Text content analysis method and system, computer device, medium, and product

Abstract

The embodiment of the invention discloses a text content analysis method and system, a computer device, a medium and a product. The text content analysis method comprises the steps of performing content analysis on a to-be-analyzed text, extracting target information, determining a text level according to the target information, and calling a corresponding number of analysis agents according to the text level; obtaining content quality analysis information, language expression analysis information and structural arrangement analysis information based on each analysis agent; obtaining the similarity between the target information and each analysis agent, and then obtaining the confidence of each analysis agent; then analyzing information and confidence of all analysis agents in three aspects are combined to obtain analysis results of three dimensions of content quality, language expression and structural arrangement; and obtaining a text content analysis result based on the content quality dimension analysis result, the language expression dimension analysis result and the structural arrangement dimension analysis result. According to the method, dynamic, comprehensive, accurate and rapid analysis can be realized according to the text content.

Description

(19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number (43) Application Publication Date (21) Application Number 202511397498.4 (22) Application Date 2025.09.28 (71) Applicant Beijing Qingsong Yikang Information Technology Co., Ltd. Address 7th Floor, Block F, Yonghe Building, No. 28 Andingmen East Street, Dongcheng District, Beijing 100007 (72) Inventors Yang Yin, Jia Weida, Huang Xiandong, Zhang Da (74) Patent Agency Beijing Youyijia Intellectual Property Agency (General Partnership) 16075 Patent Attorney Sun Jianfeng (51) Int.Cl. G06F 40 / 205 (2020.01) G06N 5 / 04 (2023.01) G06N 3 / 006 (2023.01) G06F 18 / 22 (2023.01) G06F 18 / 21 (2023.01) (54) Invention Title: Text Content Analysis Method and System, Computer Device, Medium, Product (57) Abstract: This disclosure presents a text content analysis method and system, computer device, medium, and product. The text content analysis method includes: parsing the text to be analyzed, extracting target information, determining the text level accordingly, and then calling a corresponding number of analysis agents based on the text level; obtaining content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analysis agent; obtaining the similarity between the target information and each analysis agent, and then obtaining the confidence level of each analysis agent; combining the three aspects of analysis information and confidence levels of all analysis agents to obtain analysis results in three dimensions: content quality, language expression, and structural arrangement; and obtaining text content analysis results based on the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results. This method can achieve dynamic, comprehensive, accurate, and rapid analysis based on text content. Claims 3 pages, Description 11 pages, Drawings 3 pages, CN 121328519 A 2026.01.13 CN 1 21 32 85 19 A 1. A text content analysis method, characterized in that it includes: performing content parsing on the text to be analyzed, extracting target information, the target information including keywords, technical field, and text complexity; determining the text level according to the target information; calling a corresponding number of analysis agents according to the text level; obtaining content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analysis agent; obtaining the similarity between the target information and each analysis agent, and obtaining the confidence level of each analysis agent based on the similarity; and determining the confidence level of each analysis agent based on the content quality analysis information, language expression analysis information, and structural arrangement analysis information corresponding to all analysis agents.Based on the structural arrangement analysis information and the confidence level, the analysis results of the content quality dimension, language expression dimension, and structural arrangement dimension are obtained; based on the analysis results of the content quality dimension, language expression dimension, and structural arrangement dimension, the analysis results of the text content are obtained. 2. The text content analysis method according to claim 1, characterized in that the method for obtaining text complexity includes: obtaining the number of words, the number of technical terms, the total number of words, the total number of sentences, and the number of words, the number of compound sentences, and the number of cited references for each sentence based on the text to be analyzed; obtaining the word count dimension score corresponding to the number of words according to a preset word count interval scoring rule; obtaining the technical term density according to the number of technical terms and the total number of words, and obtaining the technical term density dimension score corresponding to the technical term density according to a preset technical term density interval scoring rule; identifying all sentences whose word count exceeds a preset character limit and recording them as long sentences; obtaining the sentence structure density according to the number of compound sentences, the total number of long sentences, and the total number of sentences; obtaining the sentence structure density dimension score corresponding to the sentence structure density according to a preset sentence structure density interval scoring rule; obtaining the reference citation dimension score corresponding to the number of cited references according to a preset reference citation interval scoring rule; and obtaining the text complexity by weighted summation of the word count dimension score, the technical term density dimension score, the sentence structure density dimension score, and the reference citation dimension score according to preset weights. 3. The text content analysis method according to claim 2, characterized in that, determining the text level based on the target information includes: determining the text professional depth score based on the number and coverage of the keywords; determining the text difficulty score based on the technical field; weighting and summing the text professional depth score, the text difficulty score, and the text complexity according to preset weights to obtain a target comprehensive score; determining the text level based on the target comprehensive score, wherein the text level is any one of ordinary, medium, and complex. 4. The text content analysis method according to claim 3, characterized in that, calling the corresponding number of analysis agents based on the text level includes: when the text level is ordinary, sending the text to M analysis agents; when the text level is medium, sending the text to N analysis agents; when the text level is complex, sending the text to P analysis agents; wherein, P > N > M ≥ 1. 5. The text content analysis method according to claim 1, wherein obtaining the similarity between the target information and each of the analysis agents, and obtaining the confidence level of each analysis agent based on the similarity, comprises: obtaining historical training data of each analysis agent;Obtain the cosine similarity between the target information and the historical training data; based on the cosine similarity and a preset similarity scoring table, obtain the confidence level of the analysis agent corresponding to the similarity. 6. The text content analysis method according to claim 5, characterized in that the content quality dimension analysis result is N: ; the language expression dimension analysis result is Y: ; the structure arrangement dimension analysis result is: ; where is the content quality analysis information corresponding to the i-th analysis agent, is the confidence level of the i-th analysis agent, P is the total number of analysis agents, is the language expression analysis information corresponding to the i-th analysis agent, and is the structure arrangement analysis information corresponding to the i-th analysis agent. 7. A text content analysis system, characterized in that it comprises: an information extraction module, used to parse the text to be analyzed and extract target information, the target information including keywords, technical fields, and text complexity; a text level determination module, used to determine the text level based on the target information; an agent invocation module, used to invoke a corresponding number of analysis agents according to the text level; and obtain content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analysis agent; a confidence score acquisition module, used to obtain the similarity between the target information and each analysis agent, and obtain the confidence score of each analysis agent based on the similarity; a multi-dimensional analysis module, used to obtain content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results based on the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results corresponding to all analysis agents; and a content analysis result acquisition module, used to obtain text content analysis results based on the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results. 8. A computer device, characterized in that the computer device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the text content analysis method according to any one of claims 1-7. 9. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing a computer to perform the text content analysis method according to any one of claims 1-7. Claims 2 / 3 pages 3 CN 121328519 A 10. A computer program product comprising computer instructions, characterized in that, when executed by a processor, the computer instructions implement the steps of the method according to any one of claims 1-7. Claims 3 / 3 pages 4 CN121328519 A Text Content Analysis Method and System, Computer Device, Medium, Product Technical Field

