Battery performance data automatic extraction system based on large model

Abstract

The invention provides a battery performance data automatic extraction system based on a large model, and relates to the technical field of data extraction, and the system comprises a literature analysis module which is used for reading and analyzing a PDF document of a scientific literature related to a battery, and generating json data; the data preprocessing module is used for carrying out semantic partitioning on the json data and segmenting a text with the same semantic content into short text blocks; the battery performance data extraction module is used for extracting battery performance data from the short text blocks by utilizing multiple rounds of dialogues and a self-verification strategy based on a pre-trained large language model; and the battery performance data structured output module is used for outputting the battery performance data to an excel table in a structured manner. According to the invention, the technical problem that the accuracy of the extraction result is insufficient due to omission or wrong recognition in the face of complex battery performance data in the existing manual or semi-automatic data extraction mode is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data extraction, and in particular to a battery performance data automatic extraction system based on a large model. Background Art

[0002] With the development of battery technology, especially in the fields of electric vehicles and renewable energy storage, the demand for battery performance data is increasing. Traditional methods for extracting battery performance data rely on manual reading and parsing of scientific literature, which is time-consuming and error-prone.

[0003] Battery performance data extraction is the application of text knowledge extraction in downstream tasks. Its core task is to effectively identify and extract battery performance parameter objects and their relationships from complex texts. Most traditional knowledge extraction technologies are based on rules, pattern matching or machine learning methods, such as hidden Markov models HMM, support vector machines SVM, long short-term memory networks LSTM, conditional random fields CRF, and BiLSTM-CRF and other deep learning-based models. With the birth of large language models, more and more models such as BERT and ChatGPT are introduced in the field of knowledge extraction, which transform sequence labeling tasks into generation tasks, autonomously learn knowledge from unlabeled unstructured data, and greatly improve the efficiency of entity extraction. However, due to the defects of large models such as knowledge illusion, logical relationship understanding errors, and lack of context understanding ability, there are still many problems with battery performance data extraction in existing technologies. Summary of the invention

[0004] This application provides an automatic battery performance data extraction system based on a large model, aiming to solve the technical problem that existing manual or semi-automatic data extraction methods have omissions or misidentifications when faced with complex battery performance data, resulting in insufficient accuracy of extraction results.

[0005] The present application discloses a large model-based automatic battery performance data extraction system, which includes: a literature parsing module, which is used to read and parse PDF documents of battery-related scientific literature to generate json data; a data preprocessing module, which is used to semantically segment the json data and divide texts with the same semantic content into short text blocks; a battery performance data extraction module, which is used to extract battery performance data from the short text blocks based on a pre-trained large language model using multiple rounds of dialogue and a self-verification strategy; and a battery performance data structured output module, which is used to output the battery performance data in a structured manner to an excel table.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] Through the literature parsing module, the battery-related scientific literature PDF documents are read and parsed, and the generated json data is parsed into a data format readable by the large model. By converting the literature content into json format, the readability and operability of the data for the large model are guaranteed, supporting the data processing and extraction in the subsequent steps; through the data preprocessing module, the generated json data is semantically segmented, and the text with the same semantic content is divided into short text blocks. By splitting long text blocks into short text blocks, each short text block focuses on a specific battery performance attribute, so that the input text of the large model meets the token number limit of the large model, which makes the subsequent battery performance data extraction more accurate and efficient. Through semantic segmentation, the same semantic content is ensured to be gathered in a short text block, which helps the large language model to accurately understand the text content and extract battery performance data, avoiding information loss, context semantics sparsity and ambiguity problems; battery performance The data extraction module can extract battery performance data from short text blocks based on the pre-trained large language model using multiple rounds of dialogue and self-verification strategies. Through multiple rounds of dialogue, the large model can gradually learn the thinking mode of manual information extraction, and guide the large model to extract each battery performance data according to task requirements to ensure the integrity and consistency of each data. After each extraction, each data is verified through interaction with the large language model to ensure the authenticity and reliability of the data. This self-verification mechanism greatly reduces the risk of erroneous and inconsistent data and improves the credibility of the final output results. The battery performance data structured output module outputs the extracted battery performance data in a structured Excel table. Users can directly use the table for analysis or import it into other analysis tools, avoiding the work of manual sorting and data entry, saving a lot of time and resources, and enhancing the compatibility and flexibility of the system.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the structure of a large model-based automatic battery performance data extraction system provided in an embodiment of the present application.

