Method and system for generating bionic hierarchical memory fusion document of large electric semantic model

Abstract

The invention provides an electric power semantic large model bionic hierarchical memory fusion document generation method and system, and relates to the technical field of document generation, and the method comprises the steps: extracting knowledge in a multi-modal data form, building a long-term memory library through simulating a memory mechanism of a human hippocampus, and generating a multi-modal data form; the knowledge in the long-term memory library is stored and dynamically updated in a hierarchical manner according to three levels of sentences, paragraphs and chapters; inputting a new document generation task into the electric power semantic large model, and taking the long-term memory library as an external knowledge source of the electric power semantic large model; dynamically searching knowledge of each level related to the current task from a long-term memory library; and iteratively fusing the context background knowledge and the knowledge dynamically searched from the long-term memory library layer by layer, and finally generating complete document content. By dynamically calling long-term memory and multi-level context processing, logically coherent and information-accurate contents are generated, multi-modal data are effectively integrated, and the method is suitable for efficient generation of complex documents such as construction schemes and audit reports.

Description

Technical Field

[0001] The present disclosure relates to the technical field of document generation, and in particular to a method and system for generating documents of a large-scale bionic hierarchical memory fusion model of electric power semantics. Background Art

[0002] As the digital transformation of the power industry deepens, the demand for document generation is increasing and becoming more complex, especially in the fields of infrastructure, auditing, and equipment operation and maintenance. The documents are diverse in type and complex in content, requiring high-precision and coherent text output. At the same time, these documents often involve the integration and processing of a large amount of multimodal information such as historical data, images, and tables. Traditional document generation systems are mostly based on templates, which are difficult to adapt to complex scenarios and cannot flexibly respond to the content generation needs required for different tasks. Moreover, this generation mode usually lacks effective management of long-term memory and is difficult to handle dependencies within and across documents, especially in the power industry. Documents involving a large amount of historical records and contextual information are prone to logical incoherence or information omissions during the generation process.

[0003] At the same time, with the development of large model technology, retrieval-augmented generation (RAG) has become the main solution for large language models (LLMs) to achieve memory, and has made significant progress in the field of text generation. However, the current RAG method still faces challenges in long-distance dependency, contextual understanding, and multimodal data fusion when helping LLMs complete tasks that require integrating new knowledge across multiple text fragments; these challenges are particularly prominent in the generation of long documents, such as construction plans, audit reports, and other power industry documents, which require not only accuracy and logical consistency of content, but also the integration of multiple data forms such as images, tables, and charts.

[0004] Therefore, existing document generation technologies, especially complex and long documents in the power industry, have deficiencies in long-distance dependency, contextual understanding, and multimodal data fusion, resulting in the inability to generate documents accurately and efficiently. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method and system for generating documents based on a bionic hierarchical memory fusion of a large electric power semantic model. Based on the large electric power semantic model, the method and system generates logically coherent and accurate content by dynamically calling long-term memory and multi-level context processing, and effectively integrates multimodal data such as text, images, and tables. The method is suitable for the efficient generation of complex documents such as construction plans and audit reports.

[0006] According to some embodiments, the present disclosure adopts the following technical solutions: The method for generating documents of bionic hierarchical memory fusion of electric power semantic large model includes: Extract knowledge in the form of multimodal data from historical document data, build a long-term memory bank by simulating the memory mechanism of the human hippocampus with the help of bionics, and store and dynamically update the knowledge in the long-term memory bank in three levels: sentences, paragraphs, and chapters; The task of generating new documents is input into the electric power semantic big model, and the long-term memory is used as the external knowledge source of the electric power semantic big model; through semantic analysis and personalized retrieval algorithm, the knowledge of various levels related to the current task is dynamically searched from the long-term memory; according to the hierarchical order of sentences, paragraphs and chapters, the contextual background knowledge and the knowledge dynamically found from the long-term memory are iteratively integrated layer by layer to finally generate the complete document content.

[0007] According to some embodiments, the present disclosure adopts the following technical solutions: The electric power semantic large model bionic hierarchical memory fusion document generation system includes a memory library construction module and a document generation module: The memory library construction module is configured to: extract knowledge in the form of multimodal data from historical document data, build a long-term memory library by simulating the memory mechanism of the human hippocampus with the help of bionics, and hierarchically store and dynamically update the knowledge in the long-term memory library at three levels: sentences, paragraphs, and chapters; The document generation module is configured as follows: inputting the task of generating a new document into the electric power semantic big model, and using the long-term memory as the external knowledge source of the electric power semantic big model; dynamically searching for knowledge of various levels related to the current task from the long-term memory through semantic analysis and personalized retrieval algorithms; iteratively integrating the contextual background knowledge and the knowledge dynamically found from the long-term memory layer by layer according to the hierarchical order of sentences, paragraphs and chapters, and finally generating complete document content.

[0008] According to some embodiments, the present disclosure adopts the following technical solutions: A computer program product includes a computer program, which, when executed by a processor, implements the method for generating a bionic hierarchical memory fusion document of a large electric power semantic model.

[0009] According to some embodiments, the present disclosure adopts the following technical solutions: A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method for generating a bionic hierarchical memory fusion document of a large electric semantic model is implemented.

[0010] According to some embodiments, the present disclosure adopts the following technical solutions: An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the method for generating a bionic hierarchical memory fusion document of a large electric semantic model.

[0011] Compared with the prior art, the present invention has the following beneficial effects: Aiming at the special needs of document generation in the power industry, based on the power semantic big model, this paper proposes a document generation method that integrates bionic long-term memory and hierarchical context merging. By simulating the memory mechanism of the human hippocampus, a long-term memory library is established, and historical related knowledge is dynamically called during the generation process to keep the generated content highly consistent with the needs of the current task; at the same time, the method adopts a hierarchical context processing framework to hierarchically integrate the information of sentences, paragraphs and chapters to make the content coherent and logically consistent; it also integrates multimodal data (such as images, tables, etc.) with the text generation process to ensure that the generated documents meet the professional standards of the power industry, and can cope with the challenges of long-distance dependency and multimodal data integration in large language model text generation, significantly improving the coherence and information accuracy of long document generation, and providing an intelligent and efficient solution for the generation of complex documents such as construction plans and audit reports in the power industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0013] Figure 1 This is a flow chart of the method of Example 1. Figure 2 This is an example diagram of the knowledge graph of the long-term memory bank in Example 1. DETAILED DESCRIPTION

[0014] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0015] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0016] Example 1 In one embodiment of the present disclosure, a method for generating a bionic hierarchical memory fusion document of a large power semantic model is provided, such as Figure 1 As shown, including: Step S1: Extract knowledge in the form of multimodal data from historical document data, build a long-term memory bank by simulating the memory mechanism of the human hippocampus with the help of bionics, and store and dynamically update the knowledge in the long-term memory bank in three levels: sentences, paragraphs, and chapters; Step S2: Input the task of generating a new document into the electric power semantic big model, and use the long-term memory as the external knowledge source of the electric power semantic big model; dynamically search for knowledge of various levels related to the current task from the long-term memory through semantic analysis and personalized retrieval algorithms; iteratively integrate the contextual background knowledge and the knowledge dynamically found from the long-term memory layer by layer according to the hierarchical order of sentences, paragraphs and chapters, and finally generate the complete document content.

