Information processing system and information processing method

Abstract

To easily create a diary. [Solution] The information processing system is characterized by comprising a conversation data acquisition unit that acquires conversation data between a user, an emotion identification unit that analyzes the conversation data to identify the user's emotions, and a diary generation unit that generates diary data for the user based on the conversation data and the emotions.

Description

[Technical field]

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

[0002] Patent Document 1 proposes a system for assisting in creating a diary. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-242808 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, writing a diary is time-consuming and difficult to continue.

[0005] The present invention has been made in view of the above background, and has an object to provide a technique that enables a user to easily create a diary. [Means for solving the problem]

[0006] The main invention of the present invention for solving the above problem is an information processing system comprising a conversation data acquisition unit that acquires conversation data between a user, an emotion identification unit that analyzes the conversation data to identify the user's emotions, and a diary generation unit that generates diary data for the user based on the conversation data and the emotions.

[0007] Other problems and solutions disclosed in this application will be made clear in the description of the preferred embodiments of the invention and the drawings. Effect of the Invention

[0008] According to the present invention, a diary can be easily created. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of an overall configuration of an information processing system. [Diagram 2] 2 is a diagram illustrating an example of a hardware configuration of a management server 2. FIG. [Diagram 3] 2 illustrates an example of the software configuration of a management server 2. FIG. [Figure 4] FIG. 13 is a diagram illustrating the operation of the management server 2. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] <System Overview> An information processing system according to an embodiment of the present invention will be described below. The information processing system of this embodiment supports the creation of a diary (also called a journal, etc.) by a user. A diary is a record of a user's subjective opinion (emotions, thoughts, reactions, etc.) in addition to daily events, in order to deepen self-understanding, and is different from simple records such as minutes and various logs that leave objective facts and data. Although the word "day" is used, it does not have to be on a daily basis, and may be for a period of any length (which may be fixed or variable), such as an hourly unit, a half-day unit, a week unit, a two-week unit, or a month unit. In addition, it may be created irregularly rather than periodically. Since a diary expresses a user's subjective opinion, by analyzing the diary, for example, it is possible to estimate, judge, or diagnose the user's mental state. In many cases, the user himself is not aware of his own subjective opinion, and there are quite a few users who are not good at keeping a diary. The information processing system of this embodiment supports the creation of a diary through conversation with the user.

[0011] 1 is a diagram showing an example of the overall configuration of an information processing system. The information processing system of this embodiment is configured to include a management server 2. The management server 2 is communicably connected to a user terminal 1 via a communication network. The communication network is, for example, the Internet, and is constructed by a public telephone line network, a mobile phone line network, a wireless communication path, Ethernet (registered trademark), etc.

[0012] The user terminal 1 is a computer operated by a user. The user terminal 1 may be, for example, a smartphone, a tablet computer, or a personal computer.

[0013] The management server 2 may be a general-purpose computer such as a workstation or a personal computer, or may be logically realized by cloud computing.

[0014] <Management Server> FIG. 2 is a diagram showing an example of the hardware configuration of the management server 2. Note that the illustrated configuration is an example, and other configurations may be used. The management server 2 includes a CPU 201, a memory 202, a storage device 203, a communication interface 204, an input device 205, and an output device 206. The storage device 203 is, for example, a hard disk drive, a solid state drive, or a flash memory that stores various data and programs. The communication interface 204 is an interface for connecting to a communication network, for example, an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone line network, a wireless communication device for wireless communication, a USB (Universal Serial Bus) connector or an RS232C connector for serial communication, etc. The input device 205 is, for example, a keyboard, a mouse, a touch panel, a button, a microphone, etc. that input data. The output device 206 is, for example, a display, a printer, a speaker, etc. that output data. Each functional unit of the management server 2 described below is realized by the CPU 201 reading a program stored in the storage device 203 into the memory 202 and executing it, and each storage unit of the management server 2 is realized as part of the storage area provided by the memory 202 and the storage device 203.