[0001] This disclosure relates to the field of text analysis technology, and in particular to a text content analysis method and system, computer device, medium, and product. Background Art

[0002] In the modern information society, articles, as key carriers of information dissemination, are crucial to the dissemination effect and value realization. Different types of articles, such as academic papers, technical documents, and business reports, all require accurate quality assessment to ensure that they play their due role in their respective fields. Traditionally, article quality assessment mainly relies on expert reviews. Experts can deeply analyze articles based on their professional knowledge and experience, but this method is no longer suitable for modern needs.

[0003] Traditional article review methods have a series of problems. First, the determination of the number of expert reviews lacks scientific basis, resulting in incomplete reviews or waste of resources. Second, there is no clear limit to the number of reviews for each article, which easily leads to repetitive reviews and low efficiency. Third, the scoring rules are not uniform, and the review results are highly subjective, making it difficult to quantify the quality of the articles. Fourth, manual review and scoring calculation are time-consuming, affecting the efficiency and accuracy of the assessment.

[0004] In view of the above, embodiments of the present disclosure provide a text content analysis method and system, computer device, medium, and product, which can solve the problems of poor accuracy and low efficiency of text evaluation results in the prior art.

[0005] In a first aspect, embodiments of the present disclosure provide a text content analysis method, comprising: parsing the text to be analyzed to extract target information, the target information including keywords, technical fields, and text complexity; determining the text level according to the target information; calling a corresponding number of analysis agents according to the text level; obtaining content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analysis agent; obtaining the similarity between the target information and each analysis agent, and obtaining the confidence level of each analysis agent based on the similarity; obtaining content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results based on the content quality dimension analysis results, language expression dimension analysis results, structural arrangement dimension analysis results, and confidence levels corresponding to all analysis agents; and obtaining text content analysis results based on the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results.

[0006] In a second aspect, embodiments of this disclosure also provide a text content analysis system, comprising: an information extraction module, configured to parse the text to be analyzed and extract target information, the target information including keywords, technical fields, and text complexity; a text level determination module, configured to determine the text level based on the target information; and an agent invocation module, configured to invoke a corresponding number of analysis agents based on the text level; based on each specificationPage 1 / 11, CN 121328519 A: The analytical agent obtains content quality analysis information, language expression analysis information, and structural arrangement analysis information; a confidence acquisition module is used to obtain the similarity between the target information and each analytical agent, and obtain the confidence of each analytical agent based on the similarity; a multi-dimensional analysis module is used to obtain content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results based on the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results corresponding to all analytical agents; a content analysis result acquisition module is used to obtain text content analysis results based on the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results.

[0007] In a third aspect, embodiments of this disclosure also provide a computer device, employing the following technical solution: The computer device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the above-described text content analysis methods.

[0008] In a fourth aspect, embodiments of this disclosure also provide a computer-readable storage medium storing computer instructions for causing a computer to perform any of the above-described text content analysis methods.

[0009] In a fifth aspect, embodiments of this disclosure also provide a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of any of the above-described methods.

[0010] The text content analysis method disclosed in this application firstly parses the text to be analyzed and extracts target information, including keywords, technical fields, and text complexity; then, it determines the text level based on the target information and calls the corresponding number of analysis agents according to the text level to ensure the accuracy and comprehensiveness of the analysis; secondly, it obtains content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analysis agent, enabling a comprehensive evaluation of the text; next, it obtains the similarity between the target information and each analysis agent, and obtains the confidence level of each analysis agent based on the similarity; based on the content quality analysis information, language expression analysis information, structural arrangement analysis information, and confidence level corresponding to all analysis agents, it obtains the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results, and integrates the analysis information of multiple analysis agents to fully utilize the advantages of each analysis agent while considering its credibility, thus obtaining more objective and accurate analysis results for each dimension; finally, based on the content quality dimension analysis results...The results of the analysis of the results of the language expression dimension and the structural arrangement dimension are used to obtain the text content analysis results. By combining the analysis results of each dimension, the text content can be comprehensively and objectively evaluated as a whole, providing users with a clear text quality assessment result.