[0010] Figure 2 A schematic diagram of the structure of a data preprocessing module in a large model-based automatic battery performance data extraction system provided in an embodiment of the present application.

[0011] Figure 3 A schematic diagram of the structure of a battery performance data extraction module in a large model-based automatic battery performance data extraction system provided in an embodiment of the present application.

[0012] Explanation of the accompanying drawings: document parsing module 10, data preprocessing module 20, battery performance data extraction module 30, battery performance data structured output module 40, extraction accuracy analysis unit 21, text block size optimization unit 22, semantic segmentation unit 23, text content analysis unit 31, self-verification unit 32, attribute information output unit 33. DETAILED DESCRIPTION

[0013] The embodiment of the present application solves the technical problem that existing manual or semi-automatic data extraction methods may cause omissions or misidentifications when faced with complex battery performance data, resulting in insufficient accuracy of the extraction results, by providing an automatic battery performance data extraction system based on a large model.

[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a battery performance data automatic extraction system based on a large model, and the system includes:

[0016] The literature parsing module 10 is used to read and parse the PDF documents of battery-related scientific literature and generate json data;

[0017] Use PDF parsing tools to read the content of PDF files, perform document structured parsing through natural language processing, deep learning, OCR and other technologies, extract information such as titles, chapters, paragraphs, tables, etc., and convert the extracted text content into a standardized json format to make it readable by the large model, which contains metadata such as text, paragraphs, paragraph indexes, chapters, etc., and annotate the data in different paragraphs and tables to ensure that subsequent data processing can understand their meaning. Through the literature parsing module, read and parse the battery-related scientific literature PDF documents, generate json data and parse it into a data format readable by the large model. By converting the literature content into json format, the readability and operability of the data for the large model are guaranteed, and the data processing and extraction in the subsequent steps are more efficient.

[0018] The data preprocessing module 20 is used to semantically segment the JSON data and divide the text with the same semantic content into short text blocks;

[0019] Semantic analysis methods are used to understand the text content in the literature and divide the text blocks according to their meanings. For example, if a paragraph involves attributes such as the battery charging cycle and capacity, the paragraph is taken as a semantic block. By analyzing the length of each semantic block, the longer semantic block is automatically cut into multiple short text blocks to ensure that each short block can retain complete semantic information. The cutting criteria can be based on text length, sentence integrity, and context coherence. The obtained short text blocks are usually relatively short and contain relevant information about battery performance in the literature. Through the data preprocessing module, the generated json data is semantically segmented and the text with the same semantic content is segmented into short text blocks. By splitting the long text block into short text blocks, each short text block focuses on a specific battery performance attribute, so that the text of the input large model meets the token number limit of the large model, which makes the subsequent battery performance data extraction more accurate and efficient. Through semantic segmentation, the same semantic content is ensured to be gathered in a short text block, which helps the large language model to accurately understand the text content and extract battery performance data, avoiding information loss, context semantic sparseness and ambiguity.

[0020] A battery performance data extraction module 30, for extracting battery performance data from the short text block based on a pre-trained large language model using a multi-round dialogue and a self-verification strategy;

[0021] A pre-trained large language model refers to a model that is based on large-scale general corpus and trained on general tasks. Short text blocks are input into the pre-trained large language model. The large language model analyzes the text through its powerful semantic understanding ability to determine whether the text contains battery performance data. It uses zero-shot classification technology to classify the text based on known battery performance data types, such as capacity, number of cycles, materials, etc., to identify whether it contains battery performance data.

[0022] Among them, a multi-round dialogue method is adopted to interact with the large language model. By guiding the model through step-by-step questioning, multiple battery performance target data items are generated, including battery capacity, battery material, battery charge and discharge times, etc. Each round of dialogue focuses on one performance attribute to ensure the accuracy of the attribute data. For example, the first round of dialogue asks about the battery capacity, the second round asks about the unit, and the third round asks about the material, etc.

[0023] After each round of dialogue, the extracted data is automatically verified. If the attribute value extracted in a round of dialogue is incorrect, it will be corrected or the uncertain data will be discarded. The self-verification step includes mutual correlation verification of each extracted data item, for example, confirming whether the capacity and unit of the battery are consistent, whether the battery material is reasonable, etc. If the verification fails, the corresponding performance data will be discarded as uncertain data and the current dialogue will be terminated to prevent the transmission of erroneous information.

