Intelligent data intelligence analysis method based on LLM (Logistics Language Model)

Abstract

The invention provides a data intelligence intelligent analysis method based on an LLM large language model, and the method comprises the steps: carrying out the intelligence analysis and mining of a tree structure through the LLM large language model based on the father and son cues in a cue binary tree for data intelligence analysis, and obtaining an intelligent analysis result. Through traversing and inputting each information analysis cue word with a father-son relationship on the binary tree, the database is searched and analyzed, and the corresponding data information with the tree structure is mined. According to the method, the hierarchical information network binary tree can be quickly generated by relying on the LLM large language model, so that the data information mining analysis efficiency is improved, a large amount of sample training learning of a machine learning algorithm model is not involved, and the data analysis complexity is reduced. And finally, a data intelligence network with a tree structure can be generated, so that the user can perform intelligence analysis and lookup from different levels, and the intelligence analysis and understanding difficulty is reduced.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a data intelligence intelligent analysis method based on an LLM large language model, a data intelligence intelligent analysis device based on an LLM large language model, an electronic device and a computer-readable storage medium. Background Art

[0002] Data intelligence analysis is the process of collecting, processing and analyzing large amounts of data to extract valuable information and insights. It combines methods from fields such as data science, statistics and business intelligence to support decision making.

[0003] The key steps of data intelligence analysis include data collection, data cleaning, data analysis, data visualization and decision support: 1. Data collection: It is the basis for obtaining reliable data and the first step in data intelligence analysis. Through multi-channel and multi-dimensional data collection, the comprehensiveness and diversity of data can be ensured, laying a solid foundation for subsequent analysis. Data collection mainly includes the acquisition of internal data and external data. Internal data usually comes from the company's business system, such as CRM, ERP, etc.; external data includes public data, third-party data, etc.

[0004] 2. Data cleaning: It is an important part of data intelligence analysis, and its purpose is to ensure the accuracy and consistency of data. Data may be missing, duplicated, wrong, and inconsistent during the collection process, which will affect the subsequent analysis results. Data cleaning includes steps such as data deduplication, data completion, data verification, and data conversion.

[0005] 3. Data analysis: It is the core link of data intelligence analysis, and its purpose is to mine valuable information from data. Data analysis includes descriptive analysis, diagnostic analysis, predictive analysis and normative analysis.

[0006] 4. Data visualization: It is an important part to help users better understand and interpret data. Data visualization is to display complex data in the form of charts, graphs, etc., making the data easier to understand and analyze. Data visualization can help users quickly discover patterns and trends in data and improve the efficiency and effectiveness of data analysis.

[0007] 5. Decision support: It uses the results of data analysis to provide a scientific basis for the company's strategic planning, marketing, product development, etc. Decision support needs to comprehensively consider many factors, such as market environment, competitors, customer needs, etc., and conduct comprehensive analysis and evaluation.

[0008] There are many methods for data intelligence analysis, and the traditional methods mainly include the following: Descriptive analysis: is a basic analytical method that aims to summarize past data and understand what happened.

[0009] Diagnostic analysis: focuses on why a specific event occurred. By digging deeper into the data, analysts can find out the factors that influenced a specific event.

[0010] Predictive analytics: Use historical data to predict future trends. By building statistical models or using machine learning algorithms, you can predict future situations and make better strategic decisions.

[0011] Prescriptive analytics: Aims to provide actionable insights. It not only tells the business what might happen in the future, but also provides advice on how to respond.

[0012] Real-time analysis: In the digital age, real-time data analysis is becoming increasingly important. It allows companies to analyze data as it is generated, allowing them to respond quickly to market changes.

[0013] However, in the data analysis process, the traditional data intelligence analysis methods mentioned above mainly rely on data statistical tools to assist in analysis, and classify useful data intelligence, record and count them, so as to find out the factors that affect specific events, etc. Conventional statistical tools or components are very inefficient in mining data intelligence, and almost require manual operation, so the efficiency of data intelligence analysis and collection is very slow; the use of machine learning algorithms for predictive analysis involves the preparation of a large number of training samples and takes a long time to train models, which is a huge workload and relatively complicated; existing data intelligence analysis cannot generate a hierarchical data intelligence network and cannot provide a hierarchical intelligence data set. Summary of the invention

[0014] In order to solve the technical problems existing in the prior art, the present invention provides the following technical solutions: On the one hand, a data intelligence intelligent analysis method based on an LLM large language model is provided, the method is implemented by an electronic device, and the method includes: S1. Construct and configure a binary tree of prompt words for data intelligence analysis, wherein the binary tree of prompt words includes a parent node and a plurality of child nodes, and the parent node and the child node are respectively configured with intelligence analysis prompt words of corresponding authority; S2, traversing the prompt word binary tree based on a recursive traversal algorithm, reading the intelligence analysis prompt words on the parent and child nodes in sequence and inputting them into a preset LLM large language model, performing a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mining to obtain the data intelligence analysis results corresponding to the parent node or the child node; S3, according to the relationship between the parent and child nodes, based on the information volume and information importance sorting, orderly counting the data intelligence analysis results of each node and generating a corresponding intelligence network binary tree; S4. Traverse and verify the intelligence network binary tree, and output and save the intelligence network binary tree after verification.