[0011] The above description is only an overview of the technical solution of this disclosure. In order to better understand the technical means of this disclosure and to implement it according to the contents of the specification, and to make the above and other objects, features and advantages of this disclosure more obvious and understandable, the following are preferred embodiments, and are described in detail with reference to the accompanying drawings. Description of the drawings

[0012] In order to more clearly illustrate the technical solution of the embodiments of this disclosure, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Specification 2 / 11 pages 6 CN 121328519 A

[0013] Figure 1 is a flowchart of the text content analysis method provided by the embodiments of this disclosure.

[0014] Figure 2 is a flowchart illustrating the method for obtaining text complexity provided in an embodiment of this disclosure.

[0015] Figure 3 is a flowchart illustrating the method for obtaining the confidence level of each analytical agent provided in an embodiment of this disclosure.

[0016] Figure 4 is a structural schematic diagram of a computer device provided in an embodiment of this disclosure. Detailed Description

[0017] The embodiments of this disclosure will be described in detail below with reference to the accompanying drawings.

[0018] It should be understood that the following specific examples illustrate the implementation of this disclosure, and those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. This disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0019] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways.For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, other structures and / or functionalities besides one or more of the aspects set forth herein can be used to implement this device and / or practice the method.

[0020] It should also be noted that the illustrations provided in the following embodiments are merely schematic representations of the basic concept of this disclosure. The drawings only show components relevant to this disclosure and are not drawn according to the actual number, shape, and size of components in implementation. In actual implementation, the type, quantity, and proportion of each component can be arbitrarily changed, and the component layout may also be more complex.

[0021] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the aspects described can be practiced without these specific details.

[0022] Referring to Figure 1, this application discloses a text content analysis method, including: S100, parsing the text to be analyzed and extracting target information, including keywords, technical fields, and text complexity; S200, determining the text level based on the target information; S300, calling the corresponding number of analysis agents according to the text level; obtaining content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analysis agent; S400, obtaining the similarity between the target information and each analysis agent, and obtaining the confidence level of each analysis agent based on the similarity; S500, obtaining the content quality dimension analysis result, language expression dimension analysis result, and structural arrangement dimension analysis result based on the content quality analysis information, language expression analysis information, structural arrangement analysis information, and confidence level corresponding to all analysis agents. Specification 3 / 11 Page 7 CN 121328519 A

[0023] Specifically, the content quality dimension analysis result is N: .

[0024] The language expression dimension analysis result is Y: .

[0025] The structural arrangement dimension analysis result is: .

[0026] Wherein, is the content quality analysis information corresponding to the i-th analysis agent, is the confidence level of the i-th analysis agent, P is the total number of analysis agents, is the language expression analysis information corresponding to the i-th analysis agent, and is the structural arrangement analysis information corresponding to the i-th analysis agent.

[0027] S600, based on the content quality dimension analysis result, language expression dimension analysis result, and structural arrangement dimension analysis result, the text content analysis result is obtained.

[0028] Wherein, the text content analysis result includes at least one of the following: the overall analysis score of the text content, analysis information of each dimension, and corresponding improvement suggestions.

[0029] The text content analysis method disclosed in this application analyzes the text from multiple perspectives, including content quality, language expression dimension analysis, and structural arrangement dimension analysis.The text content analysis method disclosed in this application is an automated and standardized text analysis method that can effectively meet the requirements of modern information society for text evaluation and achieve high efficiency and high accuracy in text evaluation.

[0030] Referring to Figure 2, the method for obtaining text complexity includes: A100, obtaining the number of words, professional terms, total words, total number of sentences, and the number of words, compound sentences, and cited references based on the text to be analyzed.

[0031] Each sentence is divided using a period, exclamation mark, or question mark as an identifier, and is judged as a sentence.

[0032] A200, according to the preset word count range scoring rules, obtain the word count dimension score corresponding to the word count of the article.

[0033] Specifically, when the word count of the article is in the range of 0-500, the word count dimension score is 1; when the word count is in the range of 501-1500, the word count dimension score is 2; when the word count is above 1501, the word count dimension score is 3. This scoring method allows the impact of word count on text complexity to be presented in a quantitative form.

[0034] A300, obtain the terminology density based on the number of professional terms and the total number of words, and obtain the terminology density dimension score corresponding to the terminology density according to the preset terminology density range scoring rules.

[0035] Wherein, the terminology density is the value of the number of professional terms and the total number of words. When the density of professional terms is in the range of 0-0.1, the score for the term density dimension is 1; when it is in the range of 0.11-0.3, the score for the term density dimension is 2; and when it is above 0.31, the score for the term density dimension is 3. Calculating the density of professional terms and assigning scores according to the preset range can objectively measure the professionalism of the text. The density of professional terms reflects the proportion of professional words in the text. Different density ranges correspond to different scores, which helps to distinguish texts of different professional levels. For example, a popular science article may have a low density of professional terms and a low score, indicating that it is suitable for general readers; while a professional academic paper has a high density of professional terms and a high score, indicating that it is mainly aimed at professionals in the field.

