Dememorative story writing system and memorative story writing equipment

Abstract

The embodiment of the invention provides a disciplinary story writing system and disciplinary story writing equipment, and the system comprises a theme setting unit which is used for guiding a user to determine the theme of a disciplinary story, and extracting content parameters related to the theme from a database according to the theme; the voice dialogue unit is used for performing voice dialogue with the user around the theme content based on a large model in combination with the content parameters, mining and proposing problems by adopting a mode of identifying the intention replied by the user and managing dialogue context, dynamically guiding the user to share personal experience and emotion, and forming a current dialogue record when the voice dialogue is finished; and the story generation unit is used for generating a commemorative story according to the styles of literary and sports and the current dialogue record after the user selects the styles of literary and sports. A simple, efficient and more personalized commemorative story can be provided on the premise that the text quality is not sacrificed.

Description

Technical Field

[0001] The present invention relates to the technical field of natural language processing, and in particular to a documentary story writing system and a documentary story writing device. Background Art

[0002] Existing story continuation and article generation systems often require the author to have a certain idea of ​​the story content (plot, characters). The main purpose of the system is to diverge thinking (form multiple possible story lines) and generate stylized text. After receiving the initial story input by the user, the roles in the dialogue are determined from it. As the starting point of the dialogue generation process, the basis of the story and the participating roles are determined. As a popular online literature creation assistant, the main function of "Writing Frog" is to continue the story based on the user's existing desire to express the idea and plot.

[0003] However, the expansion or dialogue function in the known system focuses on diverging imagination, controlling the turning points and climaxes of complex plot design, adjusting the rhythm of character appearance and exit, creating characters of various personalities to match the plot, and ultimately achieving the purpose of attracting readers. However, these are contrary to the principles of writing character memoirs (non-fiction). Therefore, in the process of interaction between the system and the user and the collection of user responses, the purpose is to confirm interest, but it is impossible to control the allocation between open-ended questions, detailed questions, and emotional confirmation strategies with the goal of exploring the user's personal experience and emotional state.

[0004] There is currently no such system that can obtain user information based on the chronological order of personal life and generate stories for the purpose of recording and reproducing personal memories without any user having to plan the writing in advance.

[0005] There is no such system that can generate articles in the style of personal biography and documentary prose. When writing personal stories with general or other style models, the wording and emotional expression cannot fully interpret the story and user personality, resulting in low satisfaction. For example, the large model tends to generate emotional copywriting such as "Every time I think back to that spring morning, I feel deeply moved", but not all authors appreciate such an expression in narrating their own experiences. Summary of the invention

[0006] The embodiments of the present invention provide a documentary story writing system and a documentary story writing device, which can solve the technical problem in the prior art that it is impossible to "acquire user information with the chronological order of personal life as an index and generate a story based on the purpose of recording and reproducing personal memories without any user having any idea about the writing in advance."

[0007] To achieve the above objectives, in a first aspect, an embodiment of the present invention provides a documentary story writing system, comprising:

[0008] A theme setting unit, used to guide the user to determine the theme of the documentary story, and extract content parameters related to the theme from the database according to the theme;

[0009] The voice dialogue unit is used to conduct a voice dialogue with the user around the subject content based on the large model combined with the content parameters, identify the user's reply intention, manage the dialogue context, explore and raise questions, dynamically guide the user to share personal experiences and emotions, and form a current dialogue record when the voice dialogue ends;

[0010] The story generation unit is used to generate a documentary story according to the text style and the current conversation record after the user selects the text style. The text style has corresponding generation rules and algorithms, so that the story conforms to literary artistry and reflects the user's life and personality.

[0011] In a second aspect, an embodiment of the present invention provides a documentary story writing device, wherein the documentary story writing device has a visual interface or does not have a visual interface, and the documentary story writing device includes:

[0012] A processor; and a memory arranged to store executable instructions, which when executed cause the processor to implement the aforementioned documentary story writing system;

[0013] The documentary story writing device also includes:

[0014] Start and Remake keys, used to enter a documentary story writing mode, or re-enter another documentary story writing mode;

[0015] A dialogue control key is used to activate the dialogue control key to enter the voice dialogue mode, and to generate a documentary story through the theme setting unit, the voice dialogue unit and the story generation unit.

[0016] The above technical solution has the following beneficial effects: voice dialogue for the purpose of collecting personal experience information can automatically extract key information from life events and memories provided by users, effectively collect, process and utilize users' personal information, and generate structured, emotionally rich and personal style memoir articles, that is, generate documentary stories. It can provide a simple, efficient and more personalized story generation tool without sacrificing text quality, which can be used for users who want to write personal memoirs or have documentary nature, especially for the elderly. It can solve the problem in the prior art that it is impossible to automatically and accurately generate documentary texts that highly meet personalized needs based on personal memories and life experiences. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a logical structure diagram of a documentary story writing system according to an embodiment of the present invention;

[0019] Figure 2 is a flowchart of a documentary story writing according to an embodiment of the present invention;

[0020] Figure 3 It is a framework diagram of the hardware structure and the hardware and software dual front-end of an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] like Figure 1 As shown, in combination with an embodiment of the present invention, a documentary story writing system is provided, comprising:

[0023] Theme setting unit 11 is used to guide the user to determine the theme of the documentary story, and extract content parameters related to the theme from the database according to the theme, and the content parameters are used to construct the initial direction and dialogue depth of the documentary story;

[0024] The voice dialogue unit 12 is used to conduct a voice dialogue with the user around the subject content based on the large model combined with the content parameters, identify the user's reply intention, manage the dialogue context, dig out and raise questions, dynamically guide the user to share personal experiences and emotions, and form a current dialogue record when the voice dialogue ends;

[0025] The story generating unit 13 is used to generate a documentary story according to the writing style and the current conversation record after the writing style is selected by the user.

