An intelligent voice interaction system and electronic student ID card

Abstract

The present invention relates to the field of intelligent voice interaction technology, specifically to an intelligent voice interaction system and an electronic student ID card, wherein the system includes a voice input processing module, a semantic decomposition module, a task allocation module, a logic execution module, a dynamic response module, and a voice interaction adjustment module. In the present invention, by analyzing the frequency domain and time domain features of the voice signal, the voice details are accurately captured, the recognition accuracy is improved, the semantic content is parsed and reorganized word by word, the accurate extraction and task description of complex semantics are supported, the resource consumption and dependency relationship analysis optimize the task sequence, the system efficiency and adaptability are improved, the task execution is combined with data retrieval and content classification, and the key tasks and related tasks are coordinated. Dynamic feedback marks unfinished tasks and assembles supplementary information to enhance the dialogue coherence and natural response. The voice interaction adjustment module analyzes unfinished instructions and repeated calls to improve the adaptability to demand changes and service efficiency.

Description

Technical Field

[0001] The present invention relates to the field of intelligent voice interaction technology, and in particular to an intelligent voice interaction system and an electronic student card. Background Art

[0002] The field of intelligent voice interaction technology involves the use of speech recognition, natural language processing (NLP), dialogue management and speech synthesis technology to achieve interaction between people and computer systems. The core of this technology is to allow users to communicate in natural language, and the system can parse the intention and respond, including extracting key information from user voice input, processing context and continuity of dialogue, and generating natural and accurate voice responses. Intelligent voice interaction technology plays a key role in improving user experience and enhancing the accessibility of human-computer interfaces, and is widely used in many fields such as smart assistants, in-vehicle systems, smart home control and customer service.

[0003] Among them, the multi-round dialogue intelligent voice interaction system specifically refers to an intelligent system that can manage and maintain multiple rounds of dialogue with users. Such systems can not only recognize and respond to one-time commands, but also maintain topic coherence based on the dialogue history, handle complex interactions, and adapt to changes in user needs, including in the application scenarios of electronic student cards. This system can verify identity, provide course information, manage courses and exam arrangements, etc. through voice interaction. The use of electronic student cards enables students to access personal academics through simple voice commands, greatly improving the efficiency of educational services and the convenience of students.

[0004] The existing technology does not adequately capture the detailed features of speech signals during speech recognition, resulting in inaccurate recognition of content in non-standard speech or background noise. In semantic analysis, it is difficult to accurately separate semantic units and limiting conditions, resulting in an incomplete understanding of complex commands and insufficient analysis of the logical dependencies and time limits of tasks. In terms of task allocation, there is a lack of accurate assessment of task priorities and detailed analysis of dependency orders, which can easily lead to disordered execution order or unreasonable resource allocation. In the dynamic feedback process, the existing technology has limited ability to integrate contextual information, resulting in feedback content that is out of touch with user intent, affecting the coherence of multiple rounds of interaction. The handling of repeated calls and unfinished tasks in multiple rounds of dialogues is not intelligent enough, resulting in low interaction efficiency and affected user experience. In actual applications, it will cause response delays, task execution errors, and reduced user satisfaction, restricting the wide adaptability and precise service capabilities of intelligent voice interaction systems. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent voice interaction system and an electronic student card.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an intelligent voice interaction system comprises:

[0007] The speech input processing module analyzes the frequency domain and time domain features of the speech signal, segments the audio frames, extracts the amplitude and frequency distribution, identifies the morpheme sequence, integrates the time relationship, and generates the speech text sequence;

[0008] The semantic decomposition module analyzes the part-of-speech relationship of the speech text sequence word by word, separates verbs and target objects, extracts time and range conditions, associates semantic logic, and generates a task semantic description set;

[0009] The task allocation module parses the key tasks and secondary tasks in the task semantic description set, analyzes resources and dependency order, prioritizes and groups them, allocates them, decomposes the chain, and generates a task scheduling list;

[0010] The logic execution module loads the task attributes in the task scheduling list, calls the electronic student card to retrieve courses, parses dependencies and classifies and integrates them, executes query tasks, and generates a task execution result set;

[0011] The dynamic response module analyzes the completed query content based on the task execution result set, marks the unfinished tasks, supplements the context into feedback text, converts the voice signal output, and obtains the user feedback audio;

[0012] The voice interaction adjustment module extracts the conversation content and task execution records based on the user feedback audio, analyzes the unfinished instructions, adjusts the task chain and allocates the process, and generates a voice interaction task allocation data table.