[0036] A400, identify all sentences whose word count exceeds the preset character count and record them as long sentences; according to the number of compound sentences and the total number of long sentences, the total number of sentences is 4 / 11 pages 8 CN 121328519 AThe sentence density is obtained by considering the number of sentences and the total number of sentences. The sentence density dimension score is obtained according to the preset sentence density interval scoring rules.

[0037] Sentence density is the ratio of the sum of the number of compound sentences and the total number of long sentences to the total number of sentences. When the sentence density is in the range of 0-0.2, the sentence density dimension score is 1; in the range of 0.21-0.5, the sentence density dimension score is 2; and above 0.51, the sentence density dimension score is 3. Sentence density comprehensively considers the relationship between the number of compound sentences, the number of long sentences, and the total number of sentences, and can comprehensively reflect the complexity of the text in terms of sentence structure. The higher the sentence density, the greater the proportion of complex sentences in the text, and the more difficult it is to understand.

[0038] A500, the citation dimension score corresponding to the number of cited documents is obtained according to the preset citation interval scoring rules.

[0039] Specifically, when the number of cited references is 0, the score for the citation dimension is 1; when the number of cited references is between 1 and 3, the score for the citation dimension is 2; when the number of cited references is above 4, the score for the citation dimension is 3. The more cited references there are, the more professional knowledge and previous research results the text involves, and readers need to have a certain professional background and knowledge reserve to better understand the text.

[0040] A600, according to the preset weights, the scores for the word count dimension, term density dimension, sentence density dimension, and citation dimension are weighted and summed to obtain the text complexity.

[0041] According to the preset weights, the scores for each dimension are weighted and summed to comprehensively consider the influence of multiple factors on the text complexity and obtain a comprehensive and objective text complexity assessment result. Different dimensions may have different levels of importance in the text complexity, and this difference can be reflected by setting weights.

[0042] The method of S200 "determining the text level according to the target information" includes: S210, when the number of keywords and the coverage determine the text professional depth score.

[0043] Specifically, the number of keywords in the text is counted. If the number is between 0 and 3, a score of 1 is assigned; if the number is between 4 and 6, a score of 2 is assigned; if the number is between 7 and 9, a score of 3 is assigned; and if the number is more than 10, a score of 4 is assigned. If the coverage of all keywords only involves a single, broad basic professional field, and the keywords are mostly basic concepts, the coverage level is determined to be primary, and the corresponding score is 1. If the coverage of all keywords involves multiple aspects of a professional field, or covers a small number of related professional fields, the coverage level is determined to be intermediate, and the corresponding score is 2. If the coverage of all keywords involves multiple different professional fields, and the keywords cover professional concepts at different levels, the coverage level is determined to be advanced, and the corresponding score is 3.

[0044] If the coverage of all keywords spans multiple professional fields and has in-depth and comprehensive coverage of each field, the coverage level is determined to be top level, and the corresponding scope score is 4 points.

[0045] Finally, the quantity score and scope score are weighted and summed according to the preset weights to obtain the text professional depth score. This method can objectively and accurately calculate the professional depth score of the text, providing an important basis for subsequent text level evaluation.

[0046] S220, determine the text difficulty score according to the technical field.

[0047] Specifically, this includes: determining the field popularity and field crossover according to the technical field; determining the text difficulty score according to the field popularity and field crossover. Among them, if the technical field is a field that is generally known to the public (such as common sense, basic science, etc.) and does not involve more than two different technical fields, the text difficulty score is determined to be 1 point; if the technical field is a field that is generally known to the public and involves more than two different technical fields, the text difficulty score is determined to be 2 points; if the technical field is not a field that is generally known to the public and does not involve more than two different technical fields, the text difficulty score is determined to be 3 points; if the technical field is not a field that is generally known to the public and involves more than two different technical fields, the text difficulty score is determined to be 4 points.

[0047] In this step, the text difficulty score is determined by combining the popularity of the technical field and the crossover of fields, which can comprehensively consider the characteristics of the fields involved in the text; the popularity of the field determines the public's familiarity with the field, while the crossover of fields reflects the comprehensiveness and complexity of the text knowledge. Through clear scoring rules, the text difficulty of different fields and crossover situations is quantified, avoiding the bias of subjective judgment.

[0048] S230, the text professional depth score, text difficulty score, and text complexity score are weighted and summed according to preset weights to obtain the target comprehensive score.

[0049] The text professional depth score, text difficulty score, and text complexity score are weighted and summed according to preset weights, which can comprehensively consider the influence of multiple factors on the overall characteristics of the text. Different factors have different importance in text level evaluation. By setting weights, this difference can be accurately reflected. The scores of multiple dimensions are integrated into a comprehensive score, which provides a unified and objective evaluation standard for determining the text level, avoids the one-sidedness of single factor evaluation, and makes the evaluation results more accurate and reliable.

[0050] S240, the text level is determined according to the target comprehensive score. The text level is any one of ordinary level, medium level, and complex level.

[0051] Specifically, the correspondence between the comprehensive score of different intervals and the text level can be flexibly set according to the needs.

[0052] The method of "calling the corresponding number of analysis agents according to the text level" in S300 specifically includes: whenWhen the text level is ordinary, the text is sent to M analytical agents; when the text level is medium, the text is sent to N analytical agents; when the text level is complex, the text is sent to P analytical agents; where P > N > M ≥ 1.