[0015] 3 is a diagram showing an example of the software configuration of the management server 2. The management server 2 includes a conversation data acquisition unit 211, an emotion identification unit 212, a diary generation unit 213, a conversation data generation unit 214, an emotion history graph generation unit 215, a diary sharing unit 216, a user understanding unit 217, a content recommendation unit 218, a conversation data storage unit 231, and a diary data storage unit 232.

[0016] <Storage section> The conversation data storage unit 231 stores data indicating a conversation with a user (hereinafter referred to as conversation data). The conversation data is, for example, text data, audio data, video data, etc. The conversation data storage unit 231 can accumulate conversation data over time. For example, the conversation data storage unit 231 can store the conversation data together with time information. The time information can be a time stamp such as date and time.

[0017] The diary data storage unit 232 stores data indicating a user's diary (hereinafter referred to as diary data). The diary data can be, for example, text data. The diary data can also include still image data, audio data, video data, and the like. The diary data storage unit 232 can accumulate diary data over time. The diary data storage unit 232 can store diary data in association with information identifying the user (for example, a user ID) and time information. The time information can be a time stamp such as date and time.

[0018] Diary data may be composed of, for example, metadata, a text, and a summary. The metadata may include information for identifying a user (user ID), date, day of the week, weather, and the like. The text may include time (time of day when the event occurred (morning, afternoon, night, etc.)), place (place where the event occurred (home, workplace, store name, etc.)), person (person involved in the event (friends, colleagues, family, etc.)), action (verb phrase expressing the content of the event (had a meal, attended a meeting, etc.)), emotion (user's emotion regarding the event (joy, sadness, anger, etc.)), and details (detailed explanation of the event, user's impressions and opinions, etc.). The details may include what kind of event moved the emotion, how the user felt, and so on. In this way, the diary data may record the events of the day and the user's emotions, impressions, and reflections on them in a chronological order.

[0019] In addition to text data, diary data can also include image data and audio data. For example, photos and videos related to each entry can be taken and attached to the diary data. Also, by including audio data in the diary data, the user's live voice and environmental sounds can be recorded, making it possible to create a more realistic diary. Furthermore, diary data can also include additional data such as the user's health information and environmental information. For example, by associating information such as the number of steps, heart rate, and sleep time obtained from a wearable device, and information such as location information, temperature, and humidity obtained from a smartphone, with the diary data, it is possible to analyze the relationship between the user's physical and environmental conditions and emotions. In addition, diary data can also include notes and tags manually entered by the user. For example, the user can assign keywords and categories related to the contents of the diary, or add free-form comments.

[0020] <Functional section> The conversation data acquisition unit 211 has a function of acquiring conversation data between the user and the conversation data acquisition unit 211. The conversation data acquisition unit 211 can receive and acquire conversation data such as text data, audio data, and video data transmitted from the user terminal 1. The conversation data acquisition unit 211 stores the acquired conversation data together with time information in the storage device 203, and accumulates it as conversation data over time.

[0021] The emotion identification unit 212 has a function of analyzing the conversation data and identifying the emotion of the user. The emotion identification unit 212 analyzes the conversation data acquired by the conversation data acquisition unit 211 using techniques such as natural language processing and machine learning, and can estimate the emotion of the user from text, voice, facial expressions, etc. The emotion identification unit 212 quantifies and identifies not only the type of emotion such as joy, anger, sadness, and happiness, but also the degree of each emotion.

[0022] The emotion identification unit 212 can score the emotional meaning of words included in each sentence or paragraph by, for example, performing a method such as text mining using a previously prepared emotion dictionary on the text data included in the conversation data. The emotion dictionary can store, for each word, emotion labels such as "positive", "negative", and "neutral", and emotion values ​​that represent the degree of emotion in a numerical range such as -1 to +1.

[0023] The emotion identification unit 212 can estimate the emotion of the speaker by analyzing features such as the pitch, volume, speed, and tone of the voice data included in the conversation data. For example, by inputting acoustic features such as fundamental frequency (pitch), loudness, spectrum, and formant into a machine learning model, it is possible to output emotion labels such as "anger," "sadness," and "happiness" from the voice and the degree of each emotion in a numerical range such as 0 to 1.

