An information technology consulting service method and system based on correlation analysis

Abstract

The present invention discloses an information technology consulting service method and system based on correlation analysis, which relates to the field of information retrieval and consulting technology, including extracting keywords from user consultation requests, identifying user needs in the keywords through a user need model; processing the user needs, performing parameterized retrieval, performing correlation analysis on the retrieval results of the parameterized retrieval, and generating a correlation list based on the results of the correlation analysis; analyzing each entry in the correlation list, outputting a set of answers that meet the user needs; integrating the answer set to form an interactive question-and-answer interface for users to view. The present invention achieves accurate understanding of complex user queries, improves the relevance and accuracy of retrieval results, and at the same time enhances the system's adaptability and knowledge coverage through dynamic weight adjustment and knowledge graph integration.

Description

Technical Field

[0001] The present invention relates to the technical field of information retrieval and consultation, and in particular to an information technology consultation service method and system based on correlation analysis. Background Art

[0002] The field of information technology consulting services has experienced significant technological advancements in recent years, particularly in natural language processing and information retrieval. Early consulting services relied primarily on simple keyword matching and basic information retrieval techniques, such as Boolean search and vector space models. As technology evolved, more complex algorithms were introduced, such as latent semantic analysis (LSA) and probabilistic topic models (such as LDA). These methods have improved the accuracy and relevance of retrieval to a certain extent. In recent years, the application of deep learning technologies, such as recurrent neural networks (RNNs) and transformer models (such as BERT), has further promoted the development of natural language understanding and information retrieval, enabling the system to better understand the semantics and context of user queries.

[0003] However, despite these advances, existing information technology consulting service systems still have some significant limitations. First, most systems perform poorly when processing complex, multimodal user queries and have difficulty integrating text and voice input. Second, existing systems often use static retrieval models, which are difficult to adapt to users' personalized needs and professional terminology in different fields. Third, when building user demand models, most systems fail to fully utilize linguistic features and semantic structure information, resulting in an insufficient understanding of user intent. In addition, existing correlation analysis methods usually only consider limited dimensions, such as TF-IDF or cosine similarity, ignoring important factors such as the timeliness of documents and user interaction history. Finally, in the answer generation stage, many systems still rely on simple extractive methods and cannot provide sufficiently detailed and customized answers. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an information technology consulting service method and system based on correlation analysis to solve the problems that existing information technology consulting service systems have a poor understanding of user needs, lack contextual awareness during information retrieval, and have difficulties in integrating text and voice input.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides an information technology consulting service method based on correlation analysis, which includes extracting keywords in user consultation requests, identifying user needs in the keywords through a user needs model; processing the user needs, performing parameterized retrieval, performing correlation analysis on the retrieval results of the parameterized retrieval, and generating a correlation list based on the results of the correlation analysis; analyzing each entry in the correlation list, and outputting a set of answers that meet the user needs; integrating the answer set to form an interactive question-and-answer interface for user viewing.

[0008] As a preferred solution of the information technology consulting service method based on correlation analysis described in the present invention, the types of the user consulting requests include text form, voice form and text-speech fusion form.

[0009] As a preferred solution of the information technology consulting service method based on correlation analysis described in the present invention, wherein: extracting keywords in user consultation requests includes the following steps: preprocessing the user consultation requests; the preprocessing includes: if the user consultation request is in voice form, converting it into text form; if the user consultation request is in text-speech fusion form, separating it into a text part and a voice part, converting the voice part into text form, adding voice tags, and merging it with the text part; all types of user consultation requests are uniformly converted into a standardized text format, and retaining the voice tags.

[0010] The standardized text is subjected to linguistic preprocessing to obtain a word list; each word in the word list includes a root form and a corresponding part-of-speech tag.

[0011] Calculating the importance of each term in the term list specifically includes the following steps: calculating the standard TF-IDF values of all terms; wherein, for terms with speech tags, performing secondary processing based on the standard TF-IDF values:

[0012] M(t,d)=TF-IDF(t,d)×(1+log(1+F(t)));

[0013] Where M(t, d) represents the fused importance score of the term t with speech tags for document d; TF-IDF(t, d) represents the standard TF-IDF value of the term t for document d; and F(t) is a speech feature synthesis function used to evaluate the importance of the term t in the speech part, which is determined by speech salience, semantic relevance, and contextual importance.

[0014] M(t, d) is used as the importance of the terms with speech tags; for the terms without speech tags, the standard TF-IDF value is used as the importance.

[0015] All terms are sorted in descending order according to the importance, the sorted term list is traversed, and terms whose importance is greater than the screening threshold are selected as keywords; the screening threshold is set according to the frequency of occurrence of all terms.

[0016] As a preferred solution of the information technology consulting service method based on correlation analysis of the present invention, the speech feature comprehensive function is expressed as:

[0017]

[0018] The speech saliency is expressed as:

[0019]

[0020] The semantic relevance is expressed as:

[0021]

[0022] The context importance is expressed as:

[0023]

[0024] Among them, A(t) represents phonetic salience; B(t) represents semantic relevance; C(t) represents contextual importance; D(t) represents the syllable duration ratio of term t; E represents the average syllable duration; G(t) represents the relative volume of the term; H represents the average volume; J(t) represents the word vector similarity; K(t) represents the frequency ranking normalized score; L(t) represents contextual relevance; N(t) represents the position score of term t in the sentence.