[0013] As a further solution of the present invention, the speech text sequence includes amplitude characteristics, frequency distribution characteristics, morpheme sequences, and time relationships; the task semantic description set includes time limitation conditions, scope limitation conditions, logical relationships, and key semantic objects; the task scheduling list includes key tasks, secondary tasks, task priorities, task dependency orders, and resource consumption assessments; the task execution result set includes query operation results, task classification data, and associated condition integration results; the feedback text includes context information, natural language feedback content, and unfinished task marks; the user feedback audio includes query content, unfinished instructions, and new instruction content; and the voice interaction task allocation data table includes unfinished instructions, repeated call records, task chain adjustment data, and call process allocation information.

[0014] As a further solution of the present invention, the speech input processing module includes:

[0015] The signal analysis submodule analyzes the frequency domain and time domain characteristics of the speech signal, performs quantitative analysis on the energy distribution of the signal, performs periodicity detection and amplitude analysis on the waveform, and adjusts the detailed parameters of the frequency domain analysis to obtain a description of the signal characteristics;

[0016] The frame segmentation submodule uses the signal characteristic description to perform frame segmentation of the audio signal, adjust the time window and interval parameters of the segmentation, optimize the coherence and resolution of the data within the frame, extract the amplitude, frequency and energy of each frame, and obtain the frame characteristic data set through the analysis of the characteristic data within the frame;

[0017] The morpheme integration submodule uses the frame characteristic data set to perform morpheme analysis and integration of continuous frames, strengthen the logical and structural relationship between morphemes through time series analysis, optimize the coherence of morphemes, and generate a speech text sequence.

[0018] As a further solution of the present invention, the semantic decomposition module includes:

[0019] The part-of-speech analysis submodule performs part-of-speech tagging based on the speech text sequence, including recognition of verbs and nouns, uses corpus data for comparative analysis to verify the part-of-speech of each word, adjusts the analysis accuracy and matches the text complexity, and obtains part-of-speech relationship data;

[0020] The syntactic reorganization submodule uses the part-of-speech relationship data to adjust the relationship between the verb and the target object according to syntactic rules, optimize the sentence structure, analyze key syntactic elements and reorganize sentence components to obtain syntactic structure data;

[0021] The logical relationship submodule is based on the syntactic structure data and adopts the conditional semantic nesting analysis method to extract the time and scope limiting conditions in the sentence, associate the conditions with the key semantic objects of the sentence, use the logical analysis method to integrate the key semantic elements, and generate a task semantic description set.

[0022] As a further solution of the present invention, the formula using the conditional semantic nested analysis method is as follows:

[0023] ;

[0024] in, Represents the set value of the task semantic description, Represents the normalized value of the time qualification in the statement, represents the semantic density of the scope-qualifying conditions in the statement, Represents the correlation matching degree of key semantic objects in the sentence, Represents the sum of the weights of key semantic elements in the logical analysis process. represents the correction coefficient of the level in the syntactic structure data, represents the distribution complexity index of conditions and key semantic objects in the sentence, , is the adjustment coefficient, , is the normalization coefficient.

[0025] As a further solution of the present invention, the task allocation module includes:

[0026] The task analysis submodule identifies and classifies critical and non-critical tasks based on the task semantic description set, evaluates the resource and time consumption of each task, optimizes the accuracy of resource allocation and time allocation, adjusts the evaluation parameters to match the urgency of differentiated tasks, and obtains task resource consumption data;

[0027] The dependency sorting submodule uses the task resource consumption data to analyze the dependencies and execution priorities between tasks, optimizes the task execution order by adjusting the priority sorting parameters, and generates a task dependency sequence;

[0028] The task scheduling submodule formulates the task execution grouping and order according to the task dependency sequence, plans the scheduling of each task, adjusts the execution grouping parameters and scheduling strategy and matches the task requirements, and generates a task scheduling list.

[0029] As a further solution of the present invention, the logic execution module includes:

[0030] The task attribute loading submodule identifies the attributes of each task based on the task scheduling list, analyzes and loads the task attributes, refines the loading process using real-time adjustment technology, adjusts the loading rate and optimizes the task matching logic, and generates a task attribute data set;

[0031] The course information retrieval submodule uses the task attribute data set to call the electronic student ID data to retrieve the target course information, including adjusting and optimizing the retrieval parameters, extracting key course dependency information, and obtaining course dependency data;

[0032] The dependency parsing submodule integrates key tasks and associated conditional tasks through the course dependency data, adjusts query parameters, and organizes and executes them in sequence to generate a task execution result set.