[0053] More preferably, 1 ≤ M ≤ 2, 3 ≤ N ≤ 5, 6 ≤ P ≤ 10.

[0054] In this embodiment, different levels of text have different requirements for analysis and processing. Ordinary level text content is relatively simple, professional and less complex, and the analysis task can be completed with a smaller number of analytical agents, avoiding excessive investment of resources; complex level text contains a large amount of professional knowledge, complex logic and rich details, requiring more computing resources and analysis capabilities. Calling P analytical agents can give full play to the collaborative role of multiple agents, conduct in-depth analysis of the text from different angles, and ensure the accuracy and comprehensiveness of the analysis results. For example, for a cutting-edge academic paper involving multiple fields, multiple agents can process the content of different professional fields respectively and jointly complete the interpretation of the paper.

[0055] As the text level increases, the information content and complexity of the text increase. Increasing the number of analytical agents can ensure comprehensive coverage of the text and avoid missing important information. Multiple agents can analyze the text from different perspectives, complementing and verifying each other, thus improving the reliability of the analysis results. Medium- and complex texts often contain complex logical relationships and professional knowledge, which a single agent cannot fully understand and process. Multiple agents can rely on their respective knowledge reserves and analytical capabilities to jointly address these challenges and improve the analysis effect on complex texts.

[0056] By rationally allocating the number of analytical agents according to the text level, excessive agents are avoided when processing simple texts, thereby reducing the consumption and cost of computing resources. At the same time, for complex texts, although the number of agents increases, the overall resource utilization efficiency is improved and the unit analysis cost is reduced because the analysis tasks can be completed more efficiently. This method helps to optimize resource allocation, enabling limited analytical agent resources to better meet the analysis needs of texts at different levels. In the case of limited resources, resources can be rationally allocated according to the actual situation of the text to ensure that important and complex texts are fully analyzed and processed.

[0057] This method has a certain degree of flexibility, and the value ranges of M, N, and P can be adjusted according to the actual situation to adapt to different application scenarios and analysis needs. For example, in scenarios where the accuracy of text analysis is required to be high, the number of agents corresponding to each level can be appropriately increased; as the business develops and the amount of text increases, the processing capacity of the system can be expanded by increasing the total number of analysis agents (see page 6 / 11 of the specification, 10 CN 121328519 A); at the same time, the mechanism of dynamically calling agents according to the text level can ensure that the system can still make efficient and reasonable use of resources during the expansion process.

[0058] In this implementation, the analytical agent is preferably a large model. Further, the analytical agent can also be an expert or a large model built based on expert information.

[0059] Specifically, an expert profile can be constructed based on each expert's professional field, rating history, available time, and workload. When real experts are not required to participate in the analysis, a corresponding analytical agent can be constructed based on the expert profile.

[0060] When real experts are required to participate in the analysis, an expert database can be established first. For example, the expert database records detailed information about each expert, including: professional field identifier (e.g., cardiovascular diseases, endocrine diseases, nervous system diseases, etc.), expert authority coefficient (range 0.1-1.0), daily workload limit (e.g., a maximum of 10 articles reviewed per day), available time period (e.g., 9:00-12:00 AM, 2:00-6:00 PM), historical rating quality index, etc. When starting the analysis, the expert matching algorithm is activated. The algorithm employs a multi-factor comprehensive scoring mechanism: 1) Professional matching degree calculation: The system calculates the similarity between the article's technical field and the expert's professional field using a cosine similarity algorithm. Domain keywords are converted into vectors, and the cosine value of the angle between the vectors is calculated. The higher the similarity, the higher the matching degree; 2) Workload assessment: The system monitors each expert's current workload in real time, including the number of assigned but uncompleted review tasks and the estimated completion time. Experts with lighter workloads are prioritized to ensure a balanced task allocation; 3) Time availability check: The system selects experts who can complete the review within the required time based on the article's urgency and the expert's available time period; 4) Expert number determination rules: For low-complexity articles, 3 experts are assigned; for medium-complexity articles, 5 experts are assigned; and for high-complexity articles, 7 experts are assigned. The system also considers the article's importance level; for important articles, the number of experts can be appropriately increased.

[0061] For "obtaining content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analytical agent" in S300, the content quality analysis information includes scoring for sufficiency of arguments (0-15 points), logical rigor (0-15 points), and professional accuracy (0-10 points), and then automatically calculating the total content quality score.

[0062] The language expression analysis information includes three sub-items: accuracy of word choice (0-10 points), clarity of expression (0-10 points), and standardization of language (0-10 points), and then automatically calculating the total content quality score. The structural arrangement analysis information covers logical structure (0-15 points), paragraph arrangement (0-10 points), and overall layout (0-5 points), and then automatically calculating the total content quality score.

[0063] Each scoring item provides detailed scoring criteria explanations and examples to ensure scoring consistency, and can also output specific review comments, explaining the reasons for deductions and improvement suggestions.

[0064] Referring to Figure 3, the method for S400, "obtaining the similarity between the target information and each analytical agent, and obtaining the confidence level of each analytical agent based on the similarity", includes the following steps for obtaining the confidence level of each analytical agent: S410, obtaining historical training data for each analytical agent; S420, obtaining the cosine similarity between the target information and the historical training data; S430, obtaining the confidence level of the analytical agent corresponding to the similarity based on the cosine similarity and a preset similarity scoring table.