[0025] The process of constructing the user demand model includes the following steps: performing entity recognition on the keywords, and marking and classifying the recognized entities to form entity information; analyzing the original text of the user consultation request containing the keywords, and constructing a dependency tree containing the keywords; embedding the entity information into the dependency tree, marking the corresponding entity information at the corresponding nodes of the dependency tree, forming a structured dependency tree containing entity information, and serving as the user demand model.

[0026] As a preferred solution of the information technology consulting service method based on correlation analysis of the present invention, processing the user needs and performing parameterized search include the following steps:

[0027] A multi-level parameterized query tree is constructed based on the user requirements, and query parameters are mapped to nodes at different levels of the multi-level parameterized query tree; each node includes a query parameter type, a value range, and a weight; a parameterized search is performed based on the multi-level parameterized query tree; the parameterized search includes starting from the root node of the multi-level parameterized query tree, accessing each node in a preset traversal order, constructing query conditions based on the query parameter type, value range, and weight of the node, combining them into a complete query statement, and executing the query until a preset search depth is reached or all nodes are covered, and finally merging the search results of all nodes to obtain the search result of the parameterized search.

[0028] As a preferred solution of the information technology consulting service method based on correlation analysis described in the present invention, wherein: correlation analysis is performed on the retrieval results of the parameterized retrieval, and a correlation list is generated based on the results of the correlation analysis, including the following steps: using the BM25 algorithm to perform correlation analysis on the retrieval results of the parameterized retrieval, and outputting a correlation score as the result of the correlation analysis; sorting the retrieval results of the parameterized retrieval in descending order according to the correlation score, and screening out retrieval results with the correlation score higher than the correlation score threshold; deduplicating the filtered retrieval results, and generating a correlation list based on the deduplicated retrieval results.

[0029] As a preferred solution of the information technology consulting service method based on correlation analysis described in the present invention, wherein: each entry in the correlation list is analyzed, and a set of answers that meet the user's needs is output, including the following steps: the document of each entry in the correlation list is divided into separate sentences, each sentence is segmented, and a part-of-speech tag is added to each vocabulary unit; based on the part-of-speech tags, the actions and participants in the sentence are identified, and semantic role annotations are constructed; using the semantic role annotations, the overlap between the keywords contained in the sentence and the keywords in the user demand model is calculated; combining the semantic role annotations and the overlap, the similarity between the dependency structure of each sentence and the structured dependency tree in the user demand model is evaluated; the score of each sentence is calculated, and accumulated to obtain a document score; based on the document score, the documents with the top M scores are selected as answer candidates, where M is a preset positive integer; the sentences with the highest scores are extracted from the answer candidates to form answers, and integrated to form an answer set.

[0030] In the second aspect, the present invention provides an information technology consulting service system based on correlation analysis, including an extraction and identification module for extracting keywords in user consultation requests and identifying user needs in the keywords through a user need model; a processing and generation module for processing the user needs, performing parameterized retrieval, performing correlation analysis on the retrieval results of the parameterized retrieval, and generating a correlation list based on the results of the correlation analysis; an answer generation module for analyzing each entry in the correlation list and outputting a set of answers that meet the user needs; and an interactive question and answer interface module for integrating the answer set to form an interactive question and answer interface for user viewing.

[0031] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the information technology consulting service method based on correlation analysis as described in the first aspect of the present invention.

[0032] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the information technology consulting service method based on correlation analysis as described in the first aspect of the present invention.

[0033] The present invention has the following beneficial effects: By integrating multimodal input processing, deep semantic analysis, parameterized retrieval, and multidimensional relevance calculation, it improves the performance and user experience of information technology consulting services. The present invention achieves precise understanding of complex user queries, improving the relevance and accuracy of search results. Furthermore, through dynamic weight adjustment and knowledge graph integration, it enhances the system's adaptability and knowledge coverage. Furthermore, the present invention's answer generation mechanism combines semantic role labeling and structured dependency analysis to provide more precise and targeted responses, significantly improving the quality and efficiency of consulting services. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 This is an overall flow chart of the information technology consulting service method and system based on correlation analysis of the present invention.

[0036] Figure 2This is a computer device diagram of the information technology consulting service method and system based on correlation analysis in the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0040] Example 1, with reference to Figure 1 , which is the first embodiment of the present invention, provides an information technology consulting service method based on correlation analysis, including:

[0041] In the relevant technologies, first, most systems perform poorly when processing complex, multimodal user queries, especially when integrating text and voice input. Second, existing systems often use static retrieval models, which are difficult to adapt to users' personalized needs and professional terminology in different fields. Third, when building user demand models, most systems fail to fully utilize linguistic features and semantic structure information, resulting in an insufficient understanding of user intent. In addition, existing correlation analysis methods usually only consider limited dimensions, such as TF-IDF or cosine similarity, ignoring important factors such as the timeliness of documents and user interaction history. Finally, in the answer generation stage, many systems still rely on simple extractive methods and cannot provide sufficiently detailed and customized answers.

[0042] This application provides an effective solution to the above-mentioned problems. Next, we will explain in detail how to implement the information technology consulting service based on correlation analysis in combination with multiple embodiments.

[0043] Figure 1 The overall flow chart of an information technology consulting service method and system based on correlation analysis is shown, including:

[0044] S1: Extract keywords from user consultation requests and identify user needs in the keywords through the user needs model;

[0045] S2: Process user needs, perform parameterized search, apply multi-dimensional relevance calculation to the search results of parameterized search, and generate a relevance list;

[0046] S3: Analyze each item in the relevance list and output a set of answers that meet the user's needs;

[0047] S4: Integrate the answer set to form an interactive question-and-answer interface for users to view.