[0024] After all rounds of dialogue and verification are successful, the complete battery performance data is output as the final output. This data includes various battery performance attributes, including battery performance value, battery performance value unit, battery performance material name, and number of cycles.

[0025] The battery performance data structured output module 40 is used to output the battery performance data in a structured manner to an Excel spreadsheet.

[0026] Convert the extracted battery performance data into a structured format. Specifically, store each battery performance attribute in the corresponding column of an Excel table. Each row represents a battery performance data entry, and the columns represent different performance attributes, such as capacity, battery material, unit, number of cycles, etc. Store the data in a tabular format and ensure data consistency and readability. In this way, users can view and analyze the data directly from Excel, or import the data into other systems or tools for further analysis.

[0027] Furthermore, if Figure 2 As shown, the data preprocessing module 20 includes:

[0028] An extraction accuracy analysis unit 21, used to analyze the knowledge extraction accuracy of different text block sizes of historical extraction records according to the attributes of the knowledge to be extracted;

[0029] A text block size optimization unit 22 is used to optimize the text block size of the knowledge attribute to be extracted according to the knowledge extraction accuracy and the text block size constraint interval of the large language model to obtain a target text block size;

[0030] The semantic chunking unit 23 is used to semantically chunk the JSON data according to the target text chunk size.

[0031] Collect and analyze historical data, including the accuracy of knowledge extraction for a specific battery performance attribute (such as capacity, number of cycles, materials, etc.) under different text block sizes. For example, record the accuracy of short text blocks (such as 200 words) and long text blocks (such as 500 words) in extracting a certain attribute. The extraction accuracy of short text blocks may be higher, or vice versa.

[0032] For each text block size, the extraction accuracy is calculated. These accuracy rates can be measured based on the following factors: the number of correctly extracted attributes, for example, the battery capacity, battery material and other attributes can be successfully extracted; the number of incorrect extractions, that is, the extraction of wrong or irrelevant information; unextracted data, that is, the model failed to extract any valid information. The analysis results provide an extraction accuracy table for different text block sizes for subsequent text block optimization decisions.

[0033] According to the results of the extraction accuracy analysis and in combination with the text block size constraint interval of the large language model, the text block size that is most suitable for extracting the target attribute is automatically determined. Specifically, the text block size constraint interval of the large language model is determined. Different pre-trained large language models have different restrictions on the size of the input text. For example, the maximum number of characters supported is 512, 1024, etc.; according to the knowledge extraction accuracy, a better text block size is selected. For example, if short text blocks have a higher accuracy when extracting capacity data, while long text blocks are more accurate when extracting the number of cycles, these data will be combined to determine the most suitable text block size; the text This block size constraint interval is combined with the accuracy data to optimize the text block size to ensure that the optimization result can not only guarantee a high accuracy rate, but also does not violate the maximum length limit of the model input. Specifically, after obtaining the preliminary analysis results, optimization algorithms such as greedy algorithms, binary search, particle swarm algorithms, etc. can be used to further optimize the text block size to maximize the processing efficiency of the model while ensuring the extraction accuracy. As more data is processed, the block size is adjusted according to the new situation, so that the data extraction effect is continuously optimized. Finally, the optimization algorithm outputs a target text block size as the input of the subsequent semantic segmentation unit.

[0034] According to the optimized target text block size, the JSON data is semantically segmented, and the long text blocks are cut into short text blocks with clear semantics. Specifically, the natural language processing technology is used to perform semantic analysis on the JSON data to be processed to understand the actual meaning of each text block. The semantic analysis helps to identify which parts can be processed as an independent short text block. According to the target text block size obtained from the text block size optimization unit, the longer text is automatically cut into short text blocks that meet the target size. Each short text block should retain complete semantics as much as possible. When cutting, avoid disconnecting the core content of a sentence or paragraph to ensure that each text block can express a complete meaning independently. For example, if a paragraph contains battery materials and performance data, this information is segmented into reasonable blocks without destroying the coherence of the information. Finally, structured JSON data is generated, in which each semantic block can be assigned a text block number and the battery performance attribute information it contains for text block positioning.