[0026] Existing technologies mainly focus on story continuation and stylized text generation based on existing creative ideas, and are highly dependent on user input. In particular, in dealing with personal memories and nonfiction writing, existing systems are unable to effectively capture and reproduce users' personalized and detailed personal experiences.

[0027] A documentary story writing system according to an embodiment of the present invention, especially a voice dialogue for the purpose of collecting personal experience information, can automatically extract key information from life events and memories provided by users, effectively collect, process and utilize the personal information of users, and thereby generate a structured, emotionally rich and personally styled memoir article, that is, generate a documentary story. It can provide a simple, efficient and more personalized story generation tool without sacrificing the quality of the text, which can be used by users who want to write personal memoirs or have a documentary nature, especially suitable for the elderly. It can solve the problem in the prior art that it is impossible to automatically and accurately generate a documentary text that highly meets personalized needs based on personal memories and life experiences.

[0028] Preferably, the theme setting unit 11 includes a first theme setting subunit or a second theme setting subunit:

[0029] The first theme setting subunit is used to guide the user to select a theme from preset themes as the theme of the documentary story through dialogue on the UI interface or by pressing buttons;

[0030] The second theme setting sub-unit is used to guide the user to speak out the content information points that the theme may contain through the big model, and to connect all the content information points in series through logic to obtain an initial theme, and to expand, select and refine the content information points and theme background of the initial theme through the big model to obtain the final theme; wherein, in the process of the big model expanding, selecting and refining the content information points and theme background of the initial theme, the Internet connection can be used for retrieval.

[0031] Preferably, the theme setting unit 11 further includes:

[0032] A content parameter extraction subunit is used to extract plot guiding factors related to the theme from the database, and to extract inspiring questions corresponding to the plot guiding factors, and to use the inspiring questions as content parameters related to the theme. The content parameters are used as prompt words during voice dialogue, and guide the big model to ask questions to the user when the big model conducts a voice dialogue with the user around the theme content, so as to construct the initial direction and dialogue depth of the documentary story;

[0033] Among them, the database stores plot guiding factors of various themes and inspiring questions converted from the plot guiding factors. The plot guiding factors are extracted from massive documentary literature, and the extracted plot guiding factors include at least: event type, cause of conflict, character relationship and personal feelings.

[0034] Preferably, the documentary story writing system further includes:

[0035] The information collection unit is used to obtain the user's basic information from the database and provide it to the big model if it is not the first time for the user to generate a documentary story. After guiding the user to determine the theme of the documentary story, the basic information of the user is provided to the big model. The obtained basic information of the user is used to avoid repeated questions to the user during the process of the big model having a voice dialogue with the user around the theme content, wherein the basic information includes: gender, age, hometown, education level and highest honor.

[0036] Preferably, the speech dialogue unit 12 comprises a single agent based on a large model, and the single agent based on the large model is used to:

[0037] In combination with the content parameters, in the process of engaging in a conversation with the user around the topic content, an emotional feedback strategy is used to ask questions to the user, and a current conversation record is formed when the voice conversation ends; the emotional feedback strategy includes: confirming positive emotions and soothing negative emotions;

[0038] or,

[0039] The single agent based on the large model combines the content parameters, and in the process of conducting a voice dialogue with the user around the topic content, adopts a continuous questioning strategy to ask questions to the user, and forms a current dialogue record when the voice dialogue ends; the continuous questioning strategy includes: open-ended questions, continuing to explore a certain character, asking about event details, situation description, contradictory assumptions, asking about feelings and switching topics;

[0040] Among them, if it is not the first time for the user to generate a documentary story, the single agent based on the large model will start a voice conversation with the user around the topic content, and use the memory link as the opening remark of the voice conversation to ask questions to the user; afterward, for each group of voice conversations, the single agent based on the large model will ask at least one question at the same time. When there are at least two questions raised, the user is guided to choose to answer them.

[0041] Preferably, the speech dialogue unit 12 further includes a plurality of agents based on the large model, the plurality of agents including: a decision maker, an opinion collector and a detail miner, wherein:

[0042] Multiple agents based on the large model are used to combine the content parameters, and in the process of conducting a voice dialogue with the user around the topic content, collaboratively ask questions to the user, and form a current dialogue record when the voice dialogue ends; wherein:

[0043] The decision maker is used to control the rhythm of asking for details and changing the topic. Based on the rhythm of asking for details and changing the topic, the decision maker determines the working time and work goals of the opinion collector and detail miner, and forms a record of the current conversation at the end of the voice conversation.

[0044] The opinion collector is responsible for determining the era background according to the voice dialogue that has been generated, and forming corresponding questions based on the common sense of the era background. The corresponding questions include at least one of the following: emotional identification, contradictory assumptions and opinion inquiries; wherein the method of determining the era background includes: searching for era background information on the Internet to determine the era background according to the voice dialogue that has been generated;

[0045] A detail miner is responsible for mining stories related to a specific event and / or a specific person mentioned, raising questions based on the stories related to the specific event and / or a specific person, and adding the stories related to the specific event and / or a specific person as supplementary content to the current conversation record;

[0046] Among them, if it is not the first time for the user to generate a documentary story, the multi-agent based on the big model will start a voice dialogue with the user around the topic content, and use the memory link as the opening remark of the voice dialogue to ask questions to the user; after that, for each group of voice dialogues, the multi-agent based on the big model will ask at least one question at the same time. When there are at least two questions raised, the user is guided to choose to answer them.