[0048] In this embodiment, each step in S1 to S4 will be described one by one:

[0049] S1: extracting keywords from a user's consultation request, and identifying user needs in the keywords through a user need model.

[0050] Specifically, the types of user consultation requests include text form, voice form and text-speech fusion form. Among them, the text-speech fusion form refers to the combination of text form and voice form, and has a variety of application scenarios, such as: 1. Multimodal input: users use text and voice at the same time in the same interaction (users can start voice input and then switch to text to supplement or correct information). 2. Real-time display of speech to text: the system displays the recognized text in real time when the user is inputting voice; the user directly edits the displayed text to correct errors or add additional information while or after voice input. 3. Application of assistive technology: For some special user groups with hearing impairments or visual impairments, a hybrid input mode in the form of text-speech fusion is needed to improve the accessibility of the system.

[0051] S1.1: Extract keywords from user consultation requests, specifically by using natural language processing technology to capture keywords from collected user consultation requests.

[0052] First, the collected user consultation requests are pre-processed. Specifically, if the user consultation request is in voice form, speech recognition technology (such as Google Speech-to-Text API: Google Speech-

[0053] to-Text API) to convert it into text form; if the user consultation request is in the form of text-speech fusion, multimodal separation technology is used to separate it into text and voice parts, and the voice part is converted into text form using speech recognition technology, and voice tags are added and merged with the text part; all types of user consultation requests are uniformly converted into standardized text format, and voice tags are retained.

[0054] Next, the standardized text is linguistically preprocessed to produce a list of terms. The linguistic preprocessing process involves: 1. Using stemming and lemmatization tools from natural language processing (such as the Porter Stemmer algorithm or lemmatizer in the Natural Language Toolkit (NLTK) library), the words in the text are converted to their root form, removing all deformed, most basic forms; 2. Stop words are removed and part-of-speech tags are applied. Therefore, each term in the list contains both its root form and its corresponding part-of-speech tag (speech tags are not removed during the linguistic preprocessing process).

[0055] Then, the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm is used to calculate the importance of each term in the term list. The specific steps include the following:

[0056] Calculate the standard TF-IDF value of all terms, expressed as:

[0057]

[0058] Where TF-IDF(t,d) represents the standard TF-IDF value of term t for document d; f t,d N represents the number of times the term t appears in document d; d Represents the total number of words in document d; N represents the total number of documents; n t represents the number of documents containing the term t; Represents the frequency of term t in document d. The higher the term frequency, the more important the term is in the document. It represents the inverse document frequency of term t, reflecting the rarity of the term in the entire document collection. The larger the value, the more important the term.

[0059] Among them, for words with speech tags, secondary processing is performed based on the standard TF-IDF value:

[0060] M(t,d)=TF-IDF(t,d)×(1+log(1+F(t)));

[0061]

[0062]

[0063] Among them, M(t, d) represents the fused importance score of term t with speech tags to document d; F(t) is a speech feature synthesis function used to evaluate the importance of term t in the speech part, which is determined by speech salience, semantic relevance and contextual importance; A(t) represents speech salience; B(t) represents semantic relevance; C(t) represents contextual importance; D(t) represents the syllable duration ratio of term t, which measures the ratio of the pronunciation duration of term t in actual speech to its expected duration; E represents the average syllable duration; G(t) represents the relative volume of the term; H represents the average volume; J(t) represents the word vector similarity; K(t) represents the frequency ranking normalized score; L(t) represents the contextual relevance; N(t) represents the position score of term t in the sentence.

[0064] It should be noted that the speech feature synthesis function F(t) consists of a numerator and a denominator. In the numerator: First, the speech salience A(t) reflects the emphasis in the speech input; second, sin(B(t)) introduces periodic changes to simulate the modulation effect of semantic relevance B(t) on speech salience A(t), thereby capturing the interactive effect between speech emphasis and semantic relevance; finally, the context importance C(t) is directly added to the numerator to retain the direct influence of context importance. In the denominator: |A(t)-C(t)| reflects the difference between speech salience and context importance; (1-e -B(t) ) ranges from [0, 1) and increases with the semantic relevance B(t). The denominator makes the value of the speech feature synthesis function F(t) relatively lower when the difference between speech salience and context importance is large and the semantic relevance is high, thereby giving more balanced consideration in the final score.

[0065] Preferably, the speech comprehensive feature function F(t) of the present invention significantly improves the performance and accuracy of the multimodal information retrieval system in practical applications. The comprehensive feature function F(t) combines speech saliency, semantic relevance and contextual importance to effectively capture the emphasis, semantic changes and contextual relationships in speech input, thereby more accurately understanding the user's intention. When processing query requests in the form of text-speech fusion, the comprehensive feature function F(t) can dynamically balance the influence of speech features and text semantics, so that the present invention can maintain a high degree of adaptability when facing different user expression habits and query complexity. This improvement makes the present invention have obvious advantages over the existing technology in application scenarios that require precise understanding and rapid response, such as intelligent customer service, professional consulting and cross-language information retrieval. It not only improves the relevance and accuracy of the retrieval results, but also better handles the complex problems of ambiguous queries and context dependence, thereby significantly improving the user experience and the effectiveness of the present invention.