[0024] The emotion identification unit 212 can estimate the emotion of the speaker by detecting changes in facial expressions and body movements from the video data included in the conversation data. For example, by quantifying the coordinates and movements of feature points such as the degree of opening of the eyes and mouth, movement of the eyebrows, redness of the cheeks, and gestures and hand movements, and inputting these into a machine learning model, it is possible to output emotion labels such as "surprise," "disgust," and "fear" from the video, and the degree of each emotion in a numerical range such as 0 to 1.

[0025] The emotion identification unit 212 can estimate the emotion and the degree of the speaker based on the feature values ​​detected from the conversation data of multiple modalities, such as text, audio, and video. The emotion identification unit 212 can infer the emotion of the speaker from both the label and the numerical value by, for example, analyzing the conversation data of multiple modalities, quantifying the feature values, and inputting them into a machine learning model. The emotion identification unit 212 can obtain a more reliable emotion estimation result by, for example, determining the emotion labels obtained from each modality by majority vote or taking a weighted average of the emotion values ​​of each modality.

[0026] The diary generation unit 213 has a function of generating diary data of a user based on conversation data and emotions. The diary generation unit 213 extracts conversation data that corresponds to a predetermined emotion identified by the emotion identification unit 212 and has a degree of the emotion equal to or greater than a predetermined threshold. The diary generation unit 213 generates a prompt to output the extracted conversation data, information indicating the identified emotion, and an event estimated from the conversation data in the form of a diary. The diary generation unit 213 inputs the prompt into a large-scale language model to generate diary data. The generated diary data is transmitted to the user terminal 1 or stored in the storage device 203.

[0027] The diary generating section 213 can select conversation data to be used for generating diary data, based on the type and degree of emotion identified by the emotion identifying section 212.

[0028] For example, the diary generation unit 213 can extract conversation data that is assigned a specific emotion label such as "joy" or "sadness" and has an emotion value that is a predetermined threshold (for example, 0.7 or more) and use the extracted conversation data to generate diary data. This makes it possible to generate a diary centered on events that were impressive or memorable to the user.

[0029] For example, the diary generation unit 213 may preferentially extract conversation data with negative emotion labels such as "anger" or "disgust" regardless of the magnitude of the absolute emotion value, and include in the diary data advice on how to deal with these emotions. This makes it possible to generate a diary that supports the user's mental health and suggests ways to deal with negative emotions.

[0030] When conversation data is assigned a positive emotion label such as "joy" or "fun" and the emotion value exceeds a threshold value (e.g., 0.8 or more), the diary generation unit 213 can highlight the emotion in the diary data or automatically attach a related photo.

[0031] The diary generating unit 213 can generate diary data with appropriate content and expression according to the emotional state of the user by using the emotion labels and emotion values ​​assigned to the conversation data by the emotion identifying unit 212.

[0032] The diary generation unit 213 can use natural language processing technology to infer events from conversation data. Specifically, by combining morphological analysis, syntactic analysis, named entity extraction, and the like, it is possible to detect words and phrases that express events from conversation data and organize them in chronological order.

[0033] The diary generation unit 213 can, for example, perform morphological analysis on each sentence included in the conversation data to divide the sentence into words, determine the part of speech of each word (noun, verb, adjective, etc.), analyze the syntactic structure of each sentence by syntactic analysis, and identify components of the sentence such as the subject, predicate, and object. The diary generation unit 213 can also extract named entities such as people's names, place names, organization names, and dates and times from the conversation data using a method of named entity extraction. For example, the diary generation unit 213 can estimate the date and time and location of an event using an expression that indicates time or location as a clue. The diary generation unit 213 can, for example, integrate information obtained by the above processing and extract a phrase that indicates an event. The diary generation unit 213 can estimate an event more accurately by arranging the conversation data in chronological order and taking into account the context before and after. For example, the diary generation unit 213 can estimate the chronological order of multiple events using time expressions such as "last night" and "this afternoon" and conjunctions such as "there" and "next" as a clue.