[0015] Preferably, the step S1, constructing and configuring a binary tree of prompt words for data intelligence analysis, includes: Import binary tree; Traversing the parent node and each of the child nodes on the binary tree; According to the analysis dimensions and contents of the data intelligence to be analyzed, respectively construct analysis data keywords, analysis scope keywords and analysis logic on the corresponding analysis dimensions on the parent node and each of the child nodes; Combining the analysis data keywords, the analysis scope keywords and the analysis logic on the corresponding analysis dimension, constructing the intelligence analysis prompt words corresponding to the parent node and each of the child nodes respectively, and configuring the intelligence analysis prompt words at the corresponding parent node or the child node; After the configuration is completed, the prompt word binary tree is obtained.

[0016] Preferably, S2, based on a recursive traversal algorithm, traverses the prompt word binary tree, reads the intelligence analysis prompt words on the parent and child nodes in sequence and inputs a preset LLM large language model, performs a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mines and obtains the data intelligence analysis results corresponding to the parent node or the child node, including: Starting from the parent node on the prompt word binary tree, the intelligence analysis prompt words configured on the parent node and the child node are read in sequence, wherein the recursive traversal algorithm : , in: is the target node to be traversed currently. is the parent node (the parent node of the current node N, initially Indicates that the root node has no parent node). are the left and right child nodes of the current node N respectively, is the operation sequence symbol, which means "execute the operation on the left first, then the operation on the right". To process the parent-child relationship, output or record the information of the parent node P and the child node N. It is an empty node (indicating that the node does not exist or the traversal terminates); Input the read intelligence analysis prompt word into the preset LLM large language model, so that the LLM large language model searches the data intelligence database based on the intelligence analysis prompt word, analyzes and mines the data intelligence analysis results that match the intelligence analysis prompt word, and outputs them; The output data intelligence analysis result is written and saved to the corresponding parent node or the child node to obtain the data intelligence analysis result corresponding to the parent node or the child node.

[0017] Preferably, the S3, according to the relationship between the parent and child nodes, based on the information volume and information importance sorting, orderly counting the data intelligence analysis results of each node and generating a corresponding intelligence network binary tree, includes: The amount of information and the importance of information of each node are calculated and sorted, and the data intelligence analysis results at the parent node and each of the child nodes are traversed and counted based on the sorting results; wherein the amount of information and the importance of information are respectively expressed as and : , in: N: current node, Ai: the th attribute of node N, k: the total number of attributes of node N, wi: the weight of the i-th attribute (indicating the contribution of the attribute to the amount of information), Complexity(Ai): The complexity of the i-th attribute, calculated as follows: If the attribute value is a numeric type: Complexity(Ai) = log2(1 +|Ai|); If the attribute value is of categorical type: Complexity(Ai) = Entropy(Ai), where Entropy(Ai) is the entropy value of the categorical attribute; , in: Depth(N): the depth of node N in the tree (the root node depth is 0), Degree(N): the connectivity of node N (number of child nodes), Centrality(N): the centrality of node N (betweenness centrality or closeness centrality), Weight coefficients, used to adjust the contribution of each item to importance; Import a new binary tree A, and configure corresponding parent and child nodes of the new binary tree A according to the relationship between the parent and child nodes on the prompt word binary tree; The data intelligence analysis results of the parent node and each of the child nodes obtained by traversal extraction are written into the new binary tree A to obtain the intelligence network binary tree.

[0018] Preferably, the S4, traversing and verifying the intelligence network binary tree, and outputting and saving the intelligence network binary tree after verification, includes: Pre-configure corresponding data intelligence verification rules for the parent node and each of the child nodes; Utilize the LLM large language model to extract verification keywords, verification scope keywords and corresponding verification logic in the data intelligence verification rules; Combining the verification keyword, the verification scope keyword and the corresponding verification logic, constructing intelligence verification prompt words corresponding to the parent node and each of the child nodes, and configuring the intelligence verification prompt words at the corresponding parent node or the child node; Traversing the data intelligence analysis results and the intelligence verification prompt words at the parent node or the child node on the intelligence network binary tree, and inputting the intelligence verification prompt words into the preset LLM large language model; The data intelligence analysis result at the parent node or the child node is verified by the LLM large language model based on the intelligence verification prompt word at the parent node or the child node: If the verification is successful, the parent node or the child node is marked as a passed state; Otherwise it is marked as an alarm state; After verification is completed, the intelligence network binary tree with status marks is output and saved.

[0019] On the other hand, a data intelligence intelligent analysis device based on an LLM large language model is provided, and the data intelligence intelligent analysis device based on an LLM large language model is used to implement the data intelligence intelligent analysis method based on the LLM large language model, and the device includes: A prompt word construction module is used to construct and configure a prompt word binary tree for data intelligence analysis, wherein the prompt word binary tree includes a parent node and a plurality of child nodes, and the parent node and the child node are respectively configured with intelligence analysis prompt words of corresponding authority; An intelligence mining module is used to traverse the prompt word binary tree based on a recursive traversal algorithm, read the intelligence analysis prompt words on the parent and child nodes in turn and input them into a preset LLM large language model, perform a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mine and obtain the data intelligence analysis results corresponding to the parent node or the child node; An intelligence statistics module is used to sequentially count the data intelligence analysis results of each node and generate a corresponding intelligence network binary tree according to the relationship between parent and child nodes and based on the information volume and information importance sorting; The intelligence verification module is used to traverse and verify the intelligence network binary tree, and output and save the intelligence network binary tree after verification.