[0065] Specifically, a cosine similarity in [0, 0.2) corresponds to a confidence level of 0.1; a cosine similarity in [0.2, 0.4) corresponds to a confidence level of 0.3; a cosine similarity in [0.4, 0.6) corresponds to a confidence level of 0.5; a cosine similarity in [0.6, 0.8) corresponds to a confidence level of 0.7; and a cosine similarity in [0.8, 1] corresponds to a confidence level of 0.9.

[0066] In this embodiment, by acquiring the historical training data of each analytical agent and calculating the cosine similarity between the target information and the historical training data, the agent's ability to process the current target information can be evaluated from its past performance. The historical training data reflects the knowledge domain and patterns that the agent learns and adapts to. If the target information has a high similarity to the historical training data, it indicates that the agent has rich experience in processing this type of information, and its analysis results are more reliable. Specification 7 / 11 pages 11 CN 121328519 A

[0067] The cosine similarity is converted into a confidence score according to a preset similarity scoring table. The reliability of each analytical agent is measured by a specific value. In this way, when using the results of the analytical agents in the future, the results can be screened, weighted, or comprehensively judged based on the confidence score, avoiding blind reliance on unreliable analysis results, thereby improving the reliability of the overall analysis results.

[0068] Different target information may differ in content, structure, and domain. By calculating similarity and confidence, each analytical agent can be assigned a corresponding confidence level for different types of target information, enabling the system to flexibly select appropriate analytical agents based on the characteristics of the target information. For example, for target information in the medical field, agents with high similarity and confidence levels to the target information in historical medical training data will be given priority.

[0069] As time goes by and the agents are continuously trained, their performance may change. By continuously calculating similarity and confidence, the adaptability and reliability of each agent to different target information can be monitored in real time, changes in agent performance can be detected in a timely manner, and corresponding adjustments can be made to ensure the adaptability and flexibility of the system.

[0070] Furthermore, the analysis results of content quality dimension, language expression dimension, and structural arrangement dimension can be compared with the target content score, target language score, and target structure score respectively to obtain differential analysis.As a result, the differential analysis results include gaps in content quality, language expression, and structural arrangement.

[0071] Based on the size of the gap and the difficulty of improvement, each dimension is prioritized, with higher priority given to dimensions that have larger gaps and are relatively easier to improve.

[0072] Furthermore, personalized optimization strategies can be generated based on the differential analysis results. Specifically, based on the current rating level, relevant templates are retrieved from the corresponding strategy library, and the matching process considers factors such as article theme, professional field, and target readers. For insufficient content quality, the system analyzes the existing content structure of the article and identifies the missing key elements. For example, for articles lacking case support, it is recommended to "add 2-3 typical clinical cases, each case including symptom description, diagnosis process, treatment plan, and effect evaluation". Analyze the language characteristics of the article and identify expression problems. For cases of inappropriate terminology, it is recommended to "standardize 'stomach ache' as 'abdominal pain' and refine 'heart disease' to specific disease names such as 'coronary heart disease' or 'arrhythmia'". The logical structure of the article is evaluated, structural problems are identified, and for articles with chaotic logic, it is recommended to "reorganize the content according to the logical order of 'disease overview - etiology analysis - symptom manifestation - diagnostic methods - treatment plan - prevention measures'".

[0073] Furthermore, this application also includes establishing a dynamic feedback mechanism to continuously optimize the strategy generation effect. Specifically, when a user modifies the article according to the suggestions and resubmits it for review, the score change before and after the modification is recorded, and the actual effect of each suggestion is calculated. Among them, multi-dimensional evaluation indicators are adopted, including the improvement range (i.e., the degree of score improvement after modification), implementation difficulty (i.e., the proportion of users who adopt the suggestions) and time efficiency (i.e., the time from suggestion to improvement completion). Then, based on the effect evaluation results, the system dynamically adjusts the weight of the strategy template. The weight of the strategy template with good effect is increased and it is given priority in subsequent matching; the weight of the strategy template with poor effect is reduced.

[0074] Furthermore, the common characteristics of efficient strategies can also be analyzed periodically to generate new strategy templates, while outdated templates with poor long-term effects are eliminated.

[0075] Furthermore, this application also includes: supporting multiple rounds of optimization iterations for articles; specifically, establishing a version management mechanism for each article to record information such as the content, time, and adopted suggestions of each modification, allowing users to view the complete evolution of the article; for resubmitted articles, the system adopts an incremental review mechanism, focusing on the quality improvement of the modified parts while checking whether the modifications introduce new problems; setting progressive goals for each round of optimization. The first round focuses on solving basic problems, the second round focuses on improving details, and the third round pursues excellent quality.

[0076] Furthermore, this application also includes: establishing a multi-level quality assurance mechanism; specifically, monitoring the consistency of scores in real time, and automatically triggering a review mechanism when a large difference in scores is found, inviting senior experts or more professional large models to review the results.121328519 A Arbitration Scoring; Statistical methods are used to detect abnormal scoring behavior, such as a significant deviation of an expert's score from other experts or an unusually short scoring time; Regular scoring quality reports are provided to experts, including indicators such as scoring consistency and suggestion adoption rate, to help experts improve the quality of their reviews. For frequently accessed data such as expert information and strategy templates, a multi-level caching mechanism is used to reduce the number of database accesses; Load balancing technology is used to reasonably distribute review tasks across different servers to avoid single-point overload.