[0034] The diary generation unit 213 can dynamically generate prompts to be given to the large-scale language model in order to generate diary data based on the conversation data and emotion information. The prompts are instructions or example sentences written in natural language, and are used to specify the format and content of sentences to be output by the large-scale language model.

[0035] The diary generating unit 213 can generate a prompt, for example, through the following steps. (1) The extracted events are fitted to standard phrases such as "I performed <action> with <person> at <place> at <time>" to generate sentences that describe the events. (2) Using emotion labels and their emotion values ​​associated with the event, we generate emotion expressions such as “I felt very happy” or “I felt a little sad.” (3) By combining the event description and the emotional expression, each diary entry is generated in the form of "<Event>. After experiencing it, <Emotional expression>." (4) Arrange each entry in chronological order, add appropriate conjunctions and adverbs, and organize them into coherent sentences. (5) Add standard phrases such as "Diary on <date>" or "Thank you for your hard work today" to the beginning and end of your diary. (6) The diary sentences generated in the above manner are compiled into a prompt along with instructions for the large-scale language model (e.g., “Please rewrite the following sentence into a natural and fluent diary sentence”).

[0036] By inputting the above-mentioned prompts into the large-scale language model, the diary generating unit 213 can generate diary sentences that reflect events extracted from the conversation data and the emotion information linked to the events.

[0037] The diary generating unit 213 can also customize the method of generating prompts according to, for example, the user's preferences and habits. For example, the diary generating unit 213 can provide additional instructions to the prompts, such as to include keywords specified by the user or to generate sentences in a specific style (polite, ordinary, dialect, etc.). The diary generating unit 213 can also learn the user's preferred expression patterns by analyzing past diary data, for example, and reflect them in the generation of prompts.

[0038] The management server 2 may also include a conversation data generating unit 214 that generates conversation data to be issued to the user. The conversation data generating unit 214 has a function of generating conversation data (hereinafter referred to as guiding conversation data) that inquires the user about daily events and inquires about thoughts on the events. The conversation data generating unit 214 can generate guiding conversation data by creating a prompt including an instruction to generate conversation data that inquires the user about daily events and thoughts on the events, and inputting the prompt into a large-scale language model. The prompt may include conversation data exchanged with the user in the past. The generated guiding conversation data is transmitted to the user terminal 1 and used for conversation with the user.

[0039] When generating conversation data to be issued to a user, the conversation data generating unit 214 can generate more effective conversation data according to the situation and characteristics of the user, rather than simply asking standard questions. For example, the conversation data generating unit 214 can appropriately select topics and language in consideration of attribute information such as the user's age, sex, and occupation. By realizing a communication style that matches the attributes of the user, such as using colloquial expressions for young people and more polite language for elderly people, affinity with the user can be increased.

[0040] The conversation data generating unit 214 can also generate conversation data, for example, taking into account the emotional state of the user. For example, if the user is expressing negative emotions such as "sadness" or "anger," the user's emotions can be taken care of by providing empathetic words or a topic that encourages a change of mood. Conversely, if the user is expressing positive emotions such as "joy" or "fun," conversation data that shares these emotions and further boosts them can be generated to support the user's positive feelings.

[0041] The conversation data generating unit 214 can provide topics that match the user's interests by, for example, analyzing the user's behavior history and hobbies and preferences. For example, when the conversation data generating unit 214 infers from the diary data that the user has recently traveled, it can generate a conversation that is in line with the user's interests by asking the user a question to look back on the travel experience or inquiring about the user's next travel plans.

[0042] The conversation data generating unit 214 can generate conversation data that takes into account the context of the conversation, for example, by analyzing past interactions with the user. For example, when the user mentions a certain topic, the conversation data generating unit 214 can ask a question related to the topic or cite a related episode that came up in a past conversation.

[0043] The conversation data generating unit 214 can learn the linguistic features of the user from, for example, a conversation history with the user and reflect the learned features in the generation of conversation data. For example, the conversation data generating unit 214 can analyze the words, expressions, and ending habits of the user that are frequently used by the user and incorporate them into the conversation data, thereby realizing a speaking style that is more familiar to the user.