[0047] Preferably, the story generating unit 13 includes a first generating subunit and a second generating subunit. After each voice dialogue unit forms a current dialogue record, the first generating subunit or the second generating subunit generates a documentary story, wherein:

[0048] The first generation subunit is used to select a text style after the voice conversation ends. According to at least one group of voice conversations selected from the current conversation record and the selected text style, the text style has generation rules and algorithms for generating a documentary story that conforms to the artistry and reflects the life and personality of the user from the conversation record; through a synthesis key, according to the generation rules and algorithms, the at least one group of voices selected in the current conversation record are integrated into a narrative story draft. If the user modifies it through the edit key, the modified story draft is used as a documentary story. If the user does not modify it, the story draft is used as a documentary story. The generated documentary story is in the form of text, voice or video;

[0049] The second generation subunit is used to select a writing style after the voice conversation ends, and generate a documentary story through multiple steps according to the writing style and the current conversation record; generating a documentary story through multiple steps according to the writing style and the current conversation record includes:

[0050] First, automatically generate a clue that runs through the entire text based on the current conversation record; second, enhance the artistry of the article for the current conversation record. Methods for enhancing the artistry of the article include: polishing the beginning, adding descriptions of the environment, and increasing dialogues; third, adjust the structure of the article by setting suspense to increase the interest of the documentary story. Methods for setting suspense include: different time jumps and character perspective restrictions; fourth, generate a documentary story based on the generation rules and algorithms corresponding to the style. The generated documentary story is in text form, voice form, or video form.

[0051] Preferably, the documentary story writing system further comprises an analysis unit, which is arranged in the documentary story writing system or in a remote server, and is used to:

[0052] Convert the current conversation into text form;

[0053] Analyze the current conversation record in text form, generate continuation questions based on the current conversation record, use the continuation questions as memory links for opening remarks of the next voice conversation on the same topic, and save the memory links in a database;

[0054] Analyze the current conversation record in text form, extract basic information from the current conversation record, the basic information includes: gender, age, family members, hometown, health status, education level and highest honor, compare the extracted basic information with the basic information in the database, and update or replace the same basic information in the database;

[0055] Analyze the current conversation record in text form, extract the core elements related to mobilizing memory and writing memoirs from the current conversation record, and save them to the database. The core elements include: relevant dates, relevant people, memories, major life experiences, major events, and personal preferences;

[0056] Analyze the current conversation record in text form, extract key information other than core elements from the current conversation record, compare the extracted key information with key information in a database, and update, replace or not process similar key information in the database;

[0057] Among them, the key information includes: core elements, and historical conversation records whose semantic similarity with the current conversation record is higher than the similarity threshold;

[0058] User information includes: core elements and basic information.

[0059] Preferably, the documentary story writing system further includes a music generation unit, a picture generation unit and a video generation unit, wherein:

[0060] The music generation unit arranges the documentary story into a poem through a large model, inputs the poem as a prompt word into the music generation large model, and generates a song in combination with the music style selected by the user;

[0061] The image generation unit is used to extract the picture elements in the documentary story (for example, bicycles, plum blossom bricks at the foot of the city gate, catching butterflies at the foot of the hill, and stealing melons in the field) and generate corresponding text for the picture elements. The text is a more concise text description. The text is input as a prompt word into an open source model for image generation (for example, stablediffusion) after stylized fine-tuning to generate an image.

[0062] The video generation unit is used to receive photos that users can upload through the picture import unit, and generate corresponding short videos for the photos and the generated pictures respectively by calling the video generation API service interface, and use the short videos, set matching texts and music as video materials, and splice these video materials into a video.

[0063] In combination with an embodiment of the present invention, a documentary story writing device is provided, wherein the documentary story writing device has a visual interface or does not have a visual interface, and the documentary story writing device includes:

[0064] A processor; and a memory arranged to store executable instructions, wherein when the executable instructions are executed, the processor is implemented by any of the aforementioned documentary story writing systems;

[0065] The documentary story writing device also includes:

[0066] Start and Remake keys, used to enter a documentary story writing mode, or re-enter another documentary story writing mode;

[0067] A dialogue control key is used to activate the dialogue control key to enter the voice dialogue mode, and to generate a documentary story through the theme setting unit, the voice dialogue unit and the story generation unit.

[0068] Preferably, the documentary story writing device further comprises: a conversation history list, where the user reviews previous conversation records;

[0069] A conversation record display unit, implemented through a conversation record display key, is used to view the conversation content;

[0070] Story list, used to view all generated documentary stories. Click to enter the story display page for editing and sharing;

[0071] A story generation unit, capable of generating and editing a documentary story;

[0072] Story Square, for browsing documentary stories shared by other users, with like and comment buttons;

[0073] Memory Cards, used to view your own story memory cards on the page.

[0074] like Figure 2 As shown, combined Figure 3 The steps of implementing the documentary story writing system of the embodiment of the present invention include the following:

[0075] 1. Guide users to determine the topic of the conversation, and extract content parameters related to the specific topic from the database (topic material database). The content parameters are used for the initial direction and depth of the conversation, ensuring that the conversation is directional and purposeful. The database is pre-built and contains the core story guiding factors of various topics, such as the cause of the event, the relationship between the characters, etc., to ensure the richness and pertinence of the conversation content.