[0033] As a further solution of the present invention, the dynamic response module includes:

[0034] The query result analysis submodule performs query result analysis based on the task execution result set, distinguishes completed and uncompleted query tasks by adjusting analysis parameters, optimizes data screening logic, and obtains voice query analysis data;

[0035] The new instruction marking submodule uses the voice query analysis data to mark unfinished query tasks as new instructions, optimize the marking process, enhance the recognition response speed, adjust the classification parameters, and generate a new instruction task set;

[0036] The natural language feedback submodule summarizes the natural language feedback for the user according to the new instruction task set, adjusts the feedback parameters, converts the feedback data into a voice signal, optimizes the voice conversion process, captures the user's feedback audio, and obtains the user feedback audio.

[0037] As a further solution of the present invention, the voice interaction adjustment module includes:

[0038] The conversation analysis submodule analyzes the conversation content, including data associated with the electronic student ID card task execution record, based on the user feedback audio, and generates a detailed conversation analysis result by optimizing the voice-to-text conversion accuracy, distinguishing and identifying unfinished and repeated instructions, and strengthening the analysis of detail processing;

[0039] The task chain reorganization submodule uses the detailed conversation analysis results to reorder the tasks identified in the conversation, adjust the execution order of the tasks and reflect the priority of real-time user needs, fine-tune the task management logic to optimize the execution path, and obtain the reorganized task chain data;

[0040] The process reallocation submodule reallocates the calling process of the electronic student card function according to the reorganized task chain data, adjusts the calling sequence and resource allocation of tasks, matches user interaction requirements, optimizes the calling process, and generates a voice interaction task allocation data table.

[0041] Based on the same inventive concept, an electronic student ID card is also proposed, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the intelligent voice interaction system as described above is implemented.

[0042] Compared with the prior art, the advantages and positive effects of the present invention are:

[0043] In the present invention, by analyzing the frequency domain and time domain features of the speech signal, the audio signal is converted into a speech text sequence, which helps to accurately capture the detailed features in the speech and improve the recognition accuracy. In the processing of semantic content, by parsing and reorganizing the speech text sequence word by word, the logical relationship between time, scope and semantic objects is established to ensure a clear information structure and support the accurate extraction and task description of complex semantics. The task allocation link optimizes the task execution order through resource consumption and dependency analysis to enhance the efficiency and adaptability of the system. The task execution process combines data retrieval with dependent content classification integration to ensure the execution coordination of key tasks and related tasks. The dynamic feedback mechanism improves the coherence of the dialogue and the naturalness of the response by marking unfinished tasks and assembling supplementary information. The voice interaction adjustment module analyzes the unfinished instructions and repeated call content, optimizes task allocation and process arrangement, and enhances the sensitivity and response capabilities to changes in user needs. By strengthening voice input and processing, task decomposition and scheduling, dynamic adjustment and feedback generation capabilities, the intelligent voice interaction system has higher accuracy, coherence and adaptability, and significantly improves the user experience and service efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a system flow chart of the present invention.

[0045] Figure 2 It is a schematic diagram of the system framework of the present invention.

[0046] Figure 3 This is a flow chart of the voice input processing module in the present invention.

[0047] Figure 4 It is a flowchart of the semantic decomposition module in the present invention.

[0048] Figure 5 It is a flowchart of the task allocation module in the present invention.

[0049] Figure 6 It is a flow chart of the logic execution module in the present invention.

[0050] Figure 7 It is a flow chart of the dynamic response module in the present invention.