[0020] On the other hand, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned data intelligence intelligent analysis methods based on the LLM large language model is implemented.

[0021] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored. The at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned data intelligence intelligent analysis methods based on the LLM large language model.

[0022] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: The present invention provides a data intelligence intelligent analysis method based on an LLM large language model, which performs intelligence analysis and mining on a tree structure based on the father-child prompt words in a prompt word binary tree used for data intelligence analysis through the LLM large language model, and performs database analysis and mining of corresponding data intelligence with a tree structure by traversing and inputting each intelligence analysis prompt word with a father-child relationship on the binary tree. It can rely on the LLM large language model to quickly generate a hierarchical intelligence network binary tree, which not only improves the efficiency of data intelligence mining and analysis, but also does not involve a large number of sample training and learning of machine learning algorithm models, reducing the complexity of data analysis. And finally, it can generate a data intelligence network with a tree structure, allowing users to perform intelligence analysis and inquiry from different levels, reducing the difficulty of intelligence analysis and understanding. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0024] Figure 1 It is a flow chart of a data intelligence intelligent analysis method based on the LLM large language model provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of an application structure of a binary tree provided by an embodiment of the present invention; Figure 3 It is a block diagram of a data intelligence intelligent analysis device based on the LLM large language model provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0026] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0027] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0028] In the embodiments of the present invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are consistent.

[0029] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0030] The LLM large language model of this embodiment can be self-designed or by calling a third-party LLM large language model such as Baidu's Wenyan Yixin model, etc., which is not limited in this embodiment.

[0031] The embodiment of the present invention provides a data intelligence intelligent analysis method based on the LLM large language model, which can be implemented by an electronic device, which can be a terminal or a server. Figure 1The flowchart of the data intelligence intelligent analysis method based on the LLM large language model is shown. The processing flow of the method may include the following steps: S1. Construct and configure a binary tree of prompt words for data intelligence analysis, wherein the binary tree of prompt words includes a parent node and a plurality of child nodes, and the parent node and the child node are respectively configured with intelligence analysis prompt words of corresponding authority; S2, traversing the prompt word binary tree based on a recursive traversal algorithm, reading the intelligence analysis prompt words on the parent and child nodes in sequence and inputting them into a preset LLM large language model, performing a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mining to obtain the data intelligence analysis results corresponding to the parent node or the child node; S3, according to the relationship between the parent and child nodes, based on the information volume and information importance sorting, orderly counting the data intelligence analysis results of each node and generating a corresponding intelligence network binary tree; S4. Traverse and verify the intelligence network binary tree, and output and save the intelligence network binary tree after verification.

[0032] In this embodiment, the structure of the binary tree is not described here. The binary tree has at least one parent node, and each parent node has several child nodes (the child node of the next level may be the parent node of this level, and there are several child nodes in the next level). The specific node level can be configured according to the node level as needed.

[0033] The present invention defines and configures the binary tree of each scene, thereby constructing a corresponding prompt word binary tree or intelligence network binary tree, etc. By constructing a tree-structured large language model prompt word, the parent and child nodes are configured with prompt words according to the scope and type of the intelligence prompt word, and the LLM large language model is input to allow the model to perform data intelligence mining of the corresponding nodes (authority and data range) based on the prompt word, and finally analyze and generate a tree-structured data intelligence analysis result with clear levels, which can allow users to understand the analysis results of different levels.

[0034] In specific operations, the LLM large language model can define various data analysis logics based on the keywords in the prompt words, and perform corresponding data mining, analysis, and verification operations to match and analyze the data mining results that match the prompt words. The steps for the LLM large language model to perform data analysis based on the prompt words can refer to the following application description of the LLM large language model.

[0035] The present invention combines LLM (Large Language Model) to perform intelligent data mining, and guides the model to perform multiple rounds of intelligence data analysis and identify the final intelligence data by constructing intelligence prompt words. The main steps are: 1. Data Collection and Preprocessing ‌Data Collection‌: Collect data intelligence related to a specific topic from various data sources (such as databases, online repositories, documents, etc.) and save them in a database (data intelligence database, some of which can be saved and configured according to business scope, etc., and the specific database is specified by the user).

[0036] ‌Data preprocessing‌: Clean the collected data, filter out noise, correct errors, and organize it into a structured format suitable for analysis. High-quality, clean data is critical to ensuring model performance.

[0037] 2. Constructing intelligence prompt words ‌Define intelligence requirements‌: Clarify the type and objectives of intelligence to be mined.

[0038] ‌Build prompt words‌: According to intelligence needs, build a series of intelligence prompt words (build a tree-structured large language model prompt words, and configure the parent and child nodes according to the scope and type of intelligence prompt words). These prompt words should be able to guide the LLM model to focus on the key information in the data and promote the model to perform multiple rounds of analysis.