[0076] (1) Specifically, the user is guided to start a conversation by selecting a preset topic such as childhood impressions, childhood playmates, family memories, educational enlightenment, etc. through a physical key, touch key, or physical key without a UI interface, and automatically matching the most relevant topic tag based on the user's short description. A custom topic conversation can also be started. Topic tags include but are not limited to: childhood playmates, family memories, youth friendship; and also include some other personalized, optional topics: military career, foreign country, etc. Among them, topic tags, such as character relationships, life events, emotional changes, etc. These tags are based on historical data, literary works and psychological research, and are classified, organized and labeled by a professional team.

[0077] (2) In a custom topic dialogue, the system will first guide the user to speak out the content that the topic may contain. The content has sparse and fragmented plots (information points). Through the big model, these are connected together with a certain logic to define the content of this topic) to obtain the initial topic, and then define and expand the topic content to obtain the final topic. The background can also be expanded. The steps of expanding the topic may include multiple calls to the big model (even online retrieval) to expand, select and refine the topic content. For example, the big model is used to ask the user what story he wants to tell. It supports the adaptation of multiple large pre-trained language models (hereinafter collectively referred to as big models), such as: GPT-4, GLM-4, Dark Side of the Moon, Wenxin Yiyan, Tongyi Qianwen, etc.

[0078] For users who have no usage history, we will start with open-ended questions about a topic, such as "childhood home", and then based on the user's answers, we will ask questions about topics that the user may be interested in and that can enrich the content of their personal story.

[0079] If there are accumulated conversation records of the user, the system will ask questions based on the user's background. For example, "You mentioned the story of picking wild vegetables before. Would you like to talk about it again this time?" Then the system will automatically adjust the details of the question or switch to a new topic. For example, "Did you find any other fun at your grandma's house?", "Then let's change the topic. Who was your best friend in childhood?"

[0080] Content parameters may include some examples of colloquial, topic-related questions and descriptions of topic-related conversation strategies. For example: What were your school conditions like when you were a kid? How did you go to school? Is there anyone to go with you? When a user mentions a character and indicates that they have a close relationship, ask about the character's background in detail to try to understand the character's behavior and decisions.

[0081] (3) For various topics, we have extracted plot-guiding factors such as event types, causes of conflicts, character relationships, and personal feelings from a large amount of non-fiction literature. We have transformed these plot-guiding factors into inspiring questions, stored them in the database, and used them as prompts to guide the large model to ask questions during conversations.

[0082] 2. Obtain user information related to the topic: After guiding the user to determine the topic of the documentary story through the preset information collection unit, the basic information of the user is obtained from the database (user information database), and the system can extract key information from the user's narration, such as date, important events of related people, preferences, etc., and compare and supplement this information with the key historical information in the database. At the same time, it is given as background knowledge to the big model. The advantage is that the big model will not ask repeated questions many times when chatting with the user, such as how many people are there in the family.

[0083] The large model itself does not have "memory ability", so memory management has become an important issue in building applications based on large models. Excessive memory storage will not only cause high costs and delays, but also reduce user experience, and increase the complexity of instructions, which poses a challenge to the ability of existing large models to follow instructions. The embodiment of the present invention extracts the core elements of key information related to mobilizing memory and writing memoirs from the interaction records between users and the system for storage. The core elements include but are not limited to: memories about people, major life experiences, personal preferences, etc.

[0084] Core elements: Currently include dates, related people, major events, preferences, extracted from past conversation records.

[0085] Key information: includes core elements and historical conversation records with high semantic similarity to the current conversation.

[0086] User information: This concept is the largest. It includes core elements, key information, and other basic information: gender, age, hometown, education level, highest honor, etc.

[0087] 3. The system uses a large language model to dynamically adjust the dialogue strategy and conduct dynamic dialogue management around the subject content (i.e., topic). It combines the set initial direction and depth of the dialogue, and guides users to share their personal experiences and emotions in depth through intent recognition, sentiment analysis tools, and context management technology to form a dialogue record. In particular, the system analyzes the user's emotional response and topic adaptability in real time during the conversation. If the user shows hesitation or discomfort, the system will automatically switch to a more soothing topic or adopt a more delicate questioning method (guided by the large model through prompt words). Questioning strategies include: open-ended questions, focusing on personal resumes, asking about situational details, exploring event contradictions, paying attention to the feelings of the interviewee, guiding the topic, etc.

[0088] In order to improve the user experience, the big model asks questions for non-first conversations, especially in the first sentence of each conversation to attract users by establishing memory links. Specifically, the conversation will first echo the last conversation, and then the questions asked are based on the known content of the last conversation, and cut from a different angle. For example: Last time we talked about your family having parents and a brother, and the experience of visiting your grandma's house was also very interesting, so what is the most unforgettable time you spent with your family? Are there any fixed family activities or traditions?

[0089] After the conversation on each topic is over, a memory link is generated in advance as the opening statement for the next conversation to ensure the memory link between the new conversation and the old conversation.

[0090] (1) Single agent: The dialogue format includes two parts: emotional feedback and continued questioning. Emotional feedback strategies include but are not limited to confirming positive emotions and soothing negative emotions. Continued questioning strategies include but are not limited to open-ended questions, continuing to explore a certain character, asking for event details, scenario descriptions, contradictory assumptions, inquiring about feelings, and switching topics. For each group of voice dialogues, the single agent based on the large model asks at least one question at the same time. When there are at least two questions raised, the user is guided to choose from them to answer. The number of questions can be set according to the size of the user interaction interface and the user's operation difficulty. For example, in the web version, three questions can be issued at the same time, and the user can choose one of the three to answer, thereby providing the user with the freedom to control the direction of the story.