[0035] Furthermore, if Figure 3 As shown, the battery performance data extraction module 30 includes:

[0036] A text content analysis unit 31, configured to input the short text block into the large language model for text content analysis, and determine whether the short text block contains battery performance data through zero-sample binary classification;

[0037] a self-verification unit 32 for, if included, extracting multiple performance attribute information of the battery performance through multiple rounds of dialogue with the large language model, and performing self-verification on the extracted performance attribute information after each round of dialogue;

[0038] The attribute information output unit 33 is used to output the multiple pieces of performance attribute information as the battery performance data when all self-verifications are passed.

[0039] The short text block is input into the large language model for text content analysis, specifically, the large model is asked whether the text contains data related to battery coulomb efficiency, so as to determine whether it contains battery performance data.

[0040] If the short text block contains battery performance data, multiple performance attributes of the battery are extracted through multiple rounds of dialogue with the large language model, and self-verification is performed after each round of dialogue to ensure the accuracy of each attribute information. Specifically, the large language model is used for interactive question and answer, and questions and answers are asked and answered in each round of dialogue to extract specific battery performance data items. For example, the first round of dialogue extracts the performance value of the battery (such as capacity value); the second round of dialogue confirms whether the performance value contains units (such as mAh, Ah, etc.); the third round of dialogue extracts the material name of the battery (such as lithium battery, nickel-metal hydride battery, etc.); the fourth round of dialogue inquires and extracts the number of cycles and its units (such as times, hours, etc.).

[0041] The performance attribute information extracted in each round of dialogue needs to be self-verified to ensure the accuracy of the data. Self-verification includes correlation verification, consistency verification, data integrity verification, etc. For example, for each extracted attribute, it is automatically determined whether the correlation between the attribute and other parts of the battery performance is reasonable.

[0042] When all attribute information has passed self-verification, the extracted multiple performance attribute information is output as the final battery performance data. This process combines multiple rounds of dialogue and self-verification strategies to effectively improve the accuracy and credibility of data extraction.

[0043] Furthermore, the text content analysis unit includes:

[0044] The zero-sample binary classification channel is used to perform zero-sample binary classification on the short text block based on a preset database, and determine whether it contains battery performance data according to the binary classification result, wherein the preset database includes data related to battery coulombic efficiency.

[0045] Zero-shot classification is a classification method that does not require labeled data. It uses the capabilities of a pre-trained large language model to classify text. The goal is to determine whether the short text block contains battery performance data. Specifically, the pre-trained large language model automatically classifies the text based on its knowledge of battery performance. The specific classification task is to divide the short text blocks into those containing battery performance data and those not containing battery performance data according to a preset database. The preset database contains data related to battery coulomb efficiency, battery performance data such as battery capacity, materials, life, charge and discharge times, etc. If it does not contain battery performance data, the text block is not a description of battery performance.

[0046] Furthermore, the battery performance data extraction module 30 further includes:

[0047] The discard processing unit is used to discard the extracted performance attribute information as uncertain data and terminate the dialogue when any self-verification fails.

[0048] During multiple rounds of dialogue and self-verification, if any verification fails, for example, the attribute information is wrong, or inconsistent with other information, such as the capacity value and unit do not match, the material name cannot be recognized, etc., then the extracted data is immediately discarded and the current dialogue is terminated to avoid further extraction of invalid or erroneous data and prevent erroneous information from affecting the accuracy of subsequent data.

[0049] Furthermore, the self-verification unit further includes:

[0050] The channel for acquiring multiple performance attribute information is used to extract battery performance values, battery performance value units, battery performance material names, and cycle times in sequence through multiple rounds of dialogue as the multiple performance attribute information.

[0051] The channel for acquiring multiple performance attribute information is the core part of the battery performance data extraction module. It is responsible for gradually extracting multiple performance attribute information of the battery through multiple rounds of dialogue with the pre-trained large language model. These attributes include battery performance value, battery performance value unit, battery performance material name and number of cycles. Specifically, in the first round of dialogue, the battery performance value, such as battery capacity, energy density, etc., is first asked, and the battery performance value information is obtained from the large language model; in the second round of dialogue, after obtaining the battery performance value, the unit of the value, such as mAh, Wh, etc., is asked to obtain the battery performance value unit information; in the third round of dialogue, the material name of the battery, such as lithium battery, nickel-hydrogen battery, etc., is continued to be asked to obtain the battery performance material name information; in the fourth round of dialogue, the battery cycle number, that is, the number of charge and discharge times or service life of the battery, is asked and extracted to obtain the cycle number information. The battery performance value, battery performance value unit, battery performance material name, and cycle number extracted in sequence are integrated as the multiple performance attribute information.