[0044] The conversation data generating unit 214 may adopt a rule-based method or a generation-type method using a large-scale language model. In the rule-based method, conversation data can be generated based on a template prepared in advance, an IF-THEN rule, or the like. In the method using a large-scale language model, conversation data can be generated by providing a prompt as described above to the large-scale language model. The conversation data generating unit 214 can input, for example, past conversation data with a user, diary data, a user profile, or the like, and provide a prompt to the large-scale language model that instructs the generation of conversation data based on these conditions. The large-scale language model can probabilistically generate conversation data according to the input prompt.

[0045] In addition, in generating conversation data using a language model, a reinforcement learning method can be introduced. For example, the user's response can be fed back into the learning process, and the language model can be optimized to generate gradually better conversation data. For example, by learning to reinforce conversation data to which the user responded positively and suppress conversation data to which the user responded negatively, it becomes possible to generate conversation data that is more attractive to the user.

[0046] The diary generation unit 213 can extract the user's thoughts from the conversation data and generate diary data based on the extracted thoughts and the conversation data in addition to or instead of the emotions. The process of extracting the user's thoughts from the conversation data can use natural language processing or the like. The diary generation unit 213 can generate the user's thoughts by, for example, providing the large-scale language model with a prompt including the conversation data and an instruction to extract the user's thoughts from the conversation data.

[0047] <Operation> FIG. 4 is a diagram illustrating the operation of the management server 2. As shown in FIG.

[0048] The management server 2 generates conversation data inquiring about daily events and the user's thoughts on those events (S301), transmits and receives the conversation data with the user terminal 1 (S302), acquires the conversation data transmitted and received with the user terminal 1 (S303), analyzes the conversation data to identify the user's emotions (S304), generates diary data for the user based on the conversation data and the emotions (S305), and registers the generated diary data in the diary data storage unit 232 (S306).

[0049] As described above, the information processing system of this embodiment can generate diary data of a user from a conversation between the system and the user. The diary data reflects the user's feelings and thoughts.

[0050] Although the present embodiment has been described above, the above embodiment is intended to facilitate understanding of the present invention, and is not intended to limit the present invention. The present invention may be modified or improved without departing from the spirit of the present invention, and equivalents thereof are also included in the present invention.

[0051] For example, the processes performed by each of the functional units of the management server 2 described above may be executed by any of the functional units. Also, a different functional unit that executes part of the processes performed by each of the functional units described above may be added. Also, the functional units of the management server 2 may be provided in a distributed manner on multiple computers.

[0052] Furthermore, the information stored in each storage unit of the management server 2 may be stored by any storage unit. That is, the information stored in the above-mentioned multiple storage units may be stored by one storage unit, or part of the information stored in one of the above-mentioned storage units may be stored by another storage unit.

[0053] <Variation 1>

[0054] In the first modification, a function can be added to acquire conversation data from a plurality of users, analyze the emotions of each user, and calculate the similarity of emotions between users.

[0055] Specifically, the management server 2 collects conversation data from a plurality of user terminals 1 and analyzes the emotions of each user. Then, the emotion vector can be used to calculate the similarity of emotions between users.

[0056] An emotion vector is a vector that has the intensity of each emotion category (happiness, sadness, anger, etc.) as an element. For example, an emotion vector can be "happiness: 0.8, sadness: 0.1, anger: 0.2." The management server 2 analyzes emotions from the conversation data of each user and generates an emotion vector.

[0057] Next, the management server 2 calculates the cosine similarity of the emotion vectors between the users to calculate the similarity of the emotions between the users. The cosine similarity is an index that indicates the extent to which two vectors point in the same direction, and takes values ​​between -1 and 1. The closer the value is to 1, the more similar the directions of the two vectors are.

[0058] The management server 2 can provide various services based on the calculated emotional similarity between users. For example, it can match users with high emotional similarity with each other and provide a place for online interaction, or create a group for users with high similarity and provide an opportunity to talk about common topics.

[0059] In addition, the management server 2 can grasp the overall emotional trends of users by analyzing the similarity of emotions between users. For example, if the emotions of many users are biased toward "sadness," the management server 2 can deliver content to brighten the emotions of all users or plan an event where users can encourage each other.