[0091] (2) Multi-agent: A good interview needs to consider many factors, such as: controlling the rhythm of asking details and changing the topic according to the user's response; combining emotional identification, contradictory assumptions, and opinion inquiries with common sense of the times; comparing the information collected with the elements required for a good story, and judging the next question. Elements include, for example, the user only provided scattered information "Once I mixed up my sheep with someone else's sheep, and the old man didn't get angry, but just quietly sorted the sheep again." This lacks story elements: what kind of person is the old man, who was there at the time, why did he mix up the sheep, and what lessons did he learn afterwards.

[0092] With the intelligence capabilities of existing large models, it is difficult to take all aspects into consideration at the same time, so a multi-agent collaborative information collection solution is adopted. Depending on the cost and delay acceptance of the usage scenario, a multi-agent model can be selected. The system can include but is not limited to three agents: decision makers, opinion collectors, and detail miners.

[0093] Decision makers determine when and to what end the idea gatherers and detail miners work.

[0094] The opinion collector is responsible for searching the Internet for information to obtain the historical context. For example, if he determines that the character's experience fits the label "going into business in the 1980s", he will search the Internet for controversial points related to this, and then combine this with common sense of the historical context to conduct emotional identification, contradictory assumptions, and opinion inquiries.

[0095] Detail miners are responsible for unearthing stories about specific events and specific people, which are used to supplement the conversation record and can also be used to elicit questions to enrich the content of the conversation.

[0096] 4. Store the conversation records in the database and extract key information from them as user memory.

[0097] After the conversation is over, the current conversation record is formed, the content of the current conversation record is analyzed, key information such as major events, emotional changes, etc. are extracted, and stored for subsequent use. Multiple key information related to the topic is extracted from the conversation record, and these key information are matched and updated with the user's existing information, such as updating health status or changes in family members. The purpose is to manage the user memory stored in the database. Because if the user memory only increases and does not decrease, it will cause confusion, so the comparison and replacement method is adopted to manage the user memory.

[0098] In order to improve the accuracy of information processing and reduce redundancy, the traditional vector calculation semantic similarity technology is not used, but the memory is maintained through the topic unit. A large-scale language model, i.e. a large model, is used to judge story generation and memory update. By analyzing the relevance and information density of the conversation content, it is decided whether to update or replace the memory unit of a specific topic. This can avoid memory conflicts, improve the relevance of memory, and ensure that only sufficiently important or detailed information is updated.

[0099] At the beginning of each conversation, the system automatically generates an engaging opening statement based on updated topic-related memory links, aiming to increase the fun of the conversation and attract user engagement.

[0100] 5. Generate a story based on the conversation record and the style selected by the user, as shown in 6. The system designs corresponding generation rules and algorithms for different text styles (such as documentary, romantic, tragic, etc.) to ensure that the story not only conforms to literary artistry, but also accurately reflects the user's life and personality. The story generation module uses a hybrid algorithm that combines rule-driven and data-driven methods. The rule-driven part builds the story skeleton based on the basic rules of literary creation (for example: adding a sketch of the environment, filling in the dialogue between characters, using specific and vivid details to explain the emotions of the characters, etc.), while the data-driven part uses a deep learning model to fill in specific details and emotional colors. Users can choose the tone of the story (such as simplicity, strong literary color, sensational, etc.), and the system will adjust the story content according to these preferences to ensure that each story reflects the user's personality and emotions.

[0101] (1) The system allows users to quickly integrate a short story draft into a plain narrative by selecting only a group of dialogues and a style. The user can modify it if he wants. I provide editable functions (such as text boxes) on the application, which can view the dialogue records of a certain year, month, and day at a certain time in the morning on the front end of the software. For example, the first dialogue record generated by Grandma Liu is: OK, when I was a child, I always lived at my grandma's house. There were three or four houses around, so I often ran around with her during the summer vacation...; the second one is: We don't build houses with complex structures, such as very high towers, and now I think...

[0102] (2) At the same time, users can also generate more artistic articles through multiple steps. The first step is to use the dialogue material to determine an obvious clue that runs through the entire article. The second step is to enhance the artistry of the article by polishing the beginning, adding environmental descriptions, and dialogues. The third step is to set up suspense again through different time jumps, character perspective restrictions, and other information arrangements, and adjust the article structure again to add interest.

[0103] For example, part of the description of user Grandma Liu in the conversation record is:

[0104] Grandma Liu: Actually, I don’t remember much about these.

[0105] Grandma Liu: He has always been the solution for all the major and minor illnesses in our family. For example, if I have a fever, I go there to get an injection. I broke my leg and rested for half a year. I also went there to change the medicine every time. Including my grandfather who got cancer and died, he also took Chinese medicine there. Although I knew it was useless, they can always take care of you there, at least it seems to be professional medical support. It’s really a good model. In the city now, which patient doesn’t have some complaints about the hospital. I don’t know if excellent medical skills are what our society should really pursue.

[0106] Grandma Liu: Yes, you are absolutely right. The connections in the village are very close. There are always people to help you with everything. It is difficult for you to do anything alone. It seems that whatever you do will have an impact on a large group of people.