[0051] Figure 8 It is a flow chart of the voice interaction adjustment module in the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] See also Figure 1 to Figure 2 , an intelligent voice interaction system comprises:

[0054] The speech input processing module analyzes the frequency domain and time domain features of the speech signal, performs frame segmentation on the audio signal, extracts the amplitude and frequency distribution characteristics in consecutive frames, identifies the morpheme sequence, integrates the temporal relationship and structural content between morphemes, and generates a speech text sequence;

[0055] The semantic decomposition module analyzes the part-of-speech relationship of the speech text sequence word by word, separates the verb and the target object, reorganizes the semantics through syntactic rules, extracts time and scope constraints, associates the logical relationship between the constraints and key semantic objects, combines the parsed content, and generates a set of task semantic descriptions;

[0056] The task allocation module parses the key tasks and secondary tasks in the task semantic description set, analyzes the resource consumption time of each task, evaluates the dependency order between tasks, sorts them according to priority, allocates the grouping and order of task execution, decomposes the tasks according to the dependency chain order, and generates a task scheduling list;

[0057] The logic execution module loads the task attributes in the task scheduling list, calls the electronic student ID data to retrieve the course information, parses the task dependency content in the data and classifies and integrates it, executes the query operations required for key tasks, integrates the associated condition tasks in turn, and generates a set of task execution results;

[0058] The dynamic response module analyzes the completed query content based on the task execution result set, marks the unfinished tasks in the user request as new instructions, assembles context information through the content supplement mechanism, assembles it into feedback text in natural language form, converts the text into voice signal output, and obtains user feedback audio;

[0059] The voice interaction adjustment module extracts the conversation content in the user feedback audio and the task execution record of the electronic student card, analyzes the unfinished instructions in the conversation and the repeatedly called electronic student card functions, rearranges the task chain, and allocates the calling process to generate a voice interaction task allocation data table.

[0060] The speech text sequence includes amplitude characteristics, frequency distribution characteristics, morpheme sequences, and time relations. The task semantic description set includes time limitation conditions, scope limitation conditions, logical relations, and key semantic objects. The task scheduling list includes key tasks, secondary tasks, task priorities, task dependency order, and resource consumption assessment. The task execution result set includes query operation results, task classification data, and associated condition integration results. The feedback text includes context information, natural language feedback content, and unfinished task marks. The user feedback audio includes query content, unfinished instructions, and new instruction content. The voice interaction task allocation data table includes unfinished instructions, repeated call records, task chain adjustment data, and call process allocation information.

[0061] Specifically, if Figure 2 and Figure 3 As shown, the voice input processing module includes:

[0062] The signal analysis submodule analyzes the frequency domain characteristics and time domain characteristics of the speech signal, performs quantitative analysis on the energy distribution of the signal, performs periodicity detection and amplitude analysis on the waveform, and adjusts the detailed parameters of the frequency domain analysis to obtain the execution flow of the signal characteristic description as follows;

[0063] Analyze the frequency domain and time domain features of speech signals. By analyzing the features, the energy distribution of the signal can be quantitatively analyzed. This analysis involves the calculation of the density of the spectrum and the evaluation of the total energy. The adjustment of detailed parameters in the frequency domain analysis is to more accurately reflect the true characteristics of the signal. The adjusted parameters are optimized through mathematical optimization methods such as gradient descent to ensure that the obtained frequency domain representation is closest to the original signal. This optimization process requires iterative updating of parameters based on feedback from the actual signal. Periodic detection includes the determination of the signal period and amplitude analysis, which is used to identify periodic changes in the signal. This is particularly important for speech recognition systems because it can reveal the speaker's speech pattern and speaking rate. The signal characteristic description comprehensively refers to all analysis results of the signal and provides necessary data support for subsequent processing.

[0064] The frame segmentation submodule uses signal characteristic description to perform frame segmentation of the audio signal, adjusts the segmentation time window and interval parameters, optimizes the coherence and resolution of the intra-frame data, extracts the amplitude, frequency and energy of each frame, and obtains the frame characteristic data set through intra-frame characteristic data analysis. The execution process is as follows;

[0065] The signal characteristics are used to describe the frame segmentation of the audio signal. The time window and interval of the frame are adjusted according to the signal characteristics, using the formula:

[0066] ;

[0067] Calculate the duration of the frame, where represents the time window of the frame, represents the number of samples in the frame, is the sampling frequency;

[0068] This formula assists in precisely controlling the temporal length and coverage of the frame, thereby optimizing the coherence and resolution of the data within the frame. The frame characteristic data set is calculated from the amplitude, frequency, and energy data within the frame;

[0069] Through actual monitoring, assuming that the signal sampling rate is 44.1kHz, the number of samples per frame Set it to 1024 and substitute it into the formula to get seconds, which means that each frame lasts about 23.2 milliseconds. This setting can effectively capture the short-term changes of speech signals in practical applications, which is helpful for subsequent speech analysis and feature extraction.