[0017] As an embodiment, the disclosed method for generating documents by bionic hierarchical memory fusion of electric power semantic big model generates logically coherent and accurate information by dynamically calling long-term memory and multi-level context processing, and effectively integrates multimodal data such as text, images, and tables. It is suitable for efficient generation of complex documents such as construction plans and audit reports. The specific implementation process is as follows: Step 1: Extract knowledge in the form of multimodal data from historical document data. With the help of bionics, build a long-term memory bank by simulating the memory mechanism of the human hippocampus, and store and dynamically update the knowledge in the long-term memory bank in three levels: sentences, paragraphs, and chapters.

[0018] The bionic idea here is to simulate the powerful human contextual long-term memory system, which relies on the interaction between the neocortex and the hippocampus and consists of the following three parts: Neocortex: The neocortex is responsible for receiving and processing sensory stimuli, transforming them into higher-level, manipulable features. The neocortex primarily processes and stores actual memory representations, ensuring that the perceived information can be further transmitted in a structured form.

[0019] Parahippocampal Regions (PHR): The parahippocampal region connects the neocortex and the hippocampus, acting as an information relay. It routes sensory signals processed by the neocortex to the hippocampus and assists in the encoding and indexing of memories. It also acts as a bridge during memory retrieval, transmitting signals from the hippocampus back to the neocortex for simulation.

[0020] Hippocampus: The hippocampus is responsible for creating the "hippocampal index," a collection of memory units and their associations. In memory storage, the hippocampus ensures that representations of different perceptual experiences are unique through pattern separation; in memory retrieval, the hippocampus restores complete memories from partial cues through pattern completion. This indexing mechanism of the hippocampus allows new information to be integrated by updating the index rather than the neocortical memory representation.

[0021] In view of the above three parts, this embodiment designs a method for constructing a long-term memory bank. The function of the neocortex is simulated by the large language model LLM. LLM is responsible for extracting perceptual signals, similar to the neocortex converting perceptual stimuli into high-level feature representations. It is the information processing center of the entire system and is responsible for generating specific knowledge representations; the personalized PageRank algorithm (PPR) is more in line with the function of the parahippocampal region. PPR uses the structure of the knowledge graph in the retrieval process to find the subgraph most relevant to the context based on the query nodes (Query Nodes), which plays a role in linking the features extracted by the neocortex with the associations in the knowledge graph. By guiding the retrieval process, it ultimately helps information flow to the "hippocampus", similar to the role of the parahippocampal region as a bridge connecting the neocortex and the hippocampus. The PPR algorithm realizes accurate matching and filtering of the context; the constructed knowledge graph (KG) Analogous to the hippocampus, the knowledge graph, as the core "memory index" of the system, records the nodes and relationships in the document, and realizes pattern separation and pattern completion through its structure; during retrieval, the PPR algorithm activates query-related paths in the knowledge graph, which represent the extraction and reconstruction of memory. This design simulates the key role of the hippocampus in storing and retrieving associative memories.

[0022] Specifically, in step 1.1, all documents and historical generation records are analyzed, and the power large language model (LLM) is used to identify core concepts, keywords, and key data points as noun phrases or events, which are stored in the form of text, images, and tables.

[0023] The noun phrase or event here can be a single word, a term, a sentence, or a paragraph, depending on several factors: 1) Core concepts and subject terms: These are usually expressed as noun phrases, keywords or terms, which can be single words (such as "electricity", "substation"), phrases (such as "power equipment failure", "operating status") or more complex noun phrases (such as "equipment maintenance record"); these terms help to capture key information in the document and dynamically call it during the generation process.

[0024] 2) Key data points: This includes numbers, statistics, time information or other structured data (such as values ​​in a chart or rows and columns in a table); this data can be stored as a single data point (such as "voltage value", "operating time") or a more complex structure in a table.

[0025] 3) Sentences or paragraphs: For complex documents, especially those with contextual content, sentences or paragraphs may become storage units; for example, when generating an audit report, you may need to store a complete sentence or paragraph to preserve the integrity of the context (such as "the equipment has exceeded the specified number of working hours"). These sentences or paragraphs contain important background information or semantic context, which helps to integrate knowledge when generating documents later.

[0026] Step 1.2, by simulating the memory mechanism of the human hippocampus, build a long-term memory library to store and dynamically update knowledge in a hierarchical structure to ensure efficient retrieval and coherence of information in document generation.

[0027] In order to ensure the accessibility of information, the extracted knowledge is constructed into a multi-level knowledge graph. Each knowledge node represents a noun phrase or event. When establishing the knowledge graph, the memory characteristics of the human hippocampus are borrowed. By adding multiple synonymous relationships and hyponymous relationships, the knowledge graph has stronger relevance and scalability, and a long-term memory library in the form of a knowledge graph is obtained.

[0028] In the construction of long-term memory, referring to the memory indexing and retrieval process in HippoRAG, knowledge can be represented as a graph structure, and knowledge nodes are associated through relationships, as shown in the following figure: Figure 2 The knowledge graph of the long-term memory library shown in the figure is G=(V,E), where V represents the set of knowledge nodes, E is the set of edges connecting the knowledge nodes, and each knowledge node v∈V represents a noun phrase or event. Represents the semantic relationship between these knowledge.

[0029] The edges here include: 1) Multiple Synonymy A synonym relationship indicates that two nodes have semantically similar or equivalent meanings. For example, in the power industry, "substation" and "power transformer station" can be connected by a synonym relationship because they refer to the same type of facility.

[0030] 2) Hierarchical Relations The hierarchical relationship represents the hierarchical structure between nodes, that is, one node is the superior or subordinate of another node; the superior node (parent node) represents a more abstract concept, while the subordinate node (child node) represents a more specific instance or detail. For example, power equipment is the superior concept of substation, and distribution equipment is a type of power equipment, so it is a subordinate relationship.