[0052] Furthermore, the self-verification unit further includes:

[0053] The empty set detection channel is used to discard the extracted performance attribute information as incomplete data and terminate the conversation when the extraction result of the non-empty performance attribute information is an empty set, wherein the non-empty performance attribute information includes but is not limited to battery performance values ​​and battery performance material names.

[0054] After each round of conversation, the validity of the attribute information is automatically verified. If in any round, the extraction result of the non-empty performance attribute is an empty set, that is, the data of the attribute cannot be effectively extracted, then the discard process will be executed. The non-empty performance attributes include battery performance values, battery performance material names, etc. The loss of these attributes directly affects the integrity and validity of the extraction results. After the discard process, the current multi-round conversation is terminated immediately to avoid continuing to extract other attributes from invalid data.

[0055] Furthermore, the multiple performance attribute information acquisition channels include:

[0056] Data dictionary retrieval node, used to retrieve compound data dictionary;

[0057] A matching retrieval node is used to perform a semantic matching retrieval in the short text block based on the compound data dictionary to obtain the name of the battery performance material.

[0058] Retrieve the compound data dictionary, which is a database containing the names of various battery materials and their related information (such as chemical elements, chemical formulas, common material names, etc.). The data in the dictionary includes preferred and non-preferred words for battery materials and covers common battery materials, such as lithium (Li), cobalt (Co), nickel (Ni), graphite, etc.

[0059] Use efficient string matching algorithms such as the Boyer-Moore algorithm to preprocess short text blocks and find battery material names that may appear in them. For example, the maximum inverse matching algorithm can be used to match phrases such as "lithium battery" and "lithium cobalt oxide" in short texts. According to the standardized material names in the compound data dictionary, check whether there is content matching the dictionary entries in the short text block. For example, if "LiCoO2" is mentioned in the text, it will be matched by "lithium cobalt oxide" or "lithium cobalt oxide" in the data dictionary. For aliases or non-standardized material names, fuzzy matching algorithms can be used to identify similar words. For example, if "lithium battery" is mentioned in the literature and "Li-ion battery" is in the dictionary, the correct battery material name can be found through similarity matching. Sometimes, the battery material name may not appear alone, but with other content. It can be optimized based on context information to identify and extract the appropriate material name.

[0060] Through matching retrieval, standardized battery material names are extracted from short text blocks, such as "lithium cobalt oxide (LiCoO2)", "nickel cobalt aluminum (NCA)", etc. The matched material names will be marked as valid and passed to subsequent modules for further data extraction or output. If no matching material name is found, it will be marked as missing or incomplete data, and a decision will be made as to whether to discard the data.

[0061] Further, the compound data dictionary includes various aliases and standardized names for materials.

[0062] The compound data dictionary includes multiple aliases and standardized names for materials. For example, lithium battery material may be labeled "LiCoO2" or "lithium cobalt oxide," which all refer to the same chemical composition.

[0063] Furthermore, the self-verification unit further includes:

[0064] A first verification dialogue channel is used to extract the battery performance value and ask a large language model to conduct a verification dialogue on whether the battery performance value is positively correlated with the battery performance;

[0065] The second verification dialogue channel is used to extract the battery performance numerical unit if the answer is yes, and ask the large language model to conduct a verification dialogue on whether the battery performance numerical unit is positively correlated with the battery performance and the battery performance value;

[0066] The third verification dialogue channel is used to extract the name of the battery performance material if the answer is yes, and ask the large language model to conduct a verification dialogue on whether the name of the battery performance material is positively correlated with the battery performance and the battery performance value;

[0067] The fourth verification dialogue channel is used to extract the cycle number, including the cycle number data and unit information, if the answer is yes, and ask the large language model to conduct a verification dialogue on whether the cycle number data and unit information are positively correlated with the cycle number and the battery performance value;

[0068] The data output channel is used to output the battery performance value, battery performance value unit, battery performance material name, and cycle number if the answer is yes.

[0069] The battery performance value extracted from the short text block, such as the battery capacity of 5000, the charging voltage of 3.7, etc., is asked to the large language model to confirm whether the value is related to the battery performance. For example, the extracted value is the coulomb efficiency value corresponding to the correct compound. The large language model determines whether the value has physical meaning and meets the performance characteristics of the battery based on the existing battery knowledge and context information. If the answer is yes, the verification is passed, and the extraction will continue and enter the second verification dialogue channel to start extracting the unit of the battery performance value; if the answer is no, the verification fails, the value will be judged invalid or wrong, marked as uncertain data, and the current verification dialogue will be terminated.