[0066] Table 1 Performance comparison of multimodal information retrieval systems

[0067] index The present invention Traditional TF-IDF method BERT-based methods Query comprehension accuracy (%) 92.5 85.3 87.1 Average response time (ms) 78 95 89 Relevance score (0-1) 0.876 0.792 0.815 User satisfaction (1-5) 4.62 4.13 4.25 Multimodal fusion efficiency (%) 89.7 76.4 79.2 Success rate of ambiguous query processing (%) 86.3 74.8 77.5 Contextual relevance improvement (%) 23.6 12.7 15.4 Computational complexity (relative value) 1.15 1.00 1.08

[0068] As can be seen from Table 1, the speech comprehensive feature function F(t) proposed in the present invention significantly outperforms the existing traditional TF-IDF method and BERT-based method in multiple key performance indicators. In terms of query understanding accuracy, F(t) reached 92.5%, which is 7.2 percentage points higher than the traditional TF-IDF method and 5.4 percentage points higher than the BERT-based method, reflecting its advantage in understanding complex query intent. Although the computational complexity of F(t) is slightly higher than that of the traditional method (1.15 vs 1.00), its average response time (78ms) is lower than that of the TF-IDF method (95ms) and the BERT method (89ms), indicating that F(t)'s more accurate query understanding reduces subsequent processing steps. In terms of multimodal fusion efficiency and ambiguous query processing, F(t) achieved high performance of 89.7% and 86.3% respectively, far exceeding traditional and BERT methods, highlighting its excellent ability in processing complex multimodal inputs. Furthermore, F(t)'s performance in improving contextual relevance (23.6%) is almost double that of traditional methods (12.7%) and significantly outperforms the BERT method (15.4%), demonstrating its effective utilization of contextual information. These technical advantages ultimately translate into higher user satisfaction (4.62 vs 4.13 / 4.25), fully validating the value of this invention in practical applications. In summary, these data strongly support the significant contribution of the speech comprehensive feature function F(t) to improving the performance of multimodal information retrieval systems.

[0069] Furthermore, the average syllable duration E is expressed as:

[0070]

[0071] The average volume H is expressed as:

[0072]

[0073] The syllable duration ratio D(t) of term t is expressed as:

[0074]

[0075] This ratio reflects whether the pronunciation duration of word t in speech is different from the expected duration. If this ratio is greater than 1, it means that the pronunciation duration of the word is longer than expected; if it is less than 1, it means that the pronunciation duration is shorter than expected, which may indicate that the speaker emphasizes or downplays certain words.

[0076] The relative volume of a term G(t) is expressed as:

[0077]

[0078] The word vector similarity J(t) is expressed as:

[0079]

[0080] in, is the word vector of term t; It is the word vector of the core concept of the query.

[0081] The frequency ranking normalized score K(t) is expressed as:

[0082]

[0083] The context relevance L(t) is expressed as:

[0084]

[0085] Among them, PMI(t, i) is the pointwise mutual information (Pointwise Mutua lInformation); context(t) is the context window of term t.

[0086] The position score N(t) of term t in the sentence is expressed as:

[0087]

[0088] Here, pos(t) is the position of term t in the sentence (counting starts from 1); len(s) is the length of the sentence (number of terms).

[0089] M(t,d) is used as the importance of terms with speech tags; for terms without speech tags, the standard TF-IDF value is used as the importance of the terms.

[0090] Finally, all terms are sorted in descending order according to the importance, the sorted term list is traversed, and terms with an importance greater than a screening threshold are selected as keywords.

[0091] The screening threshold is set according to the frequency of occurrence of all terms.

[0092] It should be noted that this embodiment uses the Google Speech-to-Text API to convert voice-based consultation requests into text, achieving seamless speech-to-text conversion. This allows the system to handle diverse input formats, improving its applicability and user-friendliness. Using the Porter Stemmer or WordNetLemmatizer in the NLTK library for stemming and lemmatization extracts the basic morphology of words in the text, helping to reduce vocabulary diversity and simplifying subsequent processing steps.

[0093] Preferably, by supporting multiple input forms (text, voice and text-speech fusion forms), the present invention can better adapt to modern interactive environments, such as multimodal input scenarios, real-time speech-to-text applications, and assistive technology applications for special user groups. By using multimodal separation technology and speech recognition technology, the present invention can accurately process these complex input forms and uniformly convert them into standardized text formats. This unified processing not only simplifies the subsequent analysis steps, but also ensures the consistency and comparability of keyword extraction under different input forms. In addition, in the linguistic preprocessing stage, the present invention adopts stemming and morphological restoration technology, which helps to reduce the interference caused by word form changes and improve the accuracy and generalization ability of keyword recognition.

[0094] The present invention introduces an innovative secondary processing mechanism when using the TF-IDF algorithm to calculate the importance of terms, mainly for terms with speech tags. This secondary processing mechanism significantly improves the accuracy and relevance of keyword extraction by fusing speech features and semantic information. The present invention introduces three indicators: speech salience, semantic relevance, and contextual importance, which comprehensively consider the prominence of the term in the speech, the semantic similarity with the core concept of the query, and the importance in the context. This multi-dimensional evaluation method enables the present invention to more accurately capture the key points emphasized by the user in the speech input, while considering the semantic importance and contextual relevance of the term. In order to accurately understand the user's intention, the present invention identifies the words that the user particularly emphasizes or weakens in the speech by considering the syllable duration ratio and relative volume of the term. At the same time, by calculating the word vector similarity and frequency ranking normalized score, the present invention can better identify keywords related to the core concept of the user's query. In addition, the introduction of contextual relevance and sentence position score enables the present invention to consider the importance of the term in the entire sentence structure, thereby extracting more context-related keywords. This method, which comprehensively considers speech features, semantic associations, and contextual information, not only improves the accuracy of keyword extraction, but also better adapts to the expression habits of different users and professional terminology in specific fields, thereby providing more accurate and relevant information retrieval and analysis services in various complex consulting scenarios, such as customer service, professional consulting, medical diagnosis, etc.