[0039] 3. LLM model application ‌Choose a suitable LLM model‌: Choose a pre-trained large language model, such as GPT-3, GPT-4, etc. These models have been pre-trained on large-scale text data and have strong language understanding and generation capabilities.

[0040] ‌Multiple rounds of data analysis‌: ‌First round of analysis‌: Input the preprocessed data and the constructed intelligence prompt words into the LLM model. The model will perform a preliminary analysis of the data based on the prompt words and generate the first round of analysis results.

[0041] Subsequent rounds of analysis: Based on the results of the first round of analysis, the intelligence prompt words are adjusted or supplemented and input into the model again for the next round of analysis. This process can be repeated multiple times until the final intelligence data is identified.

[0042] 4. Intelligence identification and extraction ‌Results Evaluation‌: Evaluate the analysis results generated by the LLM model to identify key information related to intelligence needs.

[0043] ‌Intelligence Extraction‌: Extract the final intelligence data from the analysis results and organize it into a format that is easy to understand and use. This allows the LLM model to identify the data format of the corresponding node and automatically call the visualization component to perform data visualization processing, so that the analysis results of each node can be displayed in a tree structure.

[0044] Therefore, the present invention uses the LLM large language model based on the father-child prompt words in the prompt word binary tree for data intelligence analysis to perform intelligence analysis and mining on the tree structure, and by traversing each intelligence analysis prompt word with a father-child relationship on the input binary tree, the library is checked and analyzed, and the corresponding data intelligence with a tree structure is mined. It can rely on the LLM large language model to quickly generate a binary tree of intelligence network with a sense of hierarchy, which not only improves the efficiency of data intelligence mining and analysis, but also does not involve a large number of sample training and learning of machine learning algorithm models, reducing the complexity of data analysis. And finally, it can generate a data intelligence network with a tree structure, allowing users to perform intelligence analysis and consultation from different levels, reducing the difficulty of intelligence analysis and understanding.

[0045] The application principle of the present invention will be further described below.

[0046] Preferably, the step S1, constructing and configuring a binary tree of prompt words for data intelligence analysis, includes: Import binary tree; Traversing the parent node and each of the child nodes on the binary tree; According to the analysis dimensions and contents of the data intelligence to be analyzed, respectively construct analysis data keywords, analysis scope keywords and analysis logic on the corresponding analysis dimensions on the parent node and each of the child nodes; Combining the analysis data keywords, the analysis scope keywords and the analysis logic on the corresponding analysis dimension, constructing the intelligence analysis prompt words corresponding to the parent node and each of the child nodes respectively, and configuring the intelligence analysis prompt words at the corresponding parent node or the child node; After the configuration is completed, the prompt word binary tree is obtained.

[0047] In the present invention, data intelligence analysis is analyzed in layers according to the hierarchy of parent-child nodes. Therefore, intelligence analysis prompts of corresponding levels are configured on the parent node and the corresponding child nodes under the parent node, so that the greater than model is based on the intelligence analysis prompts configured by each node, and the corresponding intelligence analysis scope and dimension and analysis logic level data intelligence analysis are performed on the corresponding node. For example, on a certain parent node, it is necessary to let the parent node analyze a certain format data intelligence, such as searching and analyzing the parent node data intelligence of the customer's additional purchase behavior of a certain commodity, and the data intelligence of the next analysis dimension of the child node below it can be for women or men to analyze the additional purchase behavior of the certain commodity, or within a certain month, a certain year, the repurchase rate analysis of the commodity, etc., so as to form a hierarchical analysis logic and scope. Therefore, the data intelligence analysis of the parent node and the child node is different in the analysis dimension and analysis scope, as well as the key data keywords.

[0048] Therefore, corresponding keywords and analysis logic on the corresponding hierarchical dimensions can be constructed here for the parent and child nodes respectively. Subsequently, the keywords and analysis logic of the corresponding nodes are combined to form intelligence analysis prompt words, and corresponding intelligence analysis prompt words are constructed and configured for each parent node or child node. Subsequently, the preset LLM large language model can be input to learn the keywords and analysis logic in the prompt words, and data intelligence analysis and mining of the corresponding prompt words are performed for each parent node or child node according to the intelligence analysis prompt words, so as to generate data intelligence analysis results with corresponding analysis scopes, analysis keywords and logic for each parent node and child node.

[0049] Preferably, S2, based on a recursive traversal algorithm, traverses the prompt word binary tree, reads the intelligence analysis prompt words on the parent and child nodes in sequence and inputs a preset LLM large language model, performs a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mines and obtains the data intelligence analysis results corresponding to the parent node or the child node, including: Starting from the parent node on the prompt word binary tree, the intelligence analysis prompt words configured on the parent node and the child node are read in sequence, wherein the recursive traversal algorithm : , in: is the target node to be traversed currently. is the parent node (the parent node of the current node N, initially Indicates that the root node has no parent node). are the left and right child nodes of the current node N respectively, is the operation sequence symbol, which means "execute the operation on the left first, then the operation on the right". To process the parent-child relationship, output or record the information of the parent node P and the child node N. It is an empty node (indicating that the node does not exist or the traversal terminates); Input the read intelligence analysis prompt word into the preset LLM large language model, so that the LLM large language model searches the data intelligence database based on the intelligence analysis prompt word, analyzes and mines the data intelligence analysis results that match the intelligence analysis prompt word, and outputs them; The output data intelligence analysis result is written and saved to the corresponding parent node or the child node to obtain the data intelligence analysis result corresponding to the parent node or the child node.