[0060] Furthermore, the management server 2 can analyze the pattern of change in users' emotions by tracking changes in the similarity of their emotions. For example, if the similarity of emotions between two users gradually increases, there is a possibility that empathy is emerging between those users. By utilizing such analysis results, it becomes possible to provide detailed support that matches the changes in users' emotions.

[0061] <Variation 2>

[0062] In the second modification, the diary data can include keywords and summaries extracted from the conversation data. Specifically, the diary generating unit 213 can use natural language processing techniques such as morphological analysis and word importance calculation to extract keywords from the conversation data.

[0063] For example, the diary generation unit 213 performs morphological analysis on each sentence included in the conversation data and breaks it down into parts of speech such as nouns, verbs, and adjectives. Next, to calculate the importance of each word, a method such as TF-IDF (Term Frequency-Inverse Document Frequency) is used. TF-IDF is an index that evaluates how important a particular word is in a document, and is calculated using the frequency of occurrence of the word and the reciprocal of the number of documents in which the word appears. The diary generation unit 213 extracts words with high calculated TF-IDF values ​​as important keywords of the conversation data. The extracted keywords can be recorded as metadata of the diary data or inserted into the body of the diary.

[0064] In order to generate a summary from the conversation data, the diary generation unit 213 can use summary generation techniques such as calculating the importance of a sentence, extracting important sentences, and compressing sentences. For example, the diary generation unit 213 calculates the importance of each sentence included in the conversation data as the sum of the importance of words in the sentence, and extracts sentences with high importance. Next, the extracted important sentences are compressed using a language model and rewritten into more concise expressions. The summary generated in this way can be recorded as metadata of the diary data or inserted at the beginning or end of the main text of the diary.

[0065] The diary generating unit 213 may generate a summary to be included in the diary data by providing a prompt, including conversation data and an instruction to summarize the conversation data, to the large-scale language model.

[0066] <Variation 3>

[0067] The third modification can add a function to graph and visually display the changes in the user's emotions over time, making it easy to understand the transitions in the user's emotions.

[0068] Specifically, the management server 2 can include an emotion history graph generation unit 215. The emotion history graph generation unit 215 has a function of graphing the type and degree of the user's emotion identified by the emotion identification unit 212 in chronological order.

[0069] The emotion history graph generating unit 215 acquires emotion data for each day from the diary data accumulated in the diary data storage unit 232. The emotion data includes the type of emotion (happiness, sadness, anger, etc.) and its degree (real value between 0 and 1). The emotion history graph generating unit 215 arranges the acquired emotion data in chronological order and graphs the change in degree for each emotion type.

[0070] For example, the emotion history graph generating unit 215 can generate a line graph with the horizontal axis representing time and the vertical axis representing the degree of emotion. On the graph, lines corresponding to each type of emotion are displayed in different colors, and the height of the line represents the degree of the emotion. This allows the user to grasp at a glance the changes in each type of emotion.

[0071] Furthermore, the emotion history graph generation unit 215 can also use a radar chart to visualize the correlation between types of emotions. A radar chart is a graph that represents multivariate data on a two-dimensional plane, and can represent the relationship between variables by plotting the value of each variable on axes extending radially from a central point and connecting the plotted points with lines.

[0072] The emotion history graph generation section 215 generates a radar chart with each emotion type as an axis, and the emotion data for each day can be plotted on the radar.

[0073] The emotion history graph generating unit 215 can also generate animations showing transitions of emotions in order to summarize changes in the user's emotions. With animations, dynamic changes in the user's emotions can be expressed by moving points showing the degree of emotions on a graph over time, or by changing areas showing combinations of emotions on a radar chart.

[0074] The generated emotion history graph and animation are transmitted to the user terminal 1 and presented to the user. The user can visually grasp changes in his or her emotions.

[0075] <Modification 4>

[0076] In the fourth modification, a function can be added that allows diary data to be shared with other users based on the user's permission. This promotes communication between users and allows them to share sympathy and advice.