[0095] S1.2: Identify user needs in keywords through user need models. Specifically, this involves using named entity recognition technology and dependency parsing tools to build a user need model, and then identifying user needs in keywords through the user need model.

[0096] Specifically, the process of building a user demand model includes the following steps:

[0097] First, use named entity recognition technology (such as the Spacy (Natural Language Processing Library) model or the Stanford NER (Stanford Named Entity Recognizer) model) to identify keywords, and then label and classify the identified entities to form entity information. Assuming that the keywords are artificial, intelligent, development, and process, the NER model may recognize artificial intelligence as a composite entity.

[0098] Secondly, use dependency syntax analysis tools (such as Spacy's dependency syntax analysis module or StanfordParser) to analyze the original text of the user consultation request containing keywords, identify the dependency relationship between words (for example, the sentence analyzed is "I want to know the relationship between words in the development history of artificial intelligence"), and construct a dependency relationship tree containing keywords based on the dependency syntax analysis results (for example, I am the subject, want is the predicate verb, know is the object complement, and the development history of artificial intelligence is the object).

[0099] Finally, the entity information is embedded in the dependency tree, and the corresponding entity information is marked at the corresponding nodes of the dependency tree to form a structured dependency tree containing entity information, which is used as the user demand model.

[0100] It should be noted that the use of named entity recognition technology to perform entity recognition on keywords realizes the identification and classification of key entities in user queries, which helps to build a more accurate user demand model.

[0101] By using dependency syntax analysis tools to build a dependency tree, we can gain a deeper understanding of the relationships between words in the user's information request text, helping to more accurately grasp the user's query intent.

[0102] By embedding entity information into the dependency tree and creating a structured user demand model, we can fully reflect the user's query intention and provide precise guidance for subsequent information retrieval.

[0103] S2: Process user needs, perform parameterized search, perform correlation analysis on the search results of the parameterized search, and generate a correlation list based on the results of the correlation analysis.

[0104] S2.1: Build a multi-level parameterized query tree based on user needs and map query parameters to nodes at different levels of the tree. Each node contains the query parameter type, value range, and weight.

[0105] S2.2: Perform parameterized retrieval based on a multi-level parameterized query tree.

[0106] Specifically, parameterized retrieval includes starting from the root node of the multi-level parameterized query tree, visiting each node in a preset traversal order, building query conditions based on the node's query parameter type, value range and weight, combining them into a complete query statement and executing it until the preset retrieval depth is reached or all nodes are covered, and finally merging the retrieval results of all nodes to obtain the retrieval results of the parameterized retrieval.

[0107] S2.3: Use the BM25 algorithm to perform correlation analysis on the retrieval results of the parameterized retrieval and output the correlation score as the result of the correlation analysis.

[0108] S2.4: Sort the search results of the parameterized search in descending order according to the relevance score, set a relevance score threshold, and filter out the search results with relevance scores higher than the relevance score threshold; deduplicate the filtered search results, delete the search results with content duplication exceeding a preset ratio, and generate a relevance list based on the deduplicated search results.

[0109] S3: Analyze each entry in the relevance list and output a set of answers that meet the user's needs.

[0110] S3.1: Use a natural language processing tool (such as NLTK or Spacy) to split the document of each item in the relevance list into separate sentences. Perform tokenization on each sentence, that is, break the sentence into individual lexical units. Add a part-of-speech tag to each lexical unit to determine its grammatical function in the sentence (noun, verb, adjective, etc.).

[0111] It should be noted that the part-of-speech tags in S3.1 are not the same as the part-of-speech tagging of terms in S1. The former part-of-speech tagging is performed on the retrieved documents in preparation for subsequent semantic analysis and answer generation. The latter part-of-speech tagging belongs to the step: linguistic preprocessing of the standardized text to obtain a list of terms, which is performed on the original user input in preparation for subsequent keyword extraction and user demand model construction. The processing objects are also different: the former processes user input, and the latter processes search results; and the processing granularity is also different: the former processes to the term level, and the latter processes to the sentence level first, and then to the word level.

[0112] S3.2: Apply semantic analysis technology to identify actions (predicates) and participants (arguments) in sentences. For example, in the sentence "I want to know the development history of artificial intelligence", "want" is an action, "I" is the executor of the action, "know" is another action, and "the development history of artificial intelligence" is the object of "knowing"; construct semantic role annotations.

[0113] S3.3: Using semantic role annotation, calculate the overlap between the keywords contained in the sentence and the keywords in the user demand model, expressed as,

[0114]

[0115] Among them, J(A,B) represents the overlap between the keywords contained in the sentence and the keywords in the user demand model, A represents the keyword set in the sentence, and B represents the keyword set in the user demand model.

[0116] S3.4: Combine semantic role labeling and overlap to evaluate the similarity between the dependency structure of each sentence and the structured dependency tree in the user requirement model.

[0117] S3.5: Based on the overlap obtained in S3.3 and the similarity obtained in S3.4, the score of each sentence is calculated and accumulated to obtain the document score.