[0031] 3) Other common relationship types Causal Relationships: Used to indicate the cause-effect relationship between events or behaviors, for example, "equipment failure" may be caused by "overload".

[0032] Temporal Relationships: Indicates the temporal order between nodes. For example, "Inspection Report" is generated after "Equipment Maintenance".

[0033] Spatial Relationships: Used to represent the spatial location relationship between nodes, such as "power lines are located near substations."

[0034] Functional Relationships: Indicates the functional dependency between nodes, for example, “substation” is responsible for “power dispatching”.

[0035] Determining the relationship between nodes usually depends on the following aspects: Semantic analysis: Perform semantic analysis on nodes through a large language model (such as LLM) to identify the potential relationships between them. For example, use a large language model to extract relevant descriptions from a document and automatically identify the causal relationship between "fault" and "repair."

[0036] Domain knowledge: Based on the expertise of the power industry, knowledge graphs are used to define standard relationships within the industry. For example, the relationship between power equipment and equipment maintenance is usually functional or causal.

[0037] Contextual relationship: By analyzing the context of nodes, it is determined whether there is a temporal, spatial or hierarchical relationship between them. For example, when describing a substation, it may be automatically associated with its geographical location and the equipment it contains.

[0038] The graph structure of the long-term memory library in this embodiment simulates the hierarchical storage method of different knowledge in the human brain, so that information can be directly located and retrieved to specific content according to context requirements in subsequent calls; this process not only improves the richness of the knowledge base, but also ensures the system's ability to respond quickly to complex power document generation needs.

[0039] Furthermore, after the information is extracted and constructed as a knowledge graph, the extracted knowledge is further refined and classified and stored at different levels such as sentences, paragraphs, and chapters. Each level corresponds to a specific content unit in document generation, making it easy to call it by level.

[0040] For example, sentence-level knowledge nodes are stored at the micro level and used to generate detailed descriptions; chapter-level nodes contain macro-background information and key policy content, which are used to guide the structure of the overall document.

[0041] In addition, a dynamic update mechanism is introduced to monitor the correlation between new tasks and historical generation records, and integrate the latest generated knowledge fragments into the memory bank. Through this continuous update, it can be ensured that the information in the memory bank always remains relevant to the current generation task. This mechanism effectively addresses the problem of knowledge expiration in long document generation, so that the most timely key information can be called in different generation scenarios, achieving a high degree of unity between professionalism and accuracy.

[0042] Step 2: When generating new documents, information that is highly relevant to the current task is dynamically called from the long-term memory bank through semantic analysis and personalized retrieval algorithms to ensure the coherence of the generated content and its consistency with historical knowledge.

[0043] After receiving the generated task, the task content is first semantically analyzed through natural language processing technology to identify the subject words, core requirements and important concepts. Based on the identified key information, a preliminary match is made in the memory library, and similarity calculations are performed with the nodes in the library to identify the memory fragments most relevant to the current task; through this associated node identification mechanism, not only can the basic knowledge required for the task be extracted, but also context support can be provided for subsequent content generation, achieving accurate information retrieval and effective integration.

[0044] The memory fragments here are the specific content or long content of the nodes in the long-term memory library, and the nodes are high-level summaries of the memory fragments, which are general labels; each node represents the knowledge abstraction of a specific field, or "conceptual label", for example, the node can be "substation equipment installation standard", "equipment failure record", etc.; these nodes point to actual, detailed memory fragments, which are high-level abstractions of specific content, helping the system to better organize and retrieve information. Memory fragments contain detailed, specific text content or multimodal data (such as images, tables, documents, etc.), which are longer content (such as the entire equipment maintenance record, or a detailed description of a certain equipment failure), and they provide a more specific knowledge base for the system.

[0045] The initial matching here uses a semantic matching algorithm, with the help of the node relationship and semantic similarity in the graph, to accurately locate the most relevant knowledge points. Taking "generating an audit report on substation equipment maintenance" as an example, the specific process is as follows: 1) Receive tasks and perform semantic analysis Suppose you receive a task to generate an audit report on substation equipment maintenance. The task content is as follows: “Please generate an audit report on the maintenance of substation equipment to check whether the equipment meets the installation standards, whether there are any faults, and whether the maintenance records are complete.” Through the large language model, the task content is analyzed to extract keywords, core requirements and important concepts: Keywords: Substation, Equipment Maintenance, Audit Report Core requirements: Check whether the equipment meets the installation standards, check whether the equipment has faults, and whether the maintenance records are complete 2) Perform a preliminary match in the memory bank The keywords and core requirements identified in the task will be used as input for preliminary node matching in the memory. The memory here is a graph containing many conceptual nodes (such as "equipment installation standards", "equipment maintenance records", "equipment failures", etc.), each of which represents an abstract knowledge unit in the knowledge graph.

[0046] The role of node relationships: Each node not only contains content (memory fragments) related to it, but also establishes semantic connections with other nodes through edges (relationships); for example, there may be an "inclusion" relationship between the "equipment installation standard" node and the "substation" node, indicating that the equipment installation standard applies to all equipment in the substation.

[0047] These node relationships are used in the matching process to determine which knowledge points should be prioritized. For example, the "equipment failure" node may find maintenance records related to "failure" through the "solution" relationship with the "equipment maintenance" node.

[0048] 3) Similarity calculation and semantic matching algorithm Once the nodes are determined, the semantic similarity between the task description and the nodes in the knowledge graph is calculated. The specific process is as follows: Vectorization: Each node (such as “equipment maintenance record”, “equipment installation standard”) and keywords in the task are converted into high-dimensional vectors through a large language model.

[0049] These vectors represent the semantic information of nodes and facilitate similarity calculation.

[0050] Calculate semantic similarity: The task content vector and node vector are matched by cosine similarity (or other similarity algorithms) to calculate the semantic similarity between each task keyword and the node.

[0051] The calculation formula of cosine similarity is as follows:

[0052] in, is the task description and the node vector, . represents the dot product, is the norm of the vector, and the larger the value, the more similar it is.

[0053] Matching tasks and nodes: Based on the calculated similarity, the node most relevant to the task description and its associated memory fragments will be selected. For example, if the task mentions "check whether the equipment meets the installation standards", it will be matched to the "equipment installation standards" node, and the memory fragments related to the node will be selected. 4) Optimize matching with node relationships In addition to similarity calculations, matching results are optimized based on node relationships, for example: Hierarchical relationship: If the task requires checking equipment failure, the system will find a more specific failure type (such as "equipment overload failure") through the "Equipment Failure" node and further refine the results based on the "Failure Repair" node.

