S502.

[0107] <s505> If the graph document dialogue input / output unit 20A determines in the above-mentioned step S503 that the graph document has not been modified, it determines whether or not the graph document and dialogue history have been transmitted from the dialogue control unit 11. If the graph document and dialogue history have been transmitted, the graph document dialogue input / output unit 20A proceeds to step S506, whereas if the graph document and dialogue history have not been transmitted, it proceeds to step S507.

[0108] <s506> If the graph document dialogue input / output unit 20A determines in the above-mentioned step S505 that the graph document and dialogue history have been transmitted, it reflects the acquired dialogue history and graph document in the graph document display / edit field 201 and the dialogue history display / input field 202, and returns to the above-mentioned step S502.

[0109] <s507> The graph document interactive input / output unit 20A determines whether or not the send button 205 on the screen has been pressed. If the send button 205 has been pressed, the graph document interactive input / output unit 20A proceeds to step S508, and if the send button 205 has not been pressed, the graph document interactive input / output unit 20A returns to the above-mentioned step S502.

[0110] <s508> The graph document dialogue input / output unit 20A transmits the user utterance and the graph document on the screen to the dialogue control unit 11, and empties the text input field 204.

[0111] <s509> The graph document dialogue input / output unit 20A acquires the dialogue history and the graph document from the dialogue control unit 11.

[0112] <s510> The graph document dialogue input / output unit 20A reflects the acquired dialogue history and graph document in the graph document display / edit field 201 and the dialogue history display / input field 202, makes the text input field 204 ready for input, and returns to step S502 described above.

[0113] (C-3) Effects of the Third Embodiment As described above, the third embodiment provides the following advantages in addition to the advantages of the first and second embodiments.

[0114] Multiple users can share one graph document / dialogue via the graph document dialogue input / output unit 20A. This allows multiple users to share an idea, plan, proposal, way of thinking, etc. in the form of a graph document / dialogue, and multiple users can cooperate to create a new dialogue / graph document, enabling them to cooperate in accomplishing things that they could not do alone.

[0115] By sharing graph documents and dialogues, even users who join midway through can view the dialogue history and understand the dialogues and graph document modifications that have been made up to that point, enabling more appropriate dialogue and graph document editing.

[0116] Furthermore, by checking the dialogue and graph document corrections made by the large-scale language model 30 with multiple participating users, it is possible to monitor whether the large-scale language model 30 is outputting anything strange.

[0117] (D) Other embodiments Although various modified embodiments have been mentioned in the above-described embodiments, the following modified embodiments can also be applied.

[0118] (D-1) In the first to third embodiments described above, the input / output devices (graph document dialogue input / output units 20 (20A)) may communicate with each other to share graph contents and dialogue histories. Also, when transmitting graph contents and dialogue histories, only the differences may be transmitted.

[0119] (D-2) In the first to third embodiments described above, the screen for displaying and inputting dialogue may not be necessary. A user utterance in a dialogue may be generated by directly pointing to a part of the graph with a mouse and specifying a request for that part using a pull-down menu or the like. Also, system utterances may be displayed by adding nodes directly to the graph display. This allows a screen to be configured with only a graph display, without a dialogue display portion.

[0120] Conversely, it is also possible to configure the screen so that it only displays and inputs dialogue, without displaying the graph. In this case, the graph is not displayed, but is retained internally but not displayed, and the screen is configured so that only the display and inputs dialogue are allowed. Even in this case, the current graph content is updated internally and the dialogue is based on that. Also, instead of displaying the graph all the time, it can be displayed as needed. It can be displayed when the dialogue has finished, or at the user's request.

[0121] (D-3) In the third embodiment described above, conditions (additional information such as user or organization name, project, access rights, etc.) that further narrow down the graph documents may be added to the search query statement. For example, it may be possible to narrow down the search to only those created by a specific user, to only those belonging to a specific department, to only those belonging to a specific project, or to only those that a specific user may access. [Explanation of symbols]

[0122] 1, 1A, 1B...Graph document dialogue system, 10, 10A...Graph document dialogue device, 11...Dialogue control unit, 12...Memory unit, 13...Prompt template, 13-1...Overall prompt, 13-2...Variable part, 13-3...Detailed prompt, 13-4...Graph document, 13-5...Dialogue history, 13-6...Search results, 13A...Prompt template, 14...Dialogue history, 15...Graph document, 20, 20A...Graph document dialogue input / output unit, 30...Large-scale language model, 41...Search unit, 42...Graph document group, 43...Prompt template, 43-1...Overall prompt, 43-2...Variable part, 43-3...Graph document, 43-4...Dialogue history, 200...Graph document dialogue input / output screen, 201...Edit field, 202...Input field, 203...Dialogue display field, 204...Text input field, 205...Send button.

Claims

1. An information processing method comprising: outputting information for displaying, on a display unit, the contents of a dialogue with a large-scale language model as an editable graph document in which the document structure is graphed.

2. An information processing method characterized by outputting information for displaying on a display unit a screen having a field for displaying a dialogue history regarding dialogue content with a large-scale language model, and a field for displaying a graph document that graphs a document structure showing the dialogue content.

3. An information processing method comprising a first step of generating a first prompt including information based on a first graphical document that graphs a document structure.

4. 4. The information processing method of claim 3, further comprising a second step of outputting the first prompt to a large-scale language model that generates the first graphical document.

5. the large-scale language model also generates system utterances in response to user utterances input via an external device; the first prompt includes, in addition to the first graph document, dialogue history information of the user utterance and the system utterance; The second step includes obtaining the first graph document and the system utterance sentence updated based on the first prompt from the large-scale language model, and transmitting the obtained first graph document and the system utterance sentence to the external device.

5. The information processing method according to claim 4.

6. The large-scale language model also generates a search query sentence required to search for a reference second graph document from the dialogue content; creating a second prompt based on information including the first graph document and the dialogue history information, sending the second prompt to the large-scale language model, and obtaining the search query sentence generated based on the second prompt from the large-scale language model; a third step of searching for the second graph document from a group of graph documents stored based on the search query sentence; The first prompt includes information about the second graph document searched for and found in the third step.

6. The information processing method according to claim 5,

7. The third step is to obtain graph fragments whose contents are similar to the search query sentence by vector search, and further obtain graph fragments linked to the graph fragments by specific labels, and return these as search results.

7. The information processing method according to claim 6,

8. The third step can add additional information to the first graph document, and add a condition based on the additional information to the search query sentence so as to narrow down the second graph document to be searched.

7. The information processing method according to claim 6,

9. An information processing program that causes a computer to execute the information processing method according to any one of claims 1 to 8.

10. An information processing apparatus that executes the information processing program according to claim 9.

Images