[0107] Generate a draft of all the descriptions of Grandma Liu this time, and then save the draft. The generated draft is:

[0108] In that foggy childhood, Hao Yinsu was my inseparable friend. She was timid, and learning to ride a bicycle was a huge adventure for her. I, who had already been riding in the wind, was willing to slow down and be her solid support. Whenever it rained and the muddy road became muddy, we would abandon the car and walk. It was a long but beautiful way to school. Our laughter echoed in the thick fog, and the frost on our eyebrows looked like Santa Claus' beard, filling our world with fairy-tale warmth.

[0109] I remember one time, Yinsu was unable to ride a bike due to illness, so I skipped class to take her home. That time, she had a determined light in her eyes, and was determined to learn how to ride a bike. Finally, in junior high school, she succeeded, although she could only ride but not stop, and she needed to rely on the steps or my help every time she got on and off the bike. I always rode a little faster and waited for her in front. Her panicked shout of victory still echoes in my ears.

[0110] During that time, I became her protector, and a sense of pride arose spontaneously. I accompanied her, semester after semester, rain or shine. The warmth in her heart and the pride in my eyes became the most solid bridge of our friendship.

[0111] However, as the years passed, we each embarked on different journeys of life. Work, marriage, we are like sands scattered by the torrent of time, each settled in a corner of life. Our contact gradually decreased, but the time we spent together, the road we walked with each other in the wind and snow, still shines with eternal light in my heart. Hao Yinsu, she is the warmest page in my childhood memory, always worth my affectionate reading.

[0112] A documentary story writing system or documentary story writing system device of an embodiment of the present invention is a story sharing application for elderly users, which records and generates personal stories by talking with a large language model. The application supports multiple theme selections, conversation record preservation, historical conversation viewing, story generation and editing, story sharing and other functions. It aims to provide a convenient platform for elderly users to record their life experiences and share them with others. It can tell life stories by talking with a large language model, review and edit recorded conversations and generated stories, share generated stories with family and friends, and increase the fun of use through customized themes and Easter egg themes.

[0113] The documentary story writing system device may have a visual interface, or it may be, for example Figure 3 As shown, the specific work of the software and hardware dual front-ends can be combined to explain the process of using the documentary story writing system equipment as follows:

[0114] 1. The front end is responsible for user registration and login. The user presses the "Start / Remake" button on the hardware terminal to start the conversation. The conversation with the user is completed through the voice conversation unit. The voice of the user is collected through the voice collection unit of the hardware terminal, and the voice is recorded and sent to the server for further processing. Allow the user to choose to hold down the "Talk" button to speak, or the natural phone is voice interaction. Among them, in the process of corresponding with the user, for the user's reply, the big model converts the response into audio through Text-to-Speech (TTS) technology.

[0115] 2. As needed, pictures can be imported through the picture import unit and displayed in the image display unit; after the conversation is over, a documentary story can be generated through the story generation unit; users can view the "conversation history list" to review the conversation records at a certain time in the morning of a certain year, month, and date. For example:

[0116] A: Hello! It's a pleasure to chat with you. I heard that your childhood was full of warm stories about your hometown and neighbors, which I am very interested in. Can you share with me some interesting stories about your childhood and your neighbors?

[0117] B: Okay, when I was little, I lived at my grandma's house. My cousin lived three or four houses away from me, so I often played with her during the summer vacation. His grandma took care of him, and my grandma took care of me. She was only one year younger than me. My house was next to my aunt's house. She had a grocery store. We often went there to buy snacks. I think we bought half of them. I remember that the most common thing we bought was bubble gum. And across from my house was a hereditary doctor's family. When I was little, whether I had a fever or a broken bone, I would go there to see a doctor. I would get well with an injection.

[0118] A: Hearing you say that, it seems that your childhood was full of warmth and joy. The bubble gum you mentioned reminded me of the taste of my childhood. What was that taste like? Also, when you played with your cousin, were there any particularly memorable games or experiences?

[0119] B: I remember at my cousin's house, there was a plastic toy car with a hole at the bottom. We looked inside the hole. There was probably a small plastic button inside, but my sister insisted it was a piece of candy. We tried our best to find...

[0120] 3. Users can select a conversation record and enter the "Conversation Record Display" page to view the conversation content. Users can choose to generate a story and enter the "Story Generation" page to generate and edit a story.

[0121] 4. Users can view all generated stories in the "Story List" and click to enter the "Story Display" page for further editing and sharing.

[0122] 5. Users can browse stories shared by other users in the "Story Square", like and comment on them. Users can view their own user memories on the "Memory Card" page.

[0123] The beneficial technical effects achieved by the embodiments of the present invention are as follows:

[0124] 1. Provide a friendly and interactive platform for elderly users to easily tell and record their life stories. This can reduce the initial thinking burden of users in the article creation process, and there is no need to have a detailed idea of ​​the story in advance.

[0125] 2. Automatically allocate open-ended questions, detailed questions and emotional confirmation strategies to better explore and reflect users' personal experiences and emotional states. High-quality story generation and editing functions improve user satisfaction.

[0126] 3. Increase user stickiness and promote user interaction through story sharing and story square functions.

[0127] 4. The generated articles are closer to the user's real feelings and personal style, which improves the personalization of the text and the reader's resonance. It supports the adaptation of multiple large models, that is, large pre-trained language models, such as GPT-4, GLM-4, Dark Side of the Moon, Wen Xin Yi Yan, Tong Yi Qian Wen, etc. It can instantly connect to the interfaces of other large models when a large model does not work, so it has good flexibility and high robustness.