[0054] Causal relationship: If the task description mentions that "equipment failure" may require "equipment maintenance", the system will provide detailed information related to the fault repair through the causal relationship of the "fault repair" node and the fault repair record.

[0055] With the help of these relationships, the system can accurately locate the memory fragments most relevant to the task and provide the necessary contextual information for subsequent report generation.

[0056] Furthermore, after the initial matching of relevant nodes, a personalized PageRank algorithm is used to perform retrieval on the knowledge graph to dynamically call up key information in the memory bank. The algorithm adjusts the weights of different nodes to prioritize the retrieval of knowledge that is highly relevant to the current task and embeds these contents directly into the generation process. Through the dynamic calling mechanism, the knowledge that best fits the context can be called at each generation stage to avoid repeated calculations, thereby improving generation efficiency and consistency. For documents that require long-distance dependencies, such as complex construction plans or multi-chapter audit reports, historical information fragments related to the task, that is, the knowledge in the long-term memory bank, can be continuously called up to maintain consistency and logical coherence during the generation process, while ensuring the professionalism and accuracy of the generated content.

[0057] The following is an explanation of the PageRank algorithm: Assume that a task q is given and the personalized PageRank (PPR) algorithm is used to query the knowledge nodes most relevant to the task, which can be expressed as:

[0058] Among them, P(v i )、P(v j ) represents node v i 、v j The importance in the current query, N(v i ) is the node v i The set of neighbor nodes in the knowledge graph, is the initial distribution, and usually a higher initial value is set for query-related nodes. α is an adjustment parameter that controls the probability of random jumps. Through this algorithm, relevant nodes in the memory library can be dynamically called to ensure that the retrieved knowledge can accurately meet the needs of the current document generation task.

[0059] In the PageRank algorithm, the initial distribution refers to the "importance" weight initially assigned to each node in the graph, which is usually equal or set according to certain specific rules; it is usually closely related to the prior knowledge or task relevance of the nodes in the network; for each node v i , the initial distribution is usually It defines the "importance" or "score" of the node at the beginning of the algorithm, that is, each node 𝑣 𝑖 At the beginning, each node has an initial distribution value, that is, the "initial importance" of the node in the network. These initial values ​​can be set according to the characteristics of the node, the requirements of the task, or the design of the algorithm.

[0060] In practical applications, the basis for setting the initial distribution is mainly based on the following considerations: (1) The initial values ​​of all nodes are equal: In the simplest case, the PageRank algorithm assumes that the initial importance values ​​of all nodes are equal, so that all nodes have the same influence at the beginning of the algorithm, and then dynamically adjusts the "importance" of each node through algorithm iteration. This method is suitable when there is no obvious priority or preference in the network. The formula is:

[0061] in, is the total number of nodes. In this case, the initial value is an average and has little to do with the initial matched nodes. It is more based on the assumption of "no prior knowledge".

[0062] (2) Set initial values ​​based on task relevance: If there is prior information about the task (such as the node type or domain required by the task), the initial value can be set based on the importance and relevance of the node.

[0063] Example: Assume that the task requires the generation of an audit report related to equipment installation standards. If the "Equipment Installation Standards" node If it is mentioned in the task description or appears to be particularly important, we can set a higher initial value for this node.

[0064] Node-task relevance: For example, if the task description mentions "equipment installation standards", then nodes related to "equipment installation standards" will get a higher initial value based on the results of the semantic matching algorithm. In this way, the initially matched nodes (such as the "equipment installation standards" node) will start with a higher initial distribution , to reflect its importance in the task.

[0065] (3) Set initial values ​​based on graph structure: Sometimes, the initial values ​​of nodes can also be set based on structural information in the graph. For example, nodes with higher in-degree (i.e., more edges connected to it) may be more important, so their initial values ​​may be higher.

[0066] For nodes , if it has more incoming edges (that is, more other nodes point to it), then its initial value It will be set higher to adjust the initial weight of the node based on the in-degree or out-degree.

[0067] There is a direct relationship between the initially matched nodes and the initial distribution. In the task description, nodes related to the task requirements will be assigned higher initial values ​​to ensure that these nodes can have a greater impact on the task results in the initial stage; for example, if the task is to generate an equipment maintenance report for a substation, the system will set a higher initial distribution for the "equipment maintenance record" node based on its relevance to the task, thereby maintaining its high importance in the entire algorithm.

[0068] Step 3: Divide the document generation process into sentence, paragraph, and chapter levels, and ensure the logical coherence and professionalism of the generated content at each level by integrating contextual background knowledge and key information in the long-term memory bank layer by layer.

[0069] The contextual background knowledge and key information here are retrieved from the long-term memory bank, the difference is: Contextual background knowledge refers to all information related to the current document generation task, usually including the background of the task, industry knowledge, context requirements, historical information of the task description, etc. This information helps to ensure that the document generation is logically coherent and professional; Contextual background knowledge mainly comes from the long-term memory bank, which stores historical information related to the task, previously generated content, and long-term stored knowledge points, including: (1) Generation records of previous tasks: including reports or document fragments similar to the current task.

[0070] (2) Industry norms and standards: such as relevant laws and regulations of the power industry, equipment operation standards, etc., which can provide the necessary background support for document generation.

[0071] (3) Context of historical tasks: For example, if the document generation task is about an audit report on equipment maintenance, the content of previous equipment maintenance audit reports can be used as background knowledge reference.

[0072] (4) This information helps the system maintain contextual consistency when generating documents and ensures the logical coherence between the newly generated content and the previously generated content.

[0073] Key information is the specific information mentioned in the task requirements. This information determines the core content of the generated document and provides the system with knowledge points that need to be focused on in the execution of specific tasks. Nodes are retrieved from the long-term memory library: In the long-term memory library, nodes represent specific pieces of knowledge. They are key points in document generation. For example, if the task requires the generation of an equipment maintenance report, the "equipment maintenance record" and "equipment failure log" nodes stored in the long-term memory library will be retrieved; if the task requires the inspection of equipment installation standards, the "equipment installation standards" node and related specific content in the long-term memory library will be extracted; these nodes contain detailed information related to the task (such as equipment specifications, historical records, standard requirements, etc.), and the system uses the information in these nodes to generate specific report paragraphs.