[0050] Here we use a recursive traversal algorithm , traverse the parent node and each child node on the binary tree, let the large language model traverse the binary tree, so as to read the intelligence analysis prompt words configured on each node, and perform database search and mining analysis based on the input intelligence analysis prompt value, so as to mine the data intelligence matching the information in the prompt word and obtain the corresponding analysis results based on the analysis logic analysis, output and save them on the corresponding node.

[0051] The recursive traversal algorithm : , in: is the target node to be traversed currently. is the parent node (the parent node of the current node N, initially Indicates that the root node has no parent node). are the left and right child nodes of the current node N respectively, is the operation sequence symbol, which means "execute the operation on the left first, then the operation on the right". To process the parent-child relationship, output or record the information of the parent node P and the child node N. When accessing a node, not only the current node is accessed, but also its parent node is recorded. For example, the information of the parent node is passed during traversal, and the relationship between the parent node and the child node is processed at the same time during access. Here, it is necessary to determine the processing relationship between the parent and child nodes (processing the parent-child relationship) according to the analysis logic in the "intelligence analysis prompt words" configured on the parent node and the child node respectively. For example, the child node contains "additional purchase behavior analysis" and the parent node contains "commodity format sales data", and "additional purchase behavior analysis" needs to rely on "commodity format sales data" for analysis and calculation. Therefore, at this time, the access can record the relationship between the parent node and the child node, and clarify that the additional purchase behavior needs to be obtained after the commodity format sales data; It is an empty node (indicating that the node does not exist or the traversal terminates); Recursive traversal algorithm , the logic is as follows: 1. Input: current node N and its parent node P; 2. Termination condition: If the current node N is empty ( ), then return directly; 3. Handle parent-child relationship calls , record the relationship between the parent node P and the child node N (for example, print P N). If P= , indicating that N is the root node. At this time, the root node information can be processed separately; the parent-child relationship is processed in combination with the keyword logic of the node being visited.

[0052] 4. Recursively traverse the subtree: First recursively traverse the left subtree: ; Then recursively traverse the right subtree: .

[0053] Features of this algorithm 1. Explicit parent-child relationship: Every time a node is visited, the relationship between its parent node and the current node is recorded; 2. Depth-first traversal: Use recursion to implement the logic of first visiting the parent node and then traversing the left and right subtrees in turn.

[0054] The large language model can perform database search based on prompt words: first, it mines out data intelligence that matches the analysis dimensions, analysis data keywords, and analysis scope keywords in the prompt words, and further conducts in-depth analysis of the data intelligence based on the analysis logic, so as to generate data intelligence analysis results under this dimension and authority, and then writes the mined data intelligence and the corresponding data intelligence analysis results into the corresponding parent node or child node.

[0055] On the backend database, a corresponding data storage address can be assigned to each parent node or child node. After the large language model is searched and analyzed to obtain the corresponding data intelligence and the corresponding analysis results, the results can be saved to the storage address of the node.

[0056] We can also use distributed storage systems, such as the HDFS distributed system, to store the data intelligence of each node and its analysis results, which is convenient for distributed management and storage.

[0057] Preferably, the S3, according to the relationship between the parent and child nodes, based on the information volume and information importance sorting, orderly counting the data intelligence analysis results of each node and generating a corresponding intelligence network binary tree, includes: The amount of information and the importance of information of each node are calculated and sorted, and the data intelligence analysis results at the parent node and each of the child nodes are traversed and counted based on the sorting results; wherein the amount of information and the importance of information are respectively expressed as and : , in: N: current node, Ai: the th attribute of node N, k: the total number of attributes of node N, wi: the weight of the i-th attribute (indicating the contribution of the attribute to the amount of information), Complexity(Ai): The complexity of the i-th attribute, calculated as follows: If the attribute value is a numeric type: Complexity(Ai) = log2(1 +|Ai|); If the attribute value is of categorical type: Complexity(Ai) = Entropy(Ai), where Entropy(Ai) is the entropy value of the categorical attribute; , in: Depth(N): the depth of node N in the tree (the root node depth is 0), Degree(N): the connectivity of node N (number of child nodes), Centrality(N): the centrality of node N (betweenness centrality or closeness centrality), : Weight coefficient, used to adjust the contribution of each item to importance; Import a new binary tree A, and configure corresponding parent and child nodes of the new binary tree A according to the relationship between the parent and child nodes on the prompt word binary tree; The data intelligence analysis results of the parent node and each of the child nodes obtained by traversal extraction are written into the new binary tree A to obtain the intelligence network binary tree.