[0070] Based on the extracted performance value, the large language model is asked to confirm whether the value has the correct unit. The large language model answers the unit of the value based on the context, and further confirms whether the unit matches the battery performance value. If the answer is yes, that is, the unit is related to the value and reasonable, such as "5000" corresponds to the "mAh" unit, then the performance attribute information is determined to be valid, and the next battery performance attribute will be extracted; if the answer is no, that is, the unit is inconsistent with the value or unreasonable, for example, the capacity value is "5000" and the unit is "V", then the data is marked as invalid, the current attribute is discarded, and the conversation is terminated.

[0071] Through the verified battery performance values, continue to extract the material name of the battery, such as lithium, cobalt, graphite, etc., and associate the extracted battery material name with the battery performance value (such as capacity, energy density, etc.) for verification. The large language model confirms whether the material meets the performance requirements of the battery based on the battery performance, material properties and physical knowledge. If the answer is yes, the battery material is positively correlated with the performance value. If a battery with a capacity of 5000mAh does use lithium cobalt oxide as a material, the extracted battery material name is considered valid and will continue to enter the fourth verification dialogue channel; if the answer is no, that is, the battery material does not match the performance value, such as the battery material does not match the capacity, the data is determined to be invalid, the current data is discarded and the dialogue is terminated.

[0072] Through the dialogue, the number of cycles and its unit of the battery are further confirmed, and the extracted number of cycles is associated with the battery performance value for verification to ensure that the number of cycles is consistent with the actual battery performance. For example, if the question is "The capacity of this battery is 5000mAh, can it support 1000 cycles?", the large language model determines whether the extracted number of cycles is reasonable based on the technical characteristics, performance range and common industry standards of the battery. If the answer is yes, that is, the number of cycles is consistent with the battery performance value (such as capacity, material, etc.), the number of cycles information is considered valid; if the answer is no, that is, the number of cycles is irrelevant or unreasonable to the battery performance value, for example, a battery with a capacity of 5000mAh can only support 500 cycles instead of 1000 cycles, then the data is determined to be invalid, the current number of cycles data is discarded and the dialogue is terminated.

[0073] If the number of cycles and units are verified, it means that all multi-round dialogue verifications have passed. In this case, all extracted and verified battery performance values, battery performance value units, battery performance material names, and number of cycles are output. This process helps to ensure the accuracy, completeness, and consistency of the output data, and avoid unqualified data from flowing into subsequent analysis and decision-making.

[0074] In summary, the large model-based automatic battery performance data extraction system provided in the embodiments of the present application has the following technical effects:

[0075] Through the literature parsing module, the battery-related scientific literature PDF documents are read and parsed, and the generated json data is parsed into a data format readable by the large model. By converting the literature content into json format, the readability and operability of the data for the large model are guaranteed, supporting the data processing and extraction in the subsequent steps; through the data preprocessing module, the generated json data is semantically segmented, and the text with the same semantic content is divided into short text blocks. By splitting long text blocks into short text blocks, each short text block focuses on a specific battery performance attribute, so that the input text of the large model meets the token number limit of the large model, which makes the subsequent battery performance data extraction more accurate and efficient. Through semantic segmentation, the same semantic content is ensured to be gathered in a short text block, which helps the large language model to accurately understand the text content and extract battery performance data, avoiding information loss, contextual semantic sparsity and ambiguity problems; battery performance The data extraction module can extract battery performance data from short text blocks based on the pre-trained large language model using multiple rounds of dialogue and self-verification strategies. Through multiple rounds of dialogue, the large model can gradually learn the thinking mode of manual information extraction, and guide the large model to extract each battery performance data according to task requirements to ensure the integrity and consistency of each data. After each extraction, each data is verified through interaction with the large language model to ensure the authenticity and reliability of the data. This self-verification mechanism greatly reduces the risk of erroneous and inconsistent data and improves the credibility of the final output results. The battery performance data structured output module outputs the extracted battery performance data in a structured Excel table. Users can directly use the table for analysis or import it into other analysis tools, avoiding the work of manual sorting and data entry, saving a lot of time and resources, and enhancing the compatibility and flexibility of the system.