[0077] In a second aspect, embodiments of this disclosure also provide a text content analysis system for executing the text content analysis method disclosed in the first aspect of this application. The system specifically includes: an information extraction module for parsing the text to be analyzed and extracting target information, including keywords, technical fields, and text complexity; a text level determination module for determining the text level based on the target information; an agent invocation module for invoking a corresponding number of analysis agents based on the text level; and obtaining content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analysis agent; a confidence level acquisition module for obtaining the similarity between the target information and each analysis agent, and obtaining the confidence level of each analysis agent based on the similarity; a multi-dimensional analysis module for obtaining content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results based on the content quality dimension analysis information, language expression dimension analysis information, structural arrangement analysis information, and confidence level corresponding to all analysis agents; and a content analysis result acquisition module for obtaining text content analysis results based on the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results.

[0078] A computer device according to an embodiment of the present disclosure includes a memory and a processor. The memory is used to store non-transitory computer-readable instructions. Specifically, the memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may, for example, include read-only memory (ROM), hard disk, flash memory, etc.

[0079] The processor may be a central processing unit (CPU) or other forms of processing unit having data processing capabilities and / or instruction execution capabilities, and may control other components in the computer device to perform desired functions. In one embodiment of the present disclosure, the processor is used to run the computer-readable instructions stored in the memory, causing the computer device to perform all or part of the steps of the text content analysis method of the foregoing embodiments of the present disclosure.

[0080] Those skilled in the art should understand that, in order to solve the technical problem of how to obtain a good user experience, the present disclosure...The embodiments may also include known structures such as communication buses and interfaces, and these known structures should also be included within the protection scope of this disclosure.

[0081] FIG4 is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure. It shows a schematic diagram of the structure suitable for implementing the computer device in the embodiment of this disclosure. The computer device shown in FIG4 is merely an example and should not impose any limitations on the function and scope of use of the embodiments of this disclosure.

[0082] As shown in FIG4, the computer device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). Various programs and data required for the operation of the computer device are also stored in the RAM. The processor, ROM, and RAM are interconnected through a bus. Input / output (I / O) interfaces are also connected to the bus.

[0083] Typically, the following devices can be connected to the I / O interface: input devices, including, for example, sensors or visual information acquisition devices (see page 9 / 11 of CN 121328519 A); output devices, including, for example, displays; storage devices, including, for example, magnetic tapes, hard disks; and communication devices. Communication devices can allow the computer device to communicate wirelessly or wiredly with other devices (such as edge computing devices) to exchange data. Although FIG4 shows a computer device with various devices, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0084] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from ROM. When the computer program is executed by a processor, all or part of the steps of the text content analysis method of the present disclosure embodiments are performed.

[0085] For detailed descriptions of this embodiment, please refer to the corresponding descriptions in the foregoing embodiments, which will not be repeated here.

[0086] A computer-readable storage medium according to an embodiment of the present disclosure stores non-transitory computer-readable instructions thereon. When the non-transitory computer-readable instructions are run by a processor, all or part of the steps of the text content analysis method of the foregoing embodiments of the present disclosure are performed.

[0087] The above-mentioned computer-readable storage medium includes, but is not limited to: optical storage media (e.g., CD-ROM and DVD), magneto-optical...Storage media (e.g., MO), magnetic storage media (e.g., magnetic tape or portable hard drive), media with built-in rewritable non-volatile memory (e.g., memory card), and media with built-in ROM (e.g., ROM cartridge).

[0088] Detailed descriptions of this embodiment can be found in the corresponding descriptions of the foregoing embodiments, and will not be repeated here.

[0089] The basic principles of this disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are only for illustrative and facilitative purposes, and are not limitations. The above details do not limit the implementation of this disclosure to the use of the above specific details.

[0090] In this disclosure, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of devices, apparatuses, devices, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as "comprising," "including," "having," etc., are open-ended terms meaning "including but not limited to," and are used interchangeably with them. The terms "or" and "and" as used herein refer to the terms "and / or," and are used interchangeably with them unless the context clearly indicates otherwise. The term "such as" as used herein refers to the phrase "such as but not limited to," and is used interchangeably with it.

[0091] Additionally, as used herein, the "or" used in a list of items beginning with "at least one" indicates a separate list, such that a list of, for example, "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not imply that the described example is preferred or better than other examples.

[0092] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalents of this disclosure.

[0093] Various changes, substitutions, and modifications to the techniques described herein can be made without departing from the techniques taught by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, components, means, methods, and actions described above. Currently existing or later-developed groups of processes, machines, manufactures, events that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized.Page 14 CN 121328519 A Means, methods, or actions. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0094] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0095] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although several exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof. Instruction Manual 11 / 11 Page 15 CN 121328519 A Figure 1 Instruction Manual Figure 1 / 3 Page 16 CN 121328519 A Figure 2 Figure 3 Instruction Manual Figure 2 / 3 Page 17 CN 121328519 A Figure 4 Instruction Manual Figure 3 / 3 Page 18 CN 121328519 A {HARTEND-26011-HKSPT / 02470706v1} Abstract The embodiments of the present disclosure disclose a text content analysis method and system, a computer device, a medium, and a product. The text content analysis method includes: performing content parsing on the text to be analyzed, extracting target information, and determining the text level accordingly; and then, invoking a corresponding number of analysis agents based on the text level; obtaining content quality analysis information, language expressionanalysis information, and structural arrangement analysis information based on each analysis agent; obtaining the similarity between the target information and each analysis agent, and thereby obtaining the confidence level of each analysis agent; and then, combining the three aspects of analysis information and confidence levels of all analysis agents to respectively obtain analysis results for three dimensions: content quality, language expression, and structural arrangement; and obtaining the text content analysis result based on the analysis results of the content quality dimension, the language expression dimension, and the structural arrangement dimension. This method can achieve dynamic, comprehensive, accurate, and rapid analysis based on the text content.