[0058] Let the large language model traverse the prompt words of each node on the prompt word binary tree and perform a database query analysis. After outputting the corresponding data intelligence analysis results, in order to output the data intelligence analysis results of each node in order and perform statistics. A new binary tree structure is constructed separately here. This new binary tree structure will be used solely to visualize the data intelligence analysis results of each node extracted above. Because the previous prompt word binary tree mainly constructs prompt words for model traversal, if it is displayed again, there will be data task alternation and possible confusion. Here, the prompt word traversal retrieval analysis and result display are operated separately by binary trees, which can avoid direct data mixing between binary trees, reduce the structural complexity of each binary tree, and reduce the degree of data redundancy (because the data analysis of a business format contains data results of several hierarchical structures, and the amount of data is huge).

[0059] Therefore, a new binary tree A can be imported, and the parent-child node relationship of the new binary tree can be configured according to the parent-child node relationship on the above prompt word binary tree. By adopting the above method, a new binary tree A can be quickly constructed, and the data intelligence analysis results of the corresponding nodes can be located, copied and saved on each node of the new binary tree A according to the parent-child node relationship on the original prompt word binary tree for display of the analysis results, so as to obtain an intelligence network binary tree that visually displays the data intelligence analysis results. The intelligence network binary tree directly displays the analysis results of the corresponding nodes, and displays them through a hierarchical data structure, which allows users to quickly analyze data intelligence at each level.

[0060] Among them, in order to effectively quantify and count the information characteristics of each node, and to orderly count and analyze the intelligence information of the parent and child nodes to avoid subsequent data management confusion, this place combines the data volume and information importance of each node to orderly count the data intelligence of each node. Each node can be marked according to the information volume and information importance of each node, which is convenient for users to visualize and analyze and identify the attributes (information volume and importance) of each data intelligence information of the parent and child nodes. The node information is conveniently extracted based on the information volume and importance, and it is also convenient for the system to classify statistics and storage.

[0061] Combining the information size and information importance formula can be used in the traversal algorithm: 1. Calculate the amount of information: Use Calculate the amount of information for each node.

[0062] Calculate importance: Use Calculate the importance of each node.

[0063] 3. Sorting and extraction: Extract important information based on importance, and then extract other information based on the amount of information.

[0064] Above , An example is as follows: Assume that node N has the following properties: Attribute A1 (numeric type): value is 10.

[0065] Attribute A2 (classification type): value is {"High","Low","Medium"}, distribution is P = {0.5,0.3,0.2} Calculation process: 1.Complexity(A1)=log(1+10)≈3.46; 2.Entropy(A2)= ≈ 1.57; 3. Assume weights w1 = 1, w2 = 2; 4.Volume(N)=1·3.46+2.1.57=6.60.

[0066] Assume the following information about node N: Depth(N)=2, Degree(N)=3, Centrality(N)=0.8, Weight coefficients α=0.5, β=0.3, γ=0.2, Importance calculation process: .

[0067] In this embodiment, the weight coefficients wi, α, β, γ can be adjusted according to specific scenarios.

[0068] The present invention also performs data verification of the generated data intelligence and its results corresponding to the binary tree structure. Based on the above-mentioned large language model traversing the prompt words of each node of the binary tree to perform data analysis, an intelligence verification prompt word is set here to allow the large language model to traverse and verify the correctness of the data intelligence of each node and its analysis results. If there is a node that fails the verification, the node is marked as abnormal, which is convenient for users to quickly locate the nodes with abnormal data intelligence and results, locate the node data intelligence analysis, and quickly find the cause.

[0069] Preferably, the S4, traversing and verifying the intelligence network binary tree, and outputting and saving the intelligence network binary tree after verification, includes: Pre-configure corresponding data intelligence verification rules for the parent node and each of the child nodes; Utilize the LLM large language model to extract verification keywords, verification scope keywords and corresponding verification logic in the data intelligence verification rules; Combining the verification keyword, the verification scope keyword and the corresponding verification logic, constructing intelligence verification prompt words corresponding to the parent node and each of the child nodes, and configuring the intelligence verification prompt words at the corresponding parent node or the child node; Traversing the data intelligence analysis results and the intelligence verification prompt words at the parent node or the child node on the intelligence network binary tree, and inputting the intelligence verification prompt words into the preset LLM large language model; The data intelligence analysis result at the parent node or the child node is verified by the LLM large language model based on the intelligence verification prompt word at the parent node or the child node: If the verification is successful, the parent node or the child node is marked as a passed state; Otherwise it is marked as an alarm state; After verification is completed, the intelligence network binary tree with status marks is output and saved.

[0070] It is necessary to use a large language model to verify the data intelligence and analysis results of each parent node and child node on the binary tree. Therefore, an intelligence network binary tree can be generated according to the construction method of the above prompt word binary tree for verification. On the basis of the above intelligence network binary tree, corresponding data intelligence verification rules can be configured for each parent node and child node. The corresponding range of verification rules can be configured for each node with reference to the construction method of the above prompt word binary tree, and the verification keywords, verification range keywords and corresponding verification logic can be further extracted using the data mining algorithm. The corresponding intelligence verification prompt words are further combined with the verification keywords, verification range keywords and corresponding verification logic to generate corresponding intelligence verification prompt words, and are configured at the corresponding parent node or child node. Because the corresponding intelligence verification prompt words, corresponding data intelligence and corresponding data analysis results have been configured and saved on the intelligence network binary tree, the large language model can be allowed to traverse the binary tree, extract the intelligence analysis results and intelligence verification prompt words of the corresponding nodes, input the intelligence verification prompt words into the large language model, and let the large language model verify the data intelligence and analysis results of each node based on the information in the intelligence verification prompt words.