[0076] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The battery performance data automatic extraction system based on the large model is characterized by: The system comprises: Literature parsing module, used to read and parse PDF documents of battery-related scientific literature and generate json data; A data preprocessing module is used to semantically segment the JSON data and divide text with the same semantic content into short text blocks; A battery performance data extraction module, used to extract battery performance data from the short text block based on a pre-trained large language model using multiple rounds of dialogue and a self-verification strategy; The battery performance data structured output module is used to output the battery performance data in a structured manner to an Excel spreadsheet.

2. The large model-based automatic battery performance data extraction system according to claim 1, characterized in that: The data preprocessing module comprises: An extraction accuracy analysis unit, used to analyze the knowledge extraction accuracy of different text block sizes of historical extraction records according to the attributes of the knowledge to be extracted; A text block size optimization unit, used to optimize the text block size of the knowledge attribute to be extracted according to the knowledge extraction accuracy and the text block size constraint interval of the large language model to obtain a target text block size; The semantic chunking unit is used to semantically chunk the JSON data according to the target text chunk size.

3. The large model-based automatic battery performance data extraction system according to claim 1, characterized in that: The battery performance data extraction module includes: A text content analysis unit, used for inputting the short text block into the large language model to perform text content analysis to determine whether the short text block contains battery performance data; A self-verification unit, for, if included, extracting multiple performance attribute information of battery performance through multiple rounds of dialogue with the large language model, and self-verifying the extracted performance attribute information after each round of dialogue; The attribute information output unit is used to output the multiple pieces of performance attribute information as the battery performance data when all self-verifications are passed.

4. The large model-based automatic battery performance data extraction system according to claim 3, characterized in that: The text content analysis unit comprises: The zero-sample binary classification channel is used to perform zero-sample binary classification on the short text block based on a preset database, and determine whether it contains battery performance data according to the binary classification result, wherein the preset database includes data related to battery coulombic efficiency.

5. The large model-based automatic battery performance data extraction system according to claim 3, characterized in that: The battery performance data extraction module further includes: The discard processing unit is used to discard the extracted performance attribute information as uncertain data and terminate the dialogue when any self-verification fails.

6. The large model-based automatic battery performance data extraction system according to claim 3, characterized in that: The self-verification unit further includes: The channel for acquiring multiple performance attribute information is used to extract battery performance values, battery performance value units, battery performance material names, and cycle times in sequence through multiple rounds of dialogue as the multiple performance attribute information.

7. The large model-based automatic battery performance data extraction system according to claim 6, characterized in that: The self-verification unit further includes: The empty set detection channel is used to discard the extracted performance attribute information as incomplete data and terminate the conversation when the extraction result of the non-empty performance attribute information is an empty set, wherein the non-empty performance attribute information includes but is not limited to battery performance values ​​and battery performance material names.

8. The large model-based automatic battery performance data extraction system according to claim 6, characterized in that: The multiple performance attribute information acquisition channels include: Data dictionary retrieval node, used to retrieve compound data dictionary; A matching retrieval node is used to perform a matching retrieval in the short text block based on the compound data dictionary to obtain the name of the battery performance material.

9. The large model-based automatic battery performance data extraction system according to claim 8, characterized in that: The compound data dictionary includes various aliases and standardized names for materials.

10. The large model-based automatic battery performance data extraction system according to claim 6, characterized in that: The self-verification unit further includes: A first verification dialogue channel is used to extract the battery performance value and ask a large language model to conduct a verification dialogue on whether the battery performance value is positively correlated with the battery performance; The second verification dialogue channel is used to extract the battery performance numerical unit if the answer is yes, and ask the large language model to conduct a verification dialogue on whether the battery performance numerical unit is positively correlated with the battery performance and the battery performance value; The third verification dialogue channel is used to extract the name of the battery performance material if the answer is yes, and ask the large language model to conduct a verification dialogue on whether the name of the battery performance material is positively correlated with the battery performance and the battery performance value; The fourth verification dialogue channel is used to extract the cycle number, including the cycle number data and unit information, if the answer is yes, and ask the large language model to conduct a verification dialogue on whether the cycle number data and unit information are positively correlated with the cycle number and the battery performance value; The data output channel is used to output the battery performance value, battery performance value unit, battery performance material name, and cycle number if the answer is yes.

Images