[0118] S3.6: Based on the document scores, select the top M documents as answer candidates, where M is a preset positive integer.

[0119] S3.7: Extract the sentences with the highest scores from the answer candidates, form the answers, and integrate them to form an answer set.

[0120] S4: Integrate the answer set to form an interactive question-and-answer interface for users to view.

[0121] Design a user-friendly front-end interface that displays a collection of answers and allows users to click through them. The interface should be interactive, allowing users to select an answer to view further details or ask new related questions.

[0122] Implement a feedback mechanism where users can rate the quality of answers. This feedback can be used to improve future answer generation algorithms. The interface can also provide a search box where users can directly enter new queries, and the system will re-execute all steps to generate a new set of answers.

[0123] Ultimately, by integrating all filtered answers, users can easily and quickly find the information they need and further explore related information as needed.

[0124] It should be noted that designing a user-friendly front-end interface and implementing a feedback mechanism enables effective interaction between users and the system, improves user experience, and provides a basis for continuous improvement of the system.

[0125] All the screened answers are integrated to form an interactive question-and-answer interface, allowing users to find the information they need easily and quickly, and further explore related information as needed, ultimately realizing an efficient, accurate, and user-friendly question-and-answer system.

[0126] Through these steps, the invention realizes an intelligent question-answering system that can accurately understand user needs, efficiently retrieve relevant information, and provide high-quality answers, greatly improving user experience and information retrieval efficiency.

[0127] In summary, the present invention improves the performance and user experience of information technology consulting services by integrating multimodal input processing, deep semantic analysis, parameterized retrieval, and multidimensional relevance calculation. This invention achieves precise understanding of complex user queries, improving the relevance and accuracy of search results. It also enhances the system's adaptability and knowledge coverage through dynamic weight adjustment and knowledge graph integration. Furthermore, the present invention's answer generation mechanism combines semantic role labeling with structured dependency analysis, enabling more precise and targeted responses, significantly improving the quality and efficiency of consulting services.

[0128] Example 2, reference Figure 1 , which is a second embodiment of the present invention, provides an information technology consulting service system based on correlation analysis, including: a keyword capturing module responsible for collecting consulting requests raised by users and capturing keywords in the consulting requests using natural language processing technology;

[0129] The user demand identification module is responsible for building a user demand model based on keywords using named entity recognition technology and dependency syntax analysis tools to identify user needs;

[0130] The context-aware retrieval module is responsible for activating the context-aware mechanism based on the identified user needs, retrieving background information related to the user needs, and forming a relevance list;

[0131] The answer generation module is responsible for further analyzing each item in the relevance list using advanced natural language processing algorithms and outputting a set of answers that meet the user's needs;

[0132] The interactive question-and-answer interface module is responsible for integrating all screened answer sets to form an interactive question-and-answer interface for users to view.

[0133] Example 3, reference Figure 2, which is the third embodiment of the present invention, differs from the previous embodiment in that: if the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0134] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0135] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0136] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0137] Example 4 is the fourth example of the present invention. In order to further verify the technical solution of the present invention, experimental simulation data of an information technology consulting service method based on correlation analysis is provided.

[0138] The experimental environment was a high-performance workstation equipped with an Intel Core i9-11900K processor, 128GB of RAM, and an NVIDIA RTX 3090 graphics card. The experimental dataset consisted of 100,000 diverse user queries, covering text, speech, and text-speech fusion, along with 1,000,000 corresponding documents across multiple technical fields. To ensure comprehensiveness and fairness, three existing technologies were selected for comparison: a traditional TF-IDF retrieval method, a BERT-based semantic retrieval method, and a commercial intelligent question answering system.

[0139] The experimental process strictly followed the following steps: First, all methods were parameterized to ensure they performed optimally. Then, each method was tested using the same dataset, focusing on the performance of key aspects such as query understanding, parameterized retrieval, relevance analysis, and answer generation. In the query understanding phase, the present invention first converted multimodal input into a standardized text format and then extracted keywords using an improved TF-IDF algorithm and a speech feature synthesis function. Next, a user need model was constructed through named entity recognition and dependency parsing. In the parameterized retrieval phase, a multi-level parameterized query tree was constructed based on the user need model, and a depth-first search was performed to obtain preliminary search results. In the relevance analysis phase, an optimized BM25 algorithm was used, combined with dynamic weight adjustment and knowledge graph integration, to accurately rank the search results. Finally, in the answer generation phase, semantic role labeling and structured dependency analysis were used to extract and combine the most relevant information fragments from highly relevant documents to form the final answer. Throughout the process, the system continuously recorded various performance indicators, including processing time, accuracy, and relevance score. To evaluate the system's performance under varying loads, experiments were conducted under low load (10,000 queries / hour), medium load (50,000 queries / hour), and high load (100,000 queries / hour). Under each load condition, the experiment was repeated 50 times, and the average result was taken as the final result to eliminate the influence of random factors and ensure the reliability and representativeness of the data.

[0140] Table 2: Query processing performance comparison

[0141]

[0142] As shown in Table 2, the present invention has achieved an excellent performance of 98.7% in the success rate of multimodal input processing, far exceeding other methods. This fully demonstrates the powerful ability of the present invention in processing complex and diverse user input. It is worth noting that the present invention only takes 38ms to build the user demand model, which is much faster than other methods, while maintaining a high keyword extraction accuracy (94.6%) and entity recognition accuracy (93.8%). Table 2 shows that the present invention can not only quickly process user input, but also accurately understand user intent, laying a solid foundation for subsequent retrieval and answer generation.