[0070] The morpheme integration submodule uses the frame feature data set to perform morpheme analysis and integration of consecutive frames, strengthens the logical and structural relationship between morphemes through time series analysis, optimizes the coherence of morphemes, and generates the speech text sequence. The execution process is as follows;

[0071] The frame feature dataset is used to analyze and integrate the morphemes of consecutive frames. The integration of morphemes is based on the comparison of feature data between consecutive frames. The data is processed through time series analysis methods, such as the autoregressive moving average model or the hidden Markov model, to strengthen the logical and structural relationship between morphemes. This analysis can improve the coherence of morphemes, making the integrated morphemes more consistent with the semantics and grammatical structure of natural language, and the generated speech text sequence more fluent and natural, and the overall semantic expression is therefore optimized. Through the real-time feedback adjustment process, the processing of each morpheme is closely dependent on the analysis results of the previous step, ensuring that the speech recognition system can accurately convert speech input into text output.

[0072] Specifically, if Figure 2 and Figure 4 As shown, the semantic decomposition module includes:

[0073] The part-of-speech analysis submodule performs part-of-speech tagging based on the speech text sequence, including the recognition of verbs and nouns, uses the corpus data for comparative analysis to verify the part-of-speech of each word, adjusts the analysis accuracy and matches the text complexity, and obtains the part-of-speech relationship data in the following execution flow;

[0074] Part-of-speech tagging is performed based on speech text sequences. In this process, the recognition of verbs and nouns depends on corpus data. The data provides the necessary reference to verify the part-of-speech of each word. By comparing typical use cases in the corpus, the submodule can determine the appropriate part-of-speech of words in different contexts. The adjustment of analysis accuracy is achieved through algorithm iteration, including the recognition and correction of incorrect part-of-speech tags. Matching text complexity involves analysis of the structure and grammatical diversity of the text, ensuring that the system can adapt to text inputs from simple to complex. The acquired part-of-speech relationship data is the basis for subsequent syntactic reorganization. This data reflects the grammatical connection and structural layout between words.

[0075] The syntactic reorganization submodule uses part-of-speech relationship data to adjust the relationship between the verb and the target object according to syntactic rules, optimizes the sentence structure, analyzes key syntactic elements and reorganizes sentence components to obtain the syntactic structure data. The execution process is as follows;

[0076] Use part-of-speech relationship data to adjust the relationship between the verb and the target object according to syntactic rules. In the process of syntactic reorganization, analyze the key syntactic elements and reorganize the sentence components. This involves complex sentence component parsing and reconstruction technology, which can optimize the structure of sentences and improve the fluency and logical coherence of sentences. Syntactic structure data is the basis for generating more accurate semantic descriptions. The data integrates the results of all syntactic analyses and provides detailed syntactic relationship and structural information, which is the key to understanding and generating complex texts.

[0077] The logical relationship submodule is based on syntactic structure data and adopts conditional semantic nesting analysis to extract the time and scope limiting conditions in the sentence, associate the conditions with the key semantic objects of the sentence, and use logical analysis methods to integrate the key semantic elements to generate the task semantic description set. The execution process is as follows;

[0078] The formula for conditional semantic nested analysis is as follows:

[0079] ;

[0080] in, Represents the set value of the task semantic description, Represents the normalized value of the time qualification in the statement, represents the semantic density of the scope-qualifying conditions in the statement, Represents the correlation matching degree of key semantic objects in the sentence, Represents the sum of the weights of key semantic elements in the logical analysis process. represents the correction coefficient of the level in the syntactic structure data, represents the distribution complexity index of conditions and key semantic objects in the sentence, , is the adjustment coefficient, , is the normalization coefficient;

[0081] Detailed explanation of the formula and the process of formula calculation and derivation:

[0082] : represents the standardized value of the time qualification extracted from the sentence. In practical applications, suppose 100 text paragraphs are analyzed, and the time conditions range from dates to specific hours. After standardization, such as using the Z-score method, The value of is 1.5, which means that it deviates from the mean time condition by 1.5 standard deviations;

[0083] : represents the semantic density of the scope-limiting conditions extracted from the sentence. If the sentence contains 10 scope conditions such as "nationwide", "region", "specific city", etc., after frequency analysis and inverse document frequency calculation, The value is 0.8;

[0084] : The association matching degree refers to mining 80% matches by comparing with known semantic objects in the database, so it is set to 0.8;