[0074] Contextual background knowledge mainly helps the system to ensure the coherence and consistency of content when generating documents. For example, when generating equipment maintenance reports, the system needs to understand the industry standards and the requirements of similar tasks in history. Therefore, the system retrieves relevant nodes and historical task information from the long-term memory to construct the background part of the document to ensure that the content meets industry standards; key information directly affects the specific content of the report. For example, if the task requires "check whether the equipment meets the installation standards", the system will retrieve the nodes related to "equipment installation standards" from the long-term memory, extract the specific standard requirements, and generate task-related paragraphs accordingly; therefore, it is necessary to integrate contextual background knowledge and key information in the long-term memory.

[0075] Specifically, at the sentence level, firstly, semantically clear sentences are generated by calling relevant knowledge (i.e. key information) in the long-term memory bank and combining it with the background information of the current task (i.e. contextual background knowledge). In this process, the theme and structure of the sentence are analyzed to ensure that each sentence is semantically independent and clear while being consistent with the context. In order to lay the foundation for paragraph generation, the semantic relationship between sentences is automatically detected while generating sentences, and the master-slave relationship, causal relationship and other associations are marked. These marking information are crucial in the subsequent paragraph integration; in this way, not only the accuracy of each sentence is ensured, but also the basis for the smooth connection of the paragraph level is provided.

[0076] According to the hierarchical processing method of HOMER with hierarchical context fusion, the sentence generation in the lth level can be expressed as:

[0077] in, represents the hidden state generated by the previous layer, is the knowledge retrieved from the long-term memory bank or the context, and f is the generating function.

[0078] Furthermore, at the paragraph level, the sentences generated in the previous step are integrated according to contextual markers (i.e., marked semantic relationships) to give the paragraph a coherent logical structure and thematic consistency. At the same time, contextual background knowledge in the long-term memory bank is referenced according to the theme of the paragraph. For example, relevant construction standards and regulations are called up in paragraphs involving power construction to make the content more comprehensive and in line with industry specifications.

[0079] The paragraph theme here is the core idea of ​​the paragraph content. It is the key basis for selecting relevant background knowledge and organizing sentences when generating paragraphs. The paragraph theme is mainly obtained in the following ways: (1) Extract from the task description: Directly extract the topic: The task objective or description usually contains the keywords or focus of the paragraph topic. For example: Task description: "Generate reports on electrical construction safety." The theme extracted from the large model: "Electric Power Construction Safety".

[0080] (2) Inference from contextual information: During paragraph generation, the large language model will automatically extract the topic based on the sentence content generated in the previous paragraph. For example: The previous article mentioned "equipment installation standards", and the topic of the current paragraph may continue to be "safety of equipment installation".

[0081] (3) Combining high-frequency nodes in the long-term memory bank: During the generation process, semantic analysis is used to find high-frequency knowledge nodes in the long-term memory bank that are relevant to the task. For example: If the paragraph content involves "construction standards", the knowledge nodes related to "construction specifications" are extracted, and the large model further refines the paragraph theme as "application scenarios of construction specifications".

[0082] (4) Extraction of main clauses, subordinate clauses and core sentences: Within the paragraph, mark which sentences are the core content (main sentences), and then use the topic of the core sentence as the core of the paragraph.

[0083] Furthermore, at the chapter level, the paragraphs are further integrated and analyzed as a whole to ensure that the chapter content is logically and thematically coherent; at this time, the chapter background knowledge is called (the chapter theme is extracted through the task description, and the background knowledge related to the theme is directly matched as the chapter background knowledge), an introduction is generated for the beginning of the chapter, and a summary paragraph is generated at the end to provide overall support; through this hierarchical integration, the system can finely manage contextual information at each level, so that the generated documents maintain high-quality logical consistency and professionalism from sentences to chapters.

[0084] In order to merge contexts at the level, HOMER uses a recursive split and merge strategy. In the hierarchical merging process, Hierarchical Context Embedding Merging is introduced. The specific steps are as follows: 1. Divide long text into several chunks

[0085] 2. Perform preliminary processing on each block and generate embedding H through the self-attention mechanism i .

[0086] The preliminary processing here includes dividing the long text into several blocks, segmenting and embedding each block, and using block embedding to fuse the adjacent text block embeddings. Through the self-attention mechanism or weighted averaging, the model merges the semantic information of different blocks, so that the generated content can reflect the common semantics of multiple blocks.

[0087] 3. In the high-level merging process, adjacent context blocks are gradually merged into a larger block. The merged embedding can be expressed by the following formula:

[0088] Here, g is the merging function, which may include weighted averaging, concatenation, or other processing methods.

[0089] In the HOMER model, high-level usually refers to the incorporation of larger context units in document generation, including but not limited to: Sentences are combined to form paragraphs: Combine multiple independently generated sentences into a logically coherent paragraph.

[0090] The merging here usually needs to consider the semantic relationship between sentences (such as causality, progression, etc.).

[0091] Paragraphs are combined to form chapters: Merge multiple paragraphs to create a larger chapter unit.

[0092] At this point, it is necessary to analyze the relevance of the paragraph topics and generate transitional content connecting the paragraphs.

[0093] Chapters are combined to form a complete document: At the document level, the chapter contents are integrated into a coherent whole to form the final generated document.

[0094] When merging, you need to ensure the logical consistency between chapters and generate an overall introduction and summary.

[0095] Therefore, the high level is relative to the lower level sentence or word processing, and mainly refers to the merging of context units at the paragraph, chapter and document levels.

[0096] 4. Further context integration is performed on the merged blocks to ensure the consistency of global context information.

[0097] When performing high-level integration, large language models (such as GPT) not only refer to block embeddings, but also combine the specific text content and background knowledge of each block to ensure that the generated text is globally logically consistent, semantically fluent, and meets the task objectives, including the following steps: Weighted embeddings and contextual adjustments: Chunk embeddings are weighted based on the importance of each chunk, the relevance of the topic, and the connection between the context, so that the merged chunks are more in line with the global context; for example, some chunks may be more important than others in a certain chapter, and the model will adjust based on this.

[0098] Background knowledge injection: During the integration process, background knowledge is injected through two channels: Global background knowledge: The large model introduces standard knowledge (such as laws and regulations, industry specifications, etc.) in the long-term memory bank, making text generation more in line with real-world standards and requirements.

[0099] Local background knowledge: For a specific block, the system can also introduce knowledge in a specific field to supplement and improve the information based on the content of the block.