Claims

1. A text content analysis method, characterized in that, include: The text to be analyzed is parsed to extract target information, which includes keywords, technical fields, and text complexity. Determine the text level based on the target information; The corresponding number of analytical agents are invoked based on the text level; Based on each of the aforementioned analytical agents, content quality analysis information, language expression analysis information, and structural arrangement analysis information are obtained; Obtain the similarity between the target information and each of the analytical agents, and obtain the confidence level of each analytical agent based on the similarity. Based on the content quality analysis information, language expression analysis information, structural arrangement analysis information, and confidence level corresponding to all the analytical agents, the content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results are obtained. Based on the analysis results of the content quality dimension, the language expression dimension, and the structure and arrangement dimension, the text content analysis results are obtained.

2. The text content analysis method according to claim 1, characterized in that, The method for obtaining the text complexity includes: Based on the text to be analyzed, obtain the article's word count, number of technical terms, total number of words, total number of sentences, as well as the word count, number of compound sentences, and number of cited references for each sentence; Based on the preset word count range scoring rules, the word count dimension score corresponding to the word count of the article is obtained; The terminology density is obtained based on the number of terminology and the total number of words, and the terminology density dimension score corresponding to the terminology density is obtained according to the preset terminology density interval scoring rules. Identify all sentences that exceed the preset character limit and record them as long sentences; The sentence density is obtained based on the number of complex sentences, the total number of long sentences, and the total number of sentences; According to the preset scoring rules for sentence density intervals, the sentence density dimension score corresponding to the sentence density is obtained; According to the preset scoring rules for the cited literature interval, the literature citation dimension score corresponding to the number of cited literatures is obtained; The text complexity is obtained by weighting and summing the scores for the word count dimension, the terminology density dimension, the sentence structure density dimension, and the citation dimension based on preset weights.

3. The text content analysis method according to claim 2, characterized in that, Determining the text level based on the target information includes: The number and coverage of the keywords determine the text's professional depth score; The text difficulty score is determined based on the technical field. The text's professional depth score, text difficulty score, and text complexity score are weighted and summed according to preset weights to obtain the target comprehensive score. The text level is determined based on the overall target score, and the text level is any one of ordinary, medium, or complex.

4. The text content analysis method according to claim 3, characterized in that, The step of calling the corresponding number of analytical agents based on the text level includes: When the text level is normal, the text is sent to M analytical agents; When the text level is medium, the text is sent to N analytical agents; When the text level is complex, the text is sent to P analytical agents; Where P > N > M ≥ 1.

5. The text content analysis method according to claim 1, characterized in that, The step of obtaining the similarity between the target information and each of the analytical agents, and obtaining the confidence level of each analytical agent based on the similarity, includes: Obtain historical training data for each of the analytical agents; Obtain the cosine similarity between the target information and the historical training data; Based on the cosine similarity and the preset similarity scoring table, the confidence level of the analysis agent corresponding to the similarity is obtained.

6. The text content analysis method according to claim 5, characterized in that, The content quality dimension analysis result is N: ; The result of the language expression dimension analysis is Y: ; The structural arrangement dimension analysis results are as follows: : ; in, For the first Content quality analysis information corresponding to each analytical agent. For the first The confidence level of each analytical agent, where P is the total number of analytical agents. For the first The language expression analysis information corresponding to each of the aforementioned analytical agents. For the first The structural arrangement analysis information corresponding to each analytical agent.

7. A text content analysis system, characterized in that, include: The information extraction module is used to parse the text to be analyzed and extract target information, including keywords, technical fields, and text complexity. A text level determination module is used to determine the text level based on the target information; The agent invocation module is used to invoke a corresponding number of analytical agents according to the text level; and to obtain content quality analysis information, language expression analysis information, and structural arrangement analysis information based on each analytical agent. The confidence acquisition module is used to acquire the similarity between the target information and each of the analysis agents, and to acquire the confidence of each analysis agent based on the similarity. The multi-dimensional analysis module is used to obtain content quality dimension analysis results, language expression dimension analysis results, and structural arrangement dimension analysis results based on the content quality analysis information, language expression analysis information, structural arrangement analysis information, and confidence scores corresponding to all the analysis agents. The content analysis result acquisition module is used to obtain text content analysis results based on the content quality dimension analysis results, the language expression dimension analysis results, and the structure and arrangement dimension analysis results.

8. A computer device, characterized in that, The computer device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the text content analysis method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the text content analysis method according to any one of claims 1-7.

10. A computer program product comprising computer instructions, characterized in that, When executed by a processor, the computer instructions implement the steps of the method according to any one of claims 1-7.

Images