[0128] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0129] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0130] The disclosed embodiments are described above to enable any person skilled in the art to implement or use the present invention. Various modifications of these embodiments are obvious to those skilled in the art, and the general principles defined herein may also be applied to other embodiments without departing from the spirit and scope of the present disclosure. Therefore, the present disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.

[0131] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

[0132] Those skilled in the art may also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention may be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly demonstrate the interchangeability of hardware and software, the various illustrative components, units, and steps described above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present invention.

[0133] The various illustrative logic blocks or units described in the embodiments of the present invention can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of the above. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any conventional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0134] The steps of the method or algorithm described in the embodiments of the present invention can be directly embedded in hardware, a software module executed by a processor, or a combination of the two. The software module can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or other storage media of any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a user terminal. Optionally, the processor and the storage medium can also be arranged in different components in the user terminal.

[0135] In one or more exemplary designs, the above functions described in the embodiments of the present invention can be implemented in hardware, software, firmware or any combination of the three. If implemented in software, these functions can be stored on a computer-readable medium, or transmitted in the form of one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media that facilitate the transfer of computer programs from one place to another. The storage medium can be any available medium that can be accessed by any general or special computer. For example, such computer-readable media can include but are not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store program codes in the form of instructions or data structures and other forms that can be read by general or special computers, or general or special processors. In addition, any connection can be appropriately defined as a computer-readable medium, for example, if the software is transmitted from a website site, server or other remote resource through a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wirelessly, such as infrared, wireless and microwave, it is also included in the defined computer-readable medium. The disk and disc include compact disk, laser disk, optical disk, DVD, floppy disk and blue-ray disk. Disks usually copy data magnetically, while discs usually copy data optically with lasers. The above combination can also be included in computer readable media.

[0136] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A documentary story writing system, characterized in that: include: A theme setting unit, used to guide the user to determine the theme of the documentary story, and extract content parameters related to the theme from the database according to the theme; The voice dialogue unit is used to conduct a voice dialogue with the user around the subject content based on the large model combined with the content parameters, identify the user's reply intention, manage the dialogue context, explore and raise questions, dynamically guide the user to share personal experiences and emotions, and form a current dialogue record when the voice dialogue ends; The story generating unit is used to generate a documentary story according to the writing style and the current conversation record after the writing style is selected by the user.

2. The documentary story writing system according to claim 1, characterized in that: The theme setting unit includes a first theme setting subunit or a second theme setting subunit: The first theme setting subunit is used to guide the user to select a theme from preset themes as the theme of the documentary story through dialogue on the UI interface or by pressing buttons; The second theme setting sub-unit is used to guide the user to speak out the content information points that the theme may contain through the big model, and to connect all the content information points in series through logic to obtain an initial theme, and to expand, select and refine the content information points and theme background of the initial theme through the big model to obtain the final theme; wherein, in the process of the big model expanding, selecting and refining the content information points and theme background of the initial theme, the Internet connection can be used for retrieval.

3. The documentary story writing system according to claim 1, characterized in that: The theme setting unit also includes: A content parameter extraction unit, used to extract plot guiding factors related to the theme from the database, and to extract inspiring questions corresponding to the plot guiding factors, and to use the inspiring questions as content parameters related to the theme. The content parameters are used as prompt words during voice dialogue, and guide the big model to ask questions to the user when the big model conducts a voice dialogue with the user around the theme content; Among them, the database stores plot guiding factors of various topics and inspiring questions converted from the plot guiding factors. The plot guiding factors are extracted from non-fiction literature, and the extracted plot guiding factors include at least: event type, cause of conflict, character relationship and personal feelings.

4. The documentary story writing system according to claim 1, characterized in that: Also includes: The information collection unit is used to obtain the user's basic information from the database and provide it to the big model if it is not the first time for the user to generate a documentary story. After guiding the user to determine the theme of the documentary story, the basic information of the user is provided to the big model. The obtained basic information of the user is used to avoid repeated questions to the user during the process of the big model having a voice dialogue with the user around the theme content, wherein the basic information includes: gender, age, hometown, education level and highest honor.

5. The documentary story writing system according to claim 1, characterized in that: The speech dialogue unit includes a single agent based on a large model, which is used to: In combination with the content parameters, in the process of engaging in a conversation with the user around the topic content, an emotional feedback strategy is used to ask questions to the user, and a current conversation record is formed when the voice conversation ends; The emotional feedback strategy includes: confirming positive emotions and soothing negative emotions; or, The single agent based on the large model combines the content parameters, and in the process of conducting a voice dialogue with the user around the topic content, adopts a continuous questioning strategy to ask questions to the user, and forms a current dialogue record when the voice dialogue ends; the continuous questioning strategy includes: open-ended questions, continuing to explore a certain character, asking about event details, situation description, contradictory assumptions, asking about feelings and switching topics; Among them, if it is not the first time for the user to generate a documentary story, the single agent based on the large model will start a voice conversation with the user around the topic content, and use the memory link as the opening remark of the voice conversation to ask questions to the user; afterward, for each group of voice conversations, the single agent based on the large model will ask at least one question at the same time. When there are at least two questions raised, the user is guided to choose to answer them.