[0100] Generate logical and thematically consistent text: Finally, the integrated text will be further adjusted and optimized by the model to ensure the thematic consistency, logical fluency and professionalism of the text. The system will adjust the output according to the theme, target task and context of the paragraph or chapter to ensure that the text smoothly and accurately expresses the information.

[0101] Specifically, at each generation level, by integrating multimodal data forms such as text, images, and tables, we ensure that the content of the generated documents is not only rich and diverse but also complies with power industry standards, further improving the structural integrity of the documents and the effectiveness of information communication.

[0102] Furthermore, during the generation process, the needs of paragraph or chapter content are analyzed to determine whether it is necessary to embed multimodal data such as images and tables to enhance the comprehensiveness of information expression; for example, when generating equipment operation reports, relevant tables, drawings or images are dynamically called and embedded to more intuitively display the operating status and technical details of the equipment. By associating with multimodal information in the long-term memory library, the most appropriate multimodal data fragments are identified (these multimodal data fragments are vectorized pictures or tables, and the closest ones are found by matching the similarity with the text vectors, and then the original pictures or tables are inserted), and naturally combined with the text content, so that readers can understand the content from multiple perspectives, rather than relying solely on text descriptions, thereby effectively improving the readability and professionalism of the document.

[0103] In this scenario, the large language model will analyze the input text content, understand the complexity of the text, its structural requirements, and the needs of data presentation, and then determine whether multimodal data such as images and tables are needed to enhance the text expression based on these features. This process is explained in detail below.

[0104] (1) Analyze the content requirements of paragraphs or chapters The large language model analyzes the following aspects to determine whether an image or table needs to be embedded: 1) Complexity of content Data-intensive content: When a paragraph or chapter involves a large number of numbers, statistics, parameter comparisons, experimental results, etc., a table is usually the most appropriate way to present this information. The model will determine whether it is necessary to convert it into a table based on the amount and complexity of the data; for example: if the text describes different performance indicators of multiple devices (such as power, efficiency, age, etc.), the model may think that a table is needed to clearly compare these data.

[0105] Visualization requirements: When the paragraph description involves spatial relationships, flow charts, or system architecture, images (such as flow charts, structure diagrams, schematic diagrams, etc.) are necessary, because this information is difficult to describe clearly in words in the text, and images can provide a more intuitive understanding; example: If the paragraph involves the workflow of the power system, the model may determine whether it is necessary to generate and embed a system flowchart based on the context requirement of "power system flowchart".

[0106] 2) Limitations of language expression Expression of abstract concepts: For some abstract concepts or complex processes, simple text descriptions may be difficult for readers to understand. At this time, charts can provide intuitive help; Example: When describing the installation process of power equipment, there may be complex steps and details, and the text expression may not be clear enough. At this time, a flowchart can be used to clearly display each step of the operation.

[0107] 3) Structured information requirements Structured data presentation: If the data contained in a paragraph needs to be presented in a list, comparison, or time series format, the model will determine whether it needs to be presented in a table. Example: When describing the regular maintenance cycle of power equipment, the model will recognize that this type of information is suitable for presentation in a table, which includes the equipment name, inspection frequency, maintenance content, etc.

[0108] (2) Specific steps to determine whether a chart is needed to assist in display 1) Extraction and analysis of content topics Analyze task objectives: The model extracts the main task objectives and themes of a paragraph or chapter and identifies whether the task requires a chart or image to assist in expression. For example, if the content of a paragraph is about the comparison of device performance, the model will determine that the content can be presented in a table.

[0109] Paragraph analysis: The model analyzes sentences and keywords in a paragraph to identify whether it involves information that needs to be presented in a structured manner, such as data, processes, comparisons, time series, etc. For example, for a paragraph containing keywords such as "comparison", "changing trends", and "system processes", the model may consider that a chart is helpful in presenting the content.

[0110] 2) Data and information density in a sentence or paragraph Identify data volume: The large language model analyzes the density of data mentioned in the paragraph, such as "equipment efficiency", "failure rate" and other quantitative data. When there is a lot of data, the model will suggest using a table to improve the readability of the information.

[0111] Image requirement analysis: For paragraphs describing spatial relationships, system layouts, or processes, the model will determine whether images are needed to aid understanding. For example, if a paragraph describes a complex equipment installation process or the architecture of a power system, the model will recommend inserting an image to improve clarity.

[0112] 3) Language model generation suggestions Based on the above analysis, the model generates a decision whether a chart needs to be inserted and generates or suggests the type of chart to be inserted as needed.

[0113] (3) Embedding multimodal data When the model determines that a chart or table needs to be inserted, it calls a multimodal image or table library. The library stores various standard charts, tables, and diagrams. After vectorization, the charts and tables can be retrieved, matched, and called in an efficient way. The matching is performed through the following steps: 1) Generate vectorized representation of content requirements Requirements analysis: The large model will analyze the content of the current paragraph and identify chart requirements, such as: A performance comparison of the equipment needs to be shown.

[0114] The step-by-step process of equipment installation needs to be demonstrated.

[0115] The relationship between failure rate and maintenance period needs to be shown.

[0116] These requirements are converted into vector representations that capture the semantics and structure of the requirement.

[0117] 2) Retrieval and matching of chart library Similarity calculation: The model matches the generated demand vector with all the charts or tables in the chart library. This step determines the matching degree by calculating the cosine similarity or other distance metrics between the demand vector and the vector of each chart / table in the library; Example: If the current paragraph needs to show the device performance comparison, the model will retrieve the tables related to "device performance comparison" from the table library, calculate the similarity between these tables and the input requirements, and find the best matching table.

[0118] 3) Choose an appropriate chart or table Based on the matching results, the model selects the most appropriate chart or table. The selection criteria include: Content fit: Does the chart or table accurately reflect the data or process in the paragraph?

[0119] Format matching: Whether the format of the chart or table matches the requirements of the paragraph.

[0120] Presentation effect: readability and clarity of charts or tables, etc.

[0121] 4) Creation and insertion of charts or tables Chart generation: For some specific data, the model may generate new charts, such as generating a line chart or a bar chart based on the data in a paragraph.

[0122] Insertion of charts or tables: The generated or selected charts / tables will be embedded in the text and displayed with the corresponding content. The description in the text will be consistent with the content of the chart / table to ensure that readers can understand the data or process in the text based on the chart.