[0077] Specifically, the management server 2 can include a diary sharing section 216. The diary sharing section 216 has a function of sharing all or a part of the diary data with other users in accordance with an instruction from the user.

[0078] The diary sharing unit 216 receives a diary data sharing request from the user terminal 1. The sharing request includes information for identifying the sharing destination user (user ID, email address, SNS account, etc.) and the range of diary data to be shared (specific date, period, entry, etc.).

[0079] Based on the sharing request, the diary sharing unit 216 transmits the specified diary data to the sharing destination user. At that time, the diary sharing unit 216 adds the sharing source user's information (user ID, nickname, etc.) to the diary data so that the sharing destination user can identify the creator of the diary.

[0080] The sharing destination user can view the diary data received on his / her user terminal 1 and add comments and reactions (such as "Like" or emoticons). The added comments and reactions are fed back to the sharing source user via the diary sharing unit 216.

[0081] In addition, the diary sharing unit 216 can also calculate the degree of emotional empathy between users by analyzing comments and reactions to the shared diary data. For example, if multiple users leave similar comments or reactions to a certain diary entry, it can be determined that there is a high degree of emotional empathy between those users.

[0082] The diary sharing unit 216 can also match users based on the calculated degree of empathy with emotions. For example, users with a high degree of empathy with emotions can be connected to each other to promote deeper communication. Matched users can understand each other's emotions through diary data and exchange sympathy and advice.

[0083] The diary sharing unit 216 can also discover trends in emotions common to many users by analyzing the shared diary data. For example, if it is found that many users have similar emotions about a certain event, it suggests that the event has social significance.

[0084] The diary sharing unit 216 can have functions such as allowing the user to set the sharing range in detail, limiting the users with whom the diary can be shared according to the degree of trust, etc. In addition, in order to prevent secondary diffusion of the shared diary data, technical measures such as prohibiting copying or forwarding can be taken.

[0085] <Variation 5>

[0086] In the fifth modification, a function can be added to estimate the user's interests and concerns from the diary data and provide information and advice according to the interests and concerns. The management server 2 according to the fifth modification can include a user understanding unit 217 and a content recommendation unit 218.

[0087] The user understanding unit 217 has a function of inferring the user's interests and concerns by analyzing diary data.

[0088] The user understanding unit 217 estimates the user's interests and worries by analyzing the keywords and written contents contained in the diary data. For example, if keywords such as "cooking" and "recipe" appear frequently, it can be estimated that the user is interested in cooking. Also, if negative expressions such as "stress" and "tiredness" are frequently seen, it can be estimated that the user has some worries.

[0089] The user understanding unit 217 categorizes the estimated interests and worries into a prepared classification system. For example, interests such as "cooking" and "travel" can be categorized into the "hobbies" category, and worries such as "work stress" and "human relationship worries" can be categorized into the "mental health" category.

[0090] The content recommendation unit 218 has a function of selecting and providing information and advice suitable for the user based on the estimation result by the user understanding unit 217. The content recommendation unit 218 selects appropriate information and advice in accordance with the interests and worries estimated and classified by the user understanding unit 217. For example, new recipes and gourmet information can be provided to a user interested in "cooking," and advice on stress relief and time management can be provided to a user suffering from "work stress."

[0091] The content recommendation unit 218 can use various methods for providing information and advice, such as the following. (1) Adding related information to diary data: Recommended information or advice is added as an annotation to the relevant part of the diary data. When reviewing the diary, the user can refer to the related information. (2) Push notification: Information and advice tailored to the user's interests and concerns are periodically sent to the user terminal 1. The user can receive information at appropriate times in their daily lives. (3) Email newsletter delivery: Email newsletters are delivered on topics that correspond to the user's interests and concerns. Users can receive comprehensive information and advice on a regular basis. (4) Interaction with chatbots: Interaction scenarios with chatbots are generated based on the user's interests and concerns. Through conversations with chatbots, users can interactively obtain information and advice.