[0071] As for the data intelligence verification rules of each node, the corresponding intelligence verification prompt words can be constructed according to the data processing scope, logic, keywords, etc. set for each node in the early stage. Therefore, based on the above-mentioned intelligence network binary tree, this place combines the keywords and logic constructed for each node to generate corresponding intelligence verification prompt words, so that the model can verify the data intelligence analysis results of each node based on the intelligence verification prompt words of each node. For the analysis results of the nodes that pass the verification, the node can be marked with a pass status; for the analysis results of the nodes that fail the verification, the node can be marked with an alarm status. When performing the subsequent visualization, let the intelligence network binary tree perform the corresponding status visualization to quickly locate the nodes with abnormal status.

[0072] The specific visualization technology can call the corresponding visualization components or programs to achieve the corresponding visualization rendering and generation.

[0073] Figure 3 1 is a block diagram of a data intelligence intelligent analysis device based on an LLM large language model according to an exemplary embodiment. The device is used in a data intelligence intelligent analysis method based on an LLM large language model. Figure 3The device includes a prompt word construction module 310, an intelligence mining module 320, an intelligence statistics module 330 and an intelligence verification module 340. Among them: A prompt word construction module is used to construct and configure a prompt word binary tree for data intelligence analysis, wherein the prompt word binary tree includes a parent node and a plurality of child nodes, and the parent node and the child node are respectively configured with intelligence analysis prompt words of corresponding authority; An intelligence mining module is used to traverse the prompt word binary tree based on a recursive traversal algorithm, read the intelligence analysis prompt words on the parent and child nodes in turn and input them into a preset LLM large language model, perform a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mine and obtain the data intelligence analysis results corresponding to the parent node or the child node; An intelligence statistics module is used to sequentially count the data intelligence analysis results of each node and generate a corresponding intelligence network binary tree according to the relationship between parent and child nodes and based on the information volume and information importance sorting; The intelligence verification module is used to traverse and verify the intelligence network binary tree, and output and save the intelligence network binary tree after verification.

[0074] Please understand the above modules in conjunction with the corresponding steps in the above method.

[0075] Figure 4 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 4 As shown, the electronic device may include the above Figure 3 The data intelligence intelligent analysis device based on the LLM large language model is shown. Optionally, the electronic device 410 may include a first processor 2001.

[0076] Optionally, the electronic device 410 may further include a memory 2002 and a transceiver 2003 .

[0077] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0078] Combine the following Figure 4 The components of the electronic device 410 are described in detail: The first processor 2001 is the control center of the electronic device 410, and may be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or a specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs).

[0079] Optionally, the first processor 2001 can execute various functions of the electronic device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002 .

[0080] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 4 CPU0 and CPU1 are shown in FIG.

[0081] In a specific implementation, as an embodiment, the electronic device 410 may also include multiple processors, such as Figure 4 The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0082] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0083] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently and access the first processor 2001 through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0084] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0085] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 4 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0086] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently and communicate with the first processor 2001 through the interface circuit ( Figure 4 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0087] It should be noted that Figure 4 The structure of the electronic device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than those shown in the figure, or combine certain components, or arrange the components differently.

[0088] In addition, the technical effects of the electronic device 410 can refer to the technical effects of the data intelligence intelligent analysis method based on the LLM large language model described in the above method embodiment, which will not be repeated here.

[0089] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0090] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0091] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0092] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0093] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0094] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0095] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0097] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0098] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0100] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0101] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A data intelligence intelligent analysis method based on LLM large language model, characterized in that: The method comprises: S1. Construct and configure a binary tree of prompt words for data intelligence analysis, wherein the binary tree of prompt words includes a parent node and a plurality of child nodes, and the parent node and the child node are respectively configured with intelligence analysis prompt words of corresponding authority; S2, traversing the prompt word binary tree based on a recursive traversal algorithm, reading the intelligence analysis prompt words on the parent and child nodes in sequence and inputting them into a preset LLM large language model, performing a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mining to obtain the data intelligence analysis results corresponding to the parent node or the child node; S3, according to the relationship between the parent and child nodes, based on the information volume and information importance sorting, orderly counting the data intelligence analysis results of each node and generating a corresponding intelligence network binary tree; S4. Traverse and verify the intelligence network binary tree, and output and save the intelligence network binary tree after verification.

2. The data intelligence intelligent analysis method based on the LLM large language model according to claim 1 is characterized in that: The step S1, constructing and configuring a binary tree of prompt words for data intelligence analysis, includes: Import binary tree; Traversing the parent node and each of the child nodes on the binary tree; According to the analysis dimensions and contents of the data intelligence to be analyzed, respectively construct analysis data keywords, analysis scope keywords and analysis logic on the corresponding analysis dimensions on the parent node and each of the child nodes; Combining the analysis data keywords, the analysis scope keywords and the analysis logic on the corresponding analysis dimension, constructing the intelligence analysis prompt words corresponding to the parent node and each of the child nodes respectively, and configuring the intelligence analysis prompt words at the corresponding parent node or the child node; After the configuration is completed, the prompt word binary tree is obtained.