[0123] Furthermore, after the multimodal data is embedded, the images, tables and other elements are carefully typeset according to the standards of the power industry documents to ensure that the data layout meets the requirements of the specifications. At the same time, a brief description text will be automatically generated for each multimodal element (i.e., multimodal data) to help readers quickly understand the core information of the chart or image; these descriptions not only include an overview of the chart content, but also indicate its specific use and significance in the current document. Through the typesetting and annotation of multimodal data, it is ensured that the document has both visual hierarchy and complies with industry standards, so that the professionalism and readability of the content are further improved, thereby meeting the high-standard information presentation requirements of the power industry in documents such as construction reports and equipment operation records.

[0124] The detailed layout here is as follows: (1) Document structure analysis, structural tagging of text and multimodal elements Perform structural analysis on the document and mark out elements such as titles, paragraphs, images, tables, etc., so that it can be laid out according to the type and hierarchical relationship of the content.

[0125] (2) Application of templates and styles Template usage: Automatic typesetting can be based on templates, which define the position, spacing, alignment, etc. of each element of the document. These templates can be designed according to the standards of power industry documents to ensure that all generated documents meet the specifications. For example, in power industry documents, tables and images usually have fixed alignment, and the width and height of the table are also specified. The automatic typesetting system will adjust these parameters according to the template.

[0126] (3) Automatic adjustment of page margins and line spacing Automatically adjust page margins and line spacing: The automatic typesetting system will automatically adjust the document's page margins, line spacing, paragraph spacing, etc. according to the standards of power industry documents, making the entire document look neater and more compliant.

[0127] In the process of iteratively generating document content layer by layer, by gradually progressing at the sentence, paragraph and chapter levels and dynamically calling the long-term memory library and contextual background knowledge, we ensure that the document content is logically coherent, accurate and in compliance with industry standards.

[0128] Furthermore, in the document generation process, starting from the sentence level and gradually building upwards, the logical consistency of content generation is ensured by dynamically calling relevant knowledge in the long-term memory bank at each level; first, the sentence level focuses on accurately presenting basic concepts and specific details to ensure the high relevance of sentences and contextual information; then, entering the paragraph level, relevant sentences are integrated, and background knowledge related to the paragraph topic is introduced to enhance the logical consistency and information integrity of the paragraph; finally, at the chapter level, the overall structure of the chapter content is analyzed, each paragraph is integrated and high-level background knowledge is introduced to ensure that the chapter content is coherent and organized; by dynamically calling relevant knowledge layer by layer, high-quality information transmission and logical construction are guaranteed in the entire document generation process.

[0129] The overall structure of the analysis chapter content here includes: (1) Chapter topic extraction and analysis In order to determine the core theme of the chapter and ensure that each paragraph and sentence serves the theme, the large language model will analyze the beginning, middle and end of the chapter to extract the subject words and keywords. Usually, the chapter title, paragraph subheadings and the first paragraph of the chapter will provide clear clues. The model can also determine the theme of the chapter through text classification or keyword extraction; for example: if the chapter title is "Installation and Maintenance of Power Equipment", the system will extract relevant keywords from the content of the chapter, such as "Equipment Installation", "Technical Requirements", "Maintenance Frequency", etc., to confirm that each part of the content meets this theme.

[0130] (2) Logical relationships between paragraphs and sentences In order to ensure that there is a clear logical connection between paragraphs within a chapter and avoid information gaps or duplication, the model will analyze the transitions and connections between paragraphs to ensure that each paragraph has a clear position and role in the chapter structure. The system uses natural language processing technology or large models to identify the relationships between paragraphs (such as progressive relationships, contrast relationships, causal relationships, etc.) and optimize the connections between paragraphs based on these relationships; for example: if paragraph 1 introduces "equipment installation standards" and paragraph 2 discusses "equipment commissioning and inspection", the model will ensure that the relationship between the two is clear and may insert transition sentences, such as "After the equipment is installed, the equipment needs to be debugged and inspected to ensure its normal operation." (3) Hierarchical structure of chapters To ensure that the chapter content is organized in a logical order and has a clear structure, at the chapter level, the model integrates paragraphs hierarchically; common chapter structures include: Introduction: This summarizes the main content of the chapter, usually including the background of the problem, the objectives and the general flow.

[0131] Main content: includes specific technical details, data analysis, step-by-step instructions, etc., divided into logical and chronological sections.

[0132] Conclusion: A summary of the chapter content, possibly with suggestions for further research or practice.

[0133] For example, in the chapter on installation and maintenance of power equipment, the model will integrate the equipment installation standards, commissioning steps, maintenance frequency, etc. into the main part, and may add equipment performance evaluation or long-term maintenance recommendations at the end.

[0134] (4) Completeness and coherence of information within the chapter In order to ensure that the content of each paragraph is self-consistent and each paragraph has its reasonable position in the overall chapter, and to avoid content duplication or deviation from the topic, the large language model dynamically analyzes and adjusts the chapter structure to ensure the integrity of the paragraph content. The detailed description within the paragraph should be highly relevant to the topic and logically consistent with the previous and next paragraphs. For example: If a paragraph describes "the installation standard of power equipment", the next paragraph may describe "how to check the compliance of equipment installation". There should be a smooth transition between the two to ensure that information is not missed and the topic is consistent.

[0135] The retrieval methods for high-level background knowledge and low-level background knowledge are similar. The difference is that the low-level background knowledge is matched with low-level topics and keywords, while the high-level background knowledge is matched with high-level subjects and keywords. After matching the high-level and low-level memory fragments, the large model will perform text processing, and GPT has strong summarization capabilities.

[0136] At the chapter level, the specific steps to analyze the structure of the chapter content and introduce high-level background knowledge are as follows: Analyze chapter structure: By analyzing the paragraph level, determine the core content of the chapter and the relationship between the paragraphs (such as progression, cause and effect, contrast, etc.). At the same time, the model will extract information such as chapter titles and paragraph subheadings to help identify the theme of the chapter.

[0137] Calling background knowledge: Based on paragraph content: Based on the topic of each paragraph, the model extracts relevant background knowledge from the long-term memory bank. For example, when describing the maintenance of power equipment, the model can call "equipment maintenance standards" as background knowledge to ensure that the content is complete and in line with industry standards.

[0138] Global background knowledge: When generating a chapter as a whole, the system will extract global background knowledge from the library based on the theme of the chapter, such as the latest regulations and technical standards in the power industry, to ensure that the chapter content is not only in-depth but also meets the latest industry requirements.

[0139] Integrate generated content: Combine the generated content of each paragraph with high-level background knowledge to ensure that each part of the content is logical and complete. Each part of the chapter will be connected to the previous and next paragraphs and information to ensure that the entire chapter has good coherence.