[0085] : The sum of the weights of the key semantic elements in the logical analysis process. If there are 5 key elements, the weight of each is set according to the previous research results, and the sum is 2.5;

[0086] : The correction coefficient of the level in the syntactic structure data is adjusted according to the complexity of the sentence. Assuming that the sentence is more complex, Set to 0.7;

[0087] : The distribution complexity index of conditions and key semantic objects was calculated and determined to be 1.2;

[0088] and : Adjustment coefficients, 0.5 and 0.3 respectively, are the optimal values ​​obtained based on previous experiments and optimizations;

[0089] and : Normalization coefficient, set to 1 and 0.5 to ensure that the calculation results of the formula are within a reasonable range;

[0090] Calculate the square root of the absolute value of the product of the time condition and the range condition: ;

[0091] Calculate the adjusted contribution of the relevance match of the key semantic objects: ;

[0092] Calculate the absolute value adjusted contribution of the weight difference in the logical analysis: ;

[0093] Compute the normalized and complexity-adjusted value of the denominator: ;

[0094] In summary, the final calculation of the formula is:

[0095] ;

[0096] The results show that through the conditional semantic nesting analysis method, referring to the semantic density of time and scope and its matching degree with logical relations, the key semantic elements are effectively integrated, and the obtained task semantic description set value is about 1.273, which means that the calculation method can effectively integrate the input sentence conditions and generate a more accurate semantic description set, reflecting the application effect and accuracy of the analysis model.

[0097] Specifically, if Figure 2 and Figure 5 As shown, the task allocation module includes:

[0098] The task analysis submodule identifies and classifies critical and non-critical tasks based on the task semantic description set, evaluates the resource and time consumption of each task, optimizes the accuracy of resource allocation and time allocation, adjusts the evaluation parameters to match the urgency of differentiated tasks, and obtains the task resource consumption data. The execution process is as follows;

[0099] The tasks are optimized by evaluating the single resource consumption coefficient and the corresponding time, using the formula:

[0100] ;

[0101] Calculate the total resource consumption, where Represents the total resource consumption, Indicates The resource consumption coefficient of a task, Indicates the corresponding time;

[0102] By multiplying and accumulating the resource consumption coefficient and time, the total amount of resources required to complete a series of tasks can be accurately evaluated, thereby optimizing resource allocation and time scheduling;

[0103] Referring to a practical example, there are three tasks, and their resource consumption coefficients are The corresponding time consumption is Hour, Hour, Hour;

[0104] Total resource consumption The calculation is as follows: ,This result shows that a total of 12 units of resources are needed to complete these three tasks, which helps managers to arrange resources reasonably and ensure that tasks are completed on time without wasting resources.

[0105] The dependency sorting submodule uses the task resource consumption data to analyze the dependencies and execution priorities between tasks, optimizes the task execution order by adjusting the priority sorting parameters, and generates the execution flow of the task dependency sequence as follows;

[0106] Analyze the dependencies and execution priorities between tasks. The process involves identifying the sequence and resource flow between tasks. Through data analysis and priority adjustment, ensure the logic and efficiency of task execution, optimize the order of task execution, and use sorting algorithms such as topological sorting or priority queue technology to ensure that prerequisites are met before subsequent tasks are activated, optimize the execution order, and significantly improve the overall workflow efficiency, reduce waiting and idle time, and adjust the priority sorting parameters based on the urgency and complexity of the task. Such parameter adjustments are achieved through algorithm iteration and feedback adjustment to ensure smooth task execution and on-demand resource allocation.

[0107] The task scheduling submodule formulates the task execution grouping and order according to the task dependency sequence, plans the scheduling of each task, adjusts the execution grouping parameters and scheduling strategy and matches the task requirements, and generates the execution process of the task scheduling list as follows;

[0108] Execution groups and orders are formulated according to the task dependency sequence. The scheduling of each task is planned in detail. The scheduling strategy is set based on the urgency, importance and resource availability of the task. The submodule adjusts the execution group parameters to match various task requirements, such as parallel processing capabilities and interface requirements between tasks. The generated task scheduling list provides an execution guide for management, and lists in detail the start time, execution order and resource allocation of each task. The process ensures that all tasks can be executed within the optimal time window, thereby improving overall work efficiency and reducing resource waste caused by improper scheduling. It is particularly critical for complex multi-task environments. The scheduling submodule uses advanced algorithms to ensure the optimization of the scheduling plan, such as genetic algorithms or simulated annealing algorithms for optimizing scheduling strategies to achieve the most effective resource sharing and time coordination between tasks.