[0143] Table 3 Comparison of retrieval and relevance analysis performance

[0144]

[0145]

[0146] As shown in Table 3, the construction time of the parameterized query tree of the present invention is only 41ms, which is 41.4% faster than the commercial intelligent question answering system, while the traditional TF-IDF method and the BERT-based method do not have this advanced feature. The retrieval accuracy (P@10) reached 0.942, which is 2.4 percentage points higher than the second place. At the same time, the average retrieval time is only 73ms, which is the fastest among all methods. The present invention performs excellently in both dynamic weight adjustment effect (23.6%) and knowledge graph integration efficiency (96.2%). The combination of these two technologies greatly improves the system's processing capabilities for complex queries and the relevance of the results. The optimized BM25 algorithm achieves a relevance score of 0.924, which is significantly higher than other methods. These data fully demonstrate the outstanding contribution of the present invention in improving retrieval efficiency, accuracy and relevance.

[0147] Table 4 Comparison of answer generation and system performance

[0148]

[0149] As shown in Table 4, the present invention has outstanding performance in answer generation and overall system performance. The answer generation accuracy reached 94.3%, and the answer relevance score was as high as 0.931. Both indicators are significantly ahead of other methods. In terms of semantic role labeling accuracy, the present invention reached 93.1%, providing key support for generating more accurate answers that better meet user needs. The user satisfaction score was as high as 4.82 points (out of 5 points), which fully reflects the superiority of the present invention in practical applications. From the perspective of overall system performance, the total system response time of the present invention is only 205ms, which is 28.6% faster than the traditional method. Under high load conditions, the throughput of the present invention reached 486 queries / second, which is 10% higher than the second place, while maintaining a high resource utilization rate of 75.3%. These data show that the present invention not only improves the response speed and processing capability of the system, but also optimizes the efficiency of computing resource utilization.

[0150] In summary, the present invention demonstrates significant performance advantages in various aspects, including query understanding, parameterized retrieval, relevance analysis, and answer generation, primarily in the following areas: (1) efficient processing of multimodal input; (2) rapid and accurate construction of user demand models; (3) rapid construction and precise retrieval of parameterized query trees; (4) efficient relevance analysis combining dynamic weight adjustment and knowledge graphs; (5) precise answer generation based on semantic role annotation; and (6) excellent system load handling capabilities. These advantages not only overcome the shortcomings of existing technologies in processing complex queries and providing precise answers, but also significantly enhance the overall quality and efficiency of information technology consulting services. The experimental data in Tables 2 to 4 strongly demonstrate that the present invention can provide users with a faster, more accurate, and more satisfying consulting service experience, and has significant value and broad prospects in practical applications.

[0151] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An information technology consulting service method based on correlation analysis, characterized in that: include: Extract keywords from user consultation requests and identify user needs in the keywords through a user needs model; Processing the user demand, executing parameterized search, performing correlation analysis on the search results of the parameterized search, and generating a correlation list based on the results of the correlation analysis; Analyze each entry in the relevance list and output a set of answers that meet the user's needs; Integrate the answer set to form an interactive question-and-answer interface for users to view; Extracting keywords from user consultation requests includes the following steps: Preprocessing the user consultation request; the preprocessing includes: If the user consultation request is in voice form, it is converted into text form; if the user consultation request is in text-speech fusion form, it is separated into a text part and a voice part, the voice part is converted into text form, and voice tags are added, and then merged with the text part; all types of user consultation requests are uniformly converted into a standardized text format, and the voice tags are retained; Performing linguistic preprocessing on the standardized text to obtain a word list; each word in the word list includes a root form and a corresponding part-of-speech tag; Calculating the importance of each term in the term list specifically includes the following steps: Calculate the standard TF-IDF values for all terms. For terms with speech tags, perform secondary processing based on the standard TF-IDF values: M(t,d)=TF-IDF(t,d)×(1+log(1+F(t))); Where M(t, d) represents the fused importance score of the term t with the speech tag for document d; TF-IDF(t, d) represents the standard TF-IDF value of the term t for document d; F(t) is a speech feature synthesis function used to evaluate the importance of the term t in the speech part, which is determined by the speech salience, semantic relevance, and contextual importance. Let M(t, d) be the importance of the word with the phonetic tag; For terms without speech tags, the standard TF-IDF value is used as the importance; Sorting all terms in descending order according to the importance, traversing the sorted term list, and selecting terms with an importance greater than a screening threshold as keywords; the screening threshold is set according to the frequency of occurrence of all terms; The speech feature synthesis function is expressed as: Among them, A(t) represents the speech saliency; B(t) represents the semantic relevance; C(t) represents the context importance; The speech saliency is expressed as: The semantic relevance is expressed as: The context importance is expressed as: D(t) represents the syllable duration ratio of term t; E represents the average syllable duration; G(t) represents the relative volume of the term; H represents the average volume; J(t) represents the word vector similarity; K(t) represents the frequency ranking normalized score; L(t) represents the context relevance; N(t) represents the position score of term t in the sentence; The position score N(t) of term t in the sentence is expressed as: Here, pos(t) is the position of term t in the sentence; len(s) is the length of the sentence.

2. The information technology consulting service method based on correlation analysis according to claim 1, characterized in that: The types of the user consultation request include text form, voice form and text-speech fusion form.