6. The documentary story writing system according to claim 1, characterized in that: The speech dialogue unit also includes multiple intelligent agents based on the large model, including: decision makers, opinion collectors and detail miners, among which: Multiple agents based on the large model are used to combine the content parameters, and in the process of conducting a voice dialogue with the user around the topic content, collaboratively ask questions to the user, and form a current dialogue record when the voice dialogue ends; wherein: The decision maker is used to control the rhythm of asking for details and changing the topic. Based on the rhythm of asking for details and changing the topic, the decision maker determines the working time and work goals of the opinion collector and detail miner, and forms a record of the current conversation at the end of the voice conversation. The opinion collector is responsible for determining the era background according to the voice dialogue that has been generated, and forming corresponding questions based on the common sense of the era background. The corresponding questions include at least one of the following: emotional identification, contradictory assumptions and opinion inquiries; wherein the method of determining the era background includes: searching for era background information on the Internet to determine the era background according to the voice dialogue that has been generated; A detail miner is responsible for mining stories related to a specific event and / or a specific person mentioned, raising questions based on the stories related to the specific event and / or a specific person, and adding the stories related to the specific event and / or a specific person as supplementary content to the current conversation record; Among them, if it is not the first time for the user to generate a documentary story, the multi-agent based on the big model will start a voice dialogue with the user around the topic content, and use the memory link as the opening remark of the voice dialogue to ask questions to the user; after that, for each group of voice dialogues, the multi-agent based on the big model will ask at least one question at the same time. When there are at least two questions raised, the user is guided to choose to answer them.

7. The documentary story writing system according to claim 1, characterized in that: The story generating unit includes a first generating subunit and a second generating subunit. After each voice dialogue unit forms a current dialogue record, a documentary story is generated by the first generating subunit or the second generating subunit, wherein: The first generation subunit is used to select a text style after the voice conversation ends. According to at least one group of voice conversations selected from the current conversation record and the selected text style, the text style has generation rules and algorithms for generating a documentary story that conforms to the artistry and reflects the life and personality of the user from the conversation record; through a synthesis key, according to the generation rules and algorithms, the at least one group of voices selected in the current conversation record are integrated into a narrative story draft. If the user modifies it through the edit key, the modified story draft is used as a documentary story. If the user does not modify it, the story draft is used as a documentary story. The generated documentary story is in the form of text, voice or video; The second generation subunit is used to select a writing style after the voice conversation ends, and generate a documentary story through multiple steps according to the writing style and the current conversation record; generating a documentary story through multiple steps according to the writing style and the current conversation record includes: First, automatically generate a clue that runs through the entire text based on the current conversation record; second, enhance the artistry of the article for the current conversation record. Methods for enhancing the artistry of the article include: polishing the beginning, adding descriptions of the environment, and increasing dialogues; third, adjust the structure of the article by setting suspense to increase the interest of the documentary story. Methods for setting suspense include: different time jumps and character perspective restrictions; fourth, generate a documentary story based on the generation rules and algorithms corresponding to the style. The generated documentary story is in text form, voice form, or video form.

8. The documentary story writing system according to claim 1, characterized in that: The system further comprises an analysis unit, which is arranged in the documentary story writing system or in a remote server, and is used for: Convert the current conversation into text form; Analyze the current conversation record in text form, generate continuation questions based on the current conversation record, use the continuation questions as memory links for opening remarks of the next voice conversation on the same topic, and save the memory links in a database; Analyze the current conversation record in text form, extract basic information from the current conversation record, the basic information includes: gender, age, family members, hometown, health status, education level and highest honor, compare the extracted basic information with the basic information in the database, and update or replace the same basic information in the database; Analyze the current conversation record in text form, extract the core elements related to mobilizing memory and writing memoirs from the current conversation record, and save them to the database. The core elements include: relevant dates, relevant people, memories, major life experiences, major events, and personal preferences; Analyze the current conversation record in text form, extract key information other than core elements from the current conversation record, compare the extracted key information with key information in a database, and update, replace or not process similar key information in the database; Among them, the key information includes: core elements, and historical conversation records whose semantic similarity with the current conversation record is higher than the similarity threshold; User information includes: core elements and basic information.

9. The documentary story writing system according to claim 1, characterized in that: It also includes a music generation unit, a picture generation unit and a video generation unit, wherein: The music generation unit arranges the documentary story into a poem through a large model, inputs the poem as a prompt word into the music generation large model, and generates a song in combination with the music style selected by the user; The picture generation unit is used to extract the picture elements in the documentary story and generate corresponding texts for the picture elements, and input the texts as prompt words into the stylized fine-tuned picture generation open source model to generate pictures; The video generation unit is used to receive photos that users can upload through the image import unit, and generate corresponding short videos for the photos and the generated images respectively by calling the video generation API service interface, and splice them into a video according to the arrangement order of the short videos adjusted by the user, the matching texts set, and the music.

10. A documentary story writing device, characterized in that: The documentary story writing device has a visual interface or does not have a visual interface, and the documentary story writing device includes: A processor; and a memory arranged to store executable instructions, which, when executed, cause the processor to implement the documentary story writing system according to any one of claims 1 to 9; The documentary story writing device also includes: Start and Remake keys, used to enter a documentary story writing mode, or re-enter another documentary story writing mode; A dialogue control key, which is activated to enter a voice dialogue mode, and to generate a documentary story through a theme setting unit, a voice dialogue unit and a story generation unit; The documentary story writing device also includes: Conversation history list, where users can review previous conversation records; A conversation record display unit, implemented through a conversation record display key, is used to view the conversation content; Story list, used to view all generated documentary stories. Click to enter the story display page for editing and sharing; A story generation unit, capable of generating and editing a documentary story; Story Square, for browsing documentary stories shared by other users, with like and comment buttons; Memory Cards, used to view your own story memory cards on the page.

Images