[0109] Specifically, if Figure 2 and Figure 6 As shown, the logic execution module includes:

[0110] The task attribute loading submodule identifies the attributes of each task based on the task scheduling list, analyzes and loads the task attributes, uses real-time adjustment technology to refine the loading process, adjusts the loading rate and optimizes the task matching logic, and generates the execution process of the task attribute data set as follows;

[0111] Adjust the loading process through real-time technology, optimize the task matching logic, and use the formula:

[0112] ;

[0113] To adjust the loading rate, represents the loading power, Represents the amount of data loaded, For time;

[0114] This formula is used to calculate and adjust the data loading rate to ensure fast and accurate loading of task attribute data sets;

[0115] Refer to an actual scenario, the amount of task data 500MB, estimated loading time For 2 minutes, the loading power is calculated by the formula: MB / min, loading data at a rate of 250MB per minute within a given time, can meet the system's demand for fast data processing while maintaining system efficiency and responsiveness.

[0116] The course information retrieval submodule uses the task attribute data set to call the electronic student ID data to retrieve the target course information, including adjusting and optimizing the retrieval parameters, extracting key course dependency information, and obtaining the course dependency data. The execution process is as follows;

[0117] Using the task attribute data set, the electronic student ID data is called to retrieve course information. The adjustment and optimization of the retrieval parameters are based on the results of data analysis. The purpose of optimization is to improve the accuracy and efficiency of the retrieval. The adjusted retrieval parameters can more accurately reflect student needs and course dependencies. The extraction of key course dependency information focuses on parsing the logical relationship between courses, which is of great significance for student course planning and teaching resource allocation. By refining the retrieval logic and optimizing the algorithm, the course information required by students can be efficiently screened, providing data support for teaching management and student learning.

[0118] The dependency parsing submodule integrates key tasks and associated conditional tasks through course dependency data, adjusts query parameters, and organizes and executes them in sequence to generate a set of task execution results. The execution process is as follows;

[0119] Integrate key tasks and related conditional tasks, adjust query parameters to optimize task execution process, analyze dependencies between tasks through algorithms and set execution order. The key is to ensure that all tasks are executed correctly according to logic and priority. By dynamically adjusting query parameters, the module can flexibly respond to changing task requirements and condition restrictions. The organization of execution order involves complex logical judgments and parameter settings to ensure coordination between tasks and data consistency. The generated task execution result set provides an execution benchmark and reference for subsequent tasks, supporting stable operation and efficient management of the system.

[0120] Specifically, if Figure 2 and Figure 7 As shown, the dynamic response module includes:

[0121] The query result analysis submodule performs query result analysis based on the task execution result set, distinguishes completed and unfinished query tasks by adjusting the analysis parameters, optimizes the data screening logic, and obtains the execution process of voice query analysis data as follows;

[0122] By adjusting the analysis parameters, distinguish between completed and unfinished query tasks, using the formula:

[0123] ;

[0124] in, Indicates the percentage of task completion. is the number of unfinished tasks, is the total number of tasks;

[0125] Computational models assist in evaluating the overall task progress and ensure the effectiveness and optimization of data screening logic;

[0126] Set the total number of tasks is 100, the number of unfinished tasks If it is 20, the task completion degree Calculated as , 80% of the tasks have been completed. This indicator is crucial for evaluating project progress and adjusting future strategies, helping managers identify areas that require additional resources and attention.

[0127] The new instruction marking submodule uses voice query analysis data to mark unfinished query tasks as new instructions, optimizes the marking process, enhances the recognition response speed, adjusts the classification parameters, and generates the execution process of the new instruction task set as follows;

[0128] Voice query analysis data is used to mark and classify new instructions. The adjusted classification parameters help to accurately distinguish the status of various query tasks. Unfinished query tasks receive new instruction tags through an optimized process. During the tagging process, the system identifies task keywords through algorithm analysis and adjusts the tagging logic to improve tagging accuracy and response speed. Internal adjustments to the system include learning and adapting to users' query habits, and giving priority to frequently occurring query problems. The optimization results not only improve the system's operating efficiency, but also enhance the user experience, ensuring that all unfinished tasks are processed in a timely manner according to priority and resource availability.