[0140] Furthermore, after the chapter generation is completed, the entire document content is automatically verified according to the standards of the power industry with the help of Wenxinyiyan or GPT, including logical consistency, information integrity and professionalism. The verification process will check whether each chapter meets the document requirements of the power industry, such as the standards for construction reports and equipment operation records, by comparing industry specifications and document content structure. In addition, optimization adjustments will be automatically made to modify parts with inconsistent structures or lengthy contents to ensure that the document meets high-standard hierarchical requirements when it is finally output; verified and optimized documents can meet the power industry's needs for complex documents, achieve logically rigorous, comprehensive content and highly professional output, and make it highly readable and reference value in practical applications.

[0141] Example 2 In one embodiment of the present disclosure, a system for generating documents of a large-scale bionic hierarchical memory fusion of an electric power semantic model is provided, including a memory library building module and a document generating module: The memory library construction module is configured to: extract knowledge in the form of multimodal data from historical document data, build a long-term memory library by simulating the memory mechanism of the human hippocampus with the help of bionics, and hierarchically store and dynamically update the knowledge in the long-term memory library at three levels: sentences, paragraphs, and chapters; The document generation module is configured as follows: inputting the task of generating a new document into the electric power semantic big model, and using the long-term memory as the external knowledge source of the electric power semantic big model; dynamically searching for knowledge of various levels related to the current task from the long-term memory through semantic analysis and personalized retrieval algorithms; iteratively integrating the contextual background knowledge and the knowledge dynamically found from the long-term memory layer by layer according to the hierarchical order of sentences, paragraphs and chapters, and finally generating complete document content.

[0142] Example 3 In one embodiment of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method for generating a bionic hierarchical memory fusion document of a large electric power semantic model.

[0143] Example 4 In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method for generating a bionic hierarchical memory fusion document of a large electric semantic model is implemented.

[0144] Example 5 In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the method for generating a bionic hierarchical memory fusion document of a large electric semantic model.

[0145] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A method for generating documents based on bionic hierarchical memory fusion of a large power semantic model, characterized in that: include: Extract knowledge in the form of multimodal data from historical document data, build a long-term memory bank by simulating the memory mechanism of the human hippocampus with the help of bionics, and store and dynamically update the knowledge in the long-term memory bank in three levels: sentences, paragraphs, and chapters; The task of generating new documents is input into the electric power semantic big model, and the long-term memory is used as the external knowledge source of the electric power semantic big model; through semantic analysis and personalized retrieval algorithm, the knowledge of various levels related to the current task is dynamically searched from the long-term memory; according to the hierarchical order of sentences, paragraphs and chapters, the contextual background knowledge and the knowledge dynamically found from the long-term memory are iteratively integrated layer by layer to finally generate the complete document content.

2. The method for generating a bionic hierarchical memory fusion document of a large power semantic model according to claim 1, characterized in that: The extraction of knowledge in the form of multimodal data is to identify core concepts, keywords and key data points in documents and historical generation records, as noun phrases or events, and store them in the form of text, images, and tables.

3. The method for generating a bionic hierarchical memory fusion document of a large power semantic model according to claim 1, characterized in that: The construction of the long-term memory library is specifically as follows: Construct a knowledge graph using knowledge as nodes and semantic relationships between knowledge as edges; Drawing on the memory characteristics of the human hippocampus, multiple synonymous and hyponymous relationships are added to the constructed knowledge graph; The nodes are further classified and stored at different levels such as sentences, paragraphs and chapters.

4. The method for generating a bionic hierarchical memory fusion document of a large power semantic model according to claim 1, characterized in that: The semantic analysis and personalized retrieval algorithm are used to dynamically search for knowledge of various levels related to the current task from the long-term memory library, specifically: Use natural language processing technology to perform semantic analysis on the content of the task and identify key information, including keywords, core requirements, and important concepts; The similarity calculation between key information and nodes in the library is used to preliminarily identify knowledge nodes related to the current task; Using the personalized PageRank algorithm, based on the initially identified knowledge nodes, other knowledge nodes are retrieved on the knowledge graph of the long-term memory library, and finally knowledge at all levels related to the current task is obtained.

5. The method for generating a bionic hierarchical memory fusion document of a large power semantic model according to claim 1, characterized in that: The specific process of one iteration of generating complete document content is as follows: At the sentence level, by calling the found sentence-level knowledge and combining it with the background information of the current task, it generates semantically clear sentences. While generating sentences, it analyzes the subject and structure of the sentences, automatically detects the semantic relationship between sentences, and marks the contextual relationship, including the master-slave relationship and the causal relationship. At the paragraph level, the sentences generated in the previous step are integrated according to the contextual relationship tags, and at the same time, the relevant background knowledge in the long-term memory bank is referenced according to the paragraph theme; At the chapter level, we further integrate the paragraphs and analyze them as a whole, while calling on the chapter background knowledge to generate an introduction at the beginning of the chapter and a summary paragraph at the end.

6. The method for generating a bionic hierarchical memory fusion document of a large power semantic model according to claim 1, characterized in that: The generating of complete document content also includes: Analyze the content requirements of paragraphs or chapters to determine whether multimodal data needs to be embedded; By associating with the multimodal knowledge in the long-term memory bank, the most appropriate multimodal data is identified and combined with the text content; Automatically generate brief description text for each multimodal data in the combined document content and format it.

7. The electric power semantic large model bionic hierarchical memory fusion document generation system is characterized by: Includes memory building module and document generation module: The memory library construction module is configured to: extract knowledge in the form of multimodal data from historical document data, build a long-term memory library by simulating the memory mechanism of the human hippocampus with the help of bionics, and hierarchically store and dynamically update the knowledge in the long-term memory library at three levels: sentences, paragraphs, and chapters; The document generation module is configured as follows: inputting the task of generating a new document into the electric power semantic big model, and using the long-term memory as the external knowledge source of the electric power semantic big model; dynamically searching for knowledge of various levels related to the current task from the long-term memory through semantic analysis and personalized retrieval algorithms; iteratively integrating the contextual background knowledge and the knowledge dynamically found from the long-term memory layer by layer according to the hierarchical order of sentences, paragraphs and chapters, and finally generating complete document content.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for generating a bionic hierarchical memory fusion document for a large electric semantic model as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the method for generating a bionic hierarchical memory fusion document of a large electric semantic model as described in any one of claims 1-6 is implemented.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the method for generating a bionic hierarchical memory fusion document for a large electric semantic model as described in any one of claims 1-6.

Images