3. The data intelligence intelligent analysis method based on the LLM large language model according to claim 1 is characterized in that: S2, traversing the prompt word binary tree based on a recursive traversal algorithm, reading the intelligence analysis prompt words on the parent and child nodes in sequence and inputting a preset LLM large language model, performing a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mining to obtain data intelligence analysis results corresponding to the parent node or the child node, including: Starting from the parent node on the prompt word binary tree, the intelligence analysis prompt words configured on the parent node and the child node are read in sequence, wherein the recursive traversal algorithm : ， in: is the target node to be traversed currently. is the parent node (the parent node of the current node N, initially Indicates that the root node has no parent node). are the left and right child nodes of the current node N respectively, is the operation sequence symbol, which means "execute the left operation first, then the right operation". To process the parent-child relationship, output or record the information of the parent node P and the child node N. It is an empty node (indicating that the node does not exist or the traversal terminates); Input the read intelligence analysis prompt word into the preset LLM large language model, so that the LLM large language model searches the data intelligence database based on the intelligence analysis prompt word, analyzes and mines the data intelligence analysis results that match the intelligence analysis prompt word, and outputs them; The output data intelligence analysis result is written and saved to the corresponding parent node or the child node to obtain the data intelligence analysis result corresponding to the parent node or the child node.

4. The data intelligence intelligent analysis method based on the LLM large language model according to claim 3 is characterized in that: S3, according to the relationship between the parent and child nodes, based on the information volume and information importance sorting, orderly counting the data intelligence analysis results of each node and generating a corresponding intelligence network binary tree, including: The amount of information and the importance of information of each node are calculated and sorted, and the data intelligence analysis results at the parent node and each of the child nodes are traversed and counted based on the sorting results; wherein the amount of information and the importance of information are respectively expressed as and : ， in: N: current node, Ai: the th attribute of node N, k: the total number of attributes of node N, wi: the weight of the i-th attribute (indicating the contribution of the attribute to the amount of information), Complexity(Ai): The complexity of the i-th attribute, calculated as follows: If the attribute value is a numeric type: Complexity(Ai) = log2(1 +|Ai|); If the attribute value is of categorical type: Complexity(Ai) = Entropy(Ai), where Entropy(Ai) is the entropy value of the categorical attribute; ， in: Depth(N): the depth of node N in the tree (the root node depth is 0), Degree(N): the connectivity of node N (number of child nodes), Centrality(N): the centrality of node N (betweenness centrality or closeness centrality), Weight coefficients, used to adjust the contribution of each item to importance; Import a new binary tree A, and configure corresponding parent and child nodes of the new binary tree A according to the relationship between the parent and child nodes on the prompt word binary tree; The data intelligence analysis results of the parent node and each of the child nodes obtained by traversal extraction are written into the new binary tree A to obtain the intelligence network binary tree.

5. The data intelligence intelligent analysis method based on the LLM large language model according to claim 4 is characterized in that: The step S4, traversing and verifying the intelligence network binary tree, and outputting and saving the intelligence network binary tree after verification, includes: Pre-configure corresponding data intelligence verification rules for the parent node and each of the child nodes; Utilize the LLM large language model to extract verification keywords, verification scope keywords and corresponding verification logic in the data intelligence verification rules; Combining the verification keyword, the verification scope keyword and the corresponding verification logic, constructing intelligence verification prompt words corresponding to the parent node and each of the child nodes respectively, and configuring the intelligence verification prompt words at the corresponding parent node or the child node; traversing the data intelligence analysis results and the intelligence verification prompt words at the parent node or the child node on the intelligence network binary tree, and inputting the intelligence verification prompt words into the preset LLM large language model; The data intelligence analysis result at the parent node or the child node is verified by the LLM large language model based on the intelligence verification prompt word at the parent node or the child node: If the verification is successful, the parent node or the child node is marked as a passed state; Otherwise it is marked as an alarm state; After verification is completed, the intelligence network binary tree with status marks is output and saved.

6. A data intelligence intelligent analysis device based on an LLM large language model, the data intelligence intelligent analysis device based on an LLM large language model is used to implement the data intelligence intelligent analysis method based on an LLM large language model as claimed in any one of claims 1 to 5, characterized in that: The device comprises: A prompt word construction module is used to construct and configure a prompt word binary tree for data intelligence analysis, wherein the prompt word binary tree includes a parent node and a plurality of child nodes, and the parent node and the child node are respectively configured with intelligence analysis prompt words of corresponding authority; An intelligence mining module is used to traverse the prompt word binary tree based on a recursive traversal algorithm, read the intelligence analysis prompt words on the parent and child nodes in turn and input them into a preset LLM large language model, perform a database search and analysis based on the intelligence analysis prompt words through the LLM large language model, and mine and obtain the data intelligence analysis results corresponding to the parent node or the child node; An intelligence statistics module is used to sequentially count the data intelligence analysis results of each node and generate a corresponding intelligence network binary tree according to the relationship between parent and child nodes and based on the information volume and information importance sorting; The intelligence verification module is used to traverse and verify the intelligence network binary tree, and output and save the intelligence network binary tree after verification.

7. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 5.

Images