[0092] The content recommendation unit 218 can also improve the recommended information and advice based on feedback from the user. For example, if the user gives the recommended information a "like" or comments that it was "useful," the recommendation level of the information is increased. Conversely, if the user ignores the recommended information or comments that he or she is "not interested," the recommendation level of the information is decreased. By analyzing such feedback using techniques such as machine learning, it becomes possible to provide information and advice that are more suited to the user's preferences.

[0093] The content recommendation unit 218 can also analyze the results of the estimation of interests and worries by the user understanding unit 217 in association with the user's life events. For example, the user's interests and worries may change with life events such as marriage, childbirth, employment, and job change. By capturing such changes, it becomes possible to provide detailed information and advice according to the life stage.

[0094] <Disclosures> The present disclosure also includes the following configurations. [Item 1] A conversation data acquisition unit that acquires conversation data between the user and the conversation data acquisition unit; an emotion identification unit that analyzes the conversation data to identify an emotion of the user; a diary generating unit that generates diary data of the user based on the conversation data and the emotion; An information processing system comprising: [Item 2] The information processing system according to item 1, The conversation data includes at least two of text data, audio data, and video data; An information processing system comprising: [Item 3] The information processing system according to item 1, the conversation data acquisition unit acquires the conversation data over time in association with time information; the emotion identification unit identifies the emotion and a degree of the emotion; the diary generation unit generates the diary data by providing a large-scale language model with the conversation data corresponding to a predetermined emotion and having a degree of the emotion equal to or greater than a predetermined threshold, information indicating the emotion, and a prompt including a command to identify an event from the conversation data and output the event together with the emotion in the form of a diary; An information processing system comprising: [Item 4] a conversation data generation unit that generates the conversation data to be issued to the user, the conversation data generation unit generating guided conversation data that inquires of the user about daily events and thoughts about the events; An information processing system comprising: [Item 5] Item 4. An information processing system according to the present invention, the conversation data generation unit generates the guided conversation data by providing a prompt including an instruction to generate the conversation data inquiring of the user about daily events and thoughts about the events to a large-scale language model; An information processing system comprising: [Item 6] Acquiring conversation data between the user and the device; analyzing the conversation data to identify emotions of the user; generating diary data of the user based on the conversation data and the emotion; An information processing method characterized by being executed by a computer. [Explanation of symbols]

[0095] 1 User terminal 2 Management Server

Claims

1. A conversation data acquisition unit that acquires conversation data between the user and the conversation data acquisition unit; an emotion identification unit that analyzes the conversation data to identify an emotion of the user; a diary generating unit that generates diary data of the user based on the conversation data and the emotion; Equipped with the diary generation unit generates the diary data by providing a large-scale language model with a prompt including the conversation data extracted according to the emotion, information indicating the emotion, and an instruction to output the conversation data together with the emotion in a diary format; An information processing system comprising:

2. 2. The information processing system according to claim 1, The conversation data includes at least two of text data, audio data, and video data; An information processing system comprising:

3. 2. The information processing system according to claim 1, the emotion identification unit identifies the emotion and a degree of the emotion; the diary generation unit generates the diary data by providing, to a large-scale language model, the conversation data extracted from the conversation data corresponding to a predetermined emotion and having a degree of the emotion equal to or greater than a predetermined threshold, information indicating the emotion, and a prompt including an instruction to output the emotion together with the emotion in the form of a diary; An information processing system comprising:

4. 2. The information processing system according to claim 1, a conversation data generation unit that generates the conversation data to be issued to the user, the conversation data generation unit generating guided conversation data that inquires of the user about daily events and thoughts about the events; An information processing system comprising:

5. 5. The information processing system according to claim 4, the conversation data generation unit generates the guided conversation data by providing a prompt including an instruction to generate the conversation data inquiring of the user about daily events and thoughts about the events to a large-scale language model; An information processing system comprising:

6. Acquiring conversation data between the user and the device; analyzing the conversation data to identify emotions of the user; generating diary data of the user based on the conversation data and the emotion; The computer executes In the step of generating diary data, the computer generates the diary data by providing a large-scale language model with a prompt including the conversation data extracted according to the emotion, information indicating the emotion, and an instruction to output the conversation data together with the emotion in the form of a diary; An information processing method comprising:

Images