3. The information technology consulting service method based on correlation analysis according to claim 2, characterized in that: The process of constructing the user demand model includes the following steps: Performing entity recognition on the keywords, and marking and classifying the recognized entities to form entity information; Analyzing the original text of the user consultation request containing the keyword and constructing a dependency tree containing the keyword; The entity information is embedded in the dependency tree, and corresponding entity information is marked at corresponding nodes of the dependency tree to form a structured dependency tree containing entity information, which serves as a user demand model.

4. The information technology consulting service method based on correlation analysis according to claim 3, characterized in that: Processing the user requirements and performing parameterized search includes the following steps: Constructing a multi-level parameterized query tree based on the user's needs, and mapping query parameters to nodes at different levels of the multi-level parameterized query tree; wherein each node includes a query parameter type, a value range, and a weight; Parameterized search is performed based on the multi-level parameterized query tree; the parameterized search includes starting from the root node of the multi-level parameterized query tree, visiting each node in a preset traversal order, building query conditions according to the query parameter type, value range and weight of the node, combining them into a complete query statement and executing it until a preset search depth is reached or all nodes are covered, and finally merging the search results of all nodes to obtain the search results of the parameterized search.

5. The information technology consulting service method based on correlation analysis according to claim 4, characterized in that: Performing a correlation analysis on the retrieval results of the parameterized retrieval and generating a correlation list based on the results of the correlation analysis includes the following steps: Performing a correlation analysis on the retrieval results of the parameterized retrieval using the BM25 algorithm, and outputting a correlation score as a result of the correlation analysis; sorting the retrieval results of the parameterized search in descending order according to the relevance score, and screening out the retrieval results whose relevance score is higher than a relevance score threshold; The filtered search results are deduplicated, and a relevance list is generated based on the deduplicated search results.

6. The information technology consulting service method based on correlation analysis according to claim 5, characterized in that: Analyzing each entry in the relevance list and outputting a set of answers that meet the user's needs includes the following steps: Splitting the document of each entry in the relevance list into separate sentences, performing word segmentation on each sentence, and adding a part-of-speech tag to each vocabulary unit; Based on the part-of-speech tags, identifying actions and participants in the sentence and constructing semantic role annotations; Calculating the degree of overlap between keywords in the sentence and keywords in the user demand model using the semantic role labeling; In combination with the semantic role labeling and the overlap, evaluating the similarity between the dependency structure of each sentence and the structured dependency tree in the user demand model; Calculate the score of each sentence and add them up to get the document score; Based on the document scores, select the top M documents as answer candidates, where M is a preset positive integer; The sentences with the highest scores are extracted from the answer candidates to form answers, and the answers are integrated to form an answer set.

7. An information technology consulting service system based on correlation analysis, based on the information technology consulting service method based on correlation analysis according to any one of claims 1 to 6, characterized in that: include: An extraction and identification module is used to extract keywords from user consultation requests and identify user needs in the keywords through a user need model; A processing and generating module, configured to process the user requirements, perform parameterized search, perform correlation analysis on the search results of the parameterized search, and generate a correlation list based on the results of the correlation analysis; an answer generation module, configured to analyze each entry in the relevance list and output a set of answers that meet the user's needs; An interactive question-and-answer interface module, configured to integrate the answer set to form an interactive question-and-answer interface for users to view; The step of extracting keywords from the user's consultation request includes: Preprocessing the user consultation request; the preprocessing includes: If the user consultation request is in voice form, it is converted into text form; if the user consultation request is in text-speech fusion form, it is separated into a text part and a voice part, the voice part is converted into text form, and voice tags are added, and then merged with the text part; all types of user consultation requests are uniformly converted into a standardized text format, and the voice tags are retained; Performing linguistic preprocessing on the standardized text to obtain a word list; each word in the word list includes a root form and a corresponding part-of-speech tag; Calculating the importance of each term in the term list specifically includes the following steps: Calculate the standard TF-IDF values for all terms. For terms with speech tags, perform secondary processing based on the standard TF-IDF values: M(t,d)=TF-IDF(t,d)×(1+log(1+F(t))); Where M(t, d) represents the fused importance score of the term t with the speech tag for document d; TF-IDF(t, d) represents the standard TF-IDF value of the term t for document d; F(t) is a speech feature synthesis function used to evaluate the importance of the term t in the speech part, which is determined by the speech salience, semantic relevance, and contextual importance. Let M(t, d) be the importance of the word with the phonetic tag; For terms without speech tags, the standard TF-IDF value is used as the importance; Sorting all terms in descending order according to the importance, traversing the sorted term list, and selecting terms with an importance greater than a screening threshold as keywords; the screening threshold is set according to the frequency of occurrence of all terms; The speech feature synthesis function is expressed as: Among them, A(t) represents the speech saliency; B(t) represents the semantic relevance; C(t) represents the context importance; The speech saliency is expressed as: The semantic relevance is expressed as: The context importance is expressed as: D(t) represents the syllable duration ratio of term t; E represents the average syllable duration; G(t) represents the relative volume of the term; H represents the average volume; J(t) represents the word vector similarity; K(t) represents the frequency ranking normalized score; L(t) represents the context relevance; N(t) represents the position score of term t in the sentence; The position score N(t) of term t in the sentence is expressed as: Here, pos(t) is the position of term t in the sentence; len(s) is the length of the sentence.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the information technology consulting service method based on correlation analysis according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the information technology consulting service method based on correlation analysis according to any one of claims 1 to 6 are implemented.

Images