[0129] The natural language feedback submodule summarizes the natural language feedback for the user according to the new instruction task set, adjusts the feedback parameters, converts the feedback data into a voice signal, optimizes the voice conversion process, captures the user's feedback audio, and obtains the execution flow of the user feedback audio as follows;

[0130] The user's natural language feedback is summarized according to the new command task set, and the feedback parameters are adjusted to enhance the accuracy and fluency of speech recognition. The text feedback is converted into speech signals through advanced speech recognition technology and natural language processing algorithms. The optimization process includes the adjustment of the pitch, speed and rhythm of the speech to adapt to the pronunciation characteristics of different users. By capturing user feedback audio, adding noise filtering and speech enhancement functions, the user's instructions can be accurately captured and parsed in noisy environments. The improved feedback mechanism makes the user's interaction with the system more natural and efficient. The collected audio data is also used to further train and optimize the system's speech recognition model.

[0131] Specifically, if Figure 2 and Figure 8 As shown, the voice interaction adjustment module includes:

[0132] The conversation analysis submodule analyzes the conversation content based on the user feedback audio, including the data associated with the electronic student ID card task execution record, and optimizes the accuracy of speech-to-text conversion, distinguishes and identifies unfinished and repeated instructions, and strengthens the analysis of detail processing. The execution process of generating detailed conversation analysis results is as follows;

[0133] The conversation content is analyzed based on user feedback audio, the voice data is converted into text data, and then the text is analyzed to identify unfinished and repeated instructions. The technology used in the conversion process is an advanced speech recognition algorithm. The algorithm optimizes its recognition accuracy through a large amount of data training. Optimizing the accuracy of speech-to-text conversion not only includes improving the accuracy of speech recognition, but also involves the recognition of dialects and accents, as well as speaker separation technology in multi-person conversation scenarios. It can accurately distinguish various types of instructions and mark repeated instructions to reduce redundant operations of the system. The analysis of detailed processing further includes sentiment analysis of the conversation content to judge the user's emotions and intentions, and provide guidance for system upgrades in future time periods.

[0134] The task chain reorganization submodule uses the detailed conversation analysis results to reorder the tasks identified in the conversation, adjust the execution order of the tasks and reflect the priority of real-time user needs, fine-tune the task management logic to optimize the execution path, and obtain the execution process of the reorganized task chain data as follows;

[0135] Using the results of detailed conversation analysis to reorder and optimize conversation tasks involves complex algorithms, including natural language processing and machine learning. Especially when dealing with long conversations involving multiple tasks, the submodule analyzes the logical relationship between tasks and the user's urgent needs, and dynamically adjusts the order of task execution based on real-time data. The main methods for fine-tuning the task management logic to optimize the execution path include using decision trees and priority queue algorithms. The algorithm automatically adjusts the order of tasks according to task priorities and dependencies, thereby optimizing the execution path and being able to quickly respond to user changes. The generated reorganized task chain data makes the system more flexible and responsive to user operations, ensuring that the task management logic closely matches the user's actual interactions.

[0136] The process reallocation submodule reallocates the calling process of the electronic student ID card function according to the reorganized task chain data, adjusts the calling sequence and resource allocation of tasks, matches user interaction requirements, optimizes the calling process, and generates the voice interaction task allocation data table. The execution process is as follows;

[0137] Reassign the calling process of the electronic student ID card function according to the reorganized task chain data, using the formula:

[0138] ;

[0139] To optimize the task calling process, Indicates the task processing time, Represents the total amount of resources available. Represents the number of tasks that need to be processed at the same time;

[0140] This formula reduces the total time of task processing and improves processing efficiency by optimizing resource allocation;

[0141] Set resource amount For 1000 units, the number of tasks is 10, task processing time The calculation is as follows: Unit time;

[0142] The results show that each task obtains an average of 100 units of time resources, allowing the system to efficiently process multiple tasks in parallel, thereby quickly responding to user interaction needs. The optimized calling process ensures the rational allocation of resources and efficient task processing.

[0143] An electronic student ID card includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the intelligent voice interaction system as described above is implemented.

[0144] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent voice interaction system, characterized in that: The system comprises: The speech input processing module analyzes the frequency domain and time domain features of the speech signal, segments the audio frames, extracts the amplitude and frequency distribution, identifies the morpheme sequence, integrates the time relationship, and generates the speech text sequence; The semantic decomposition module analyzes the part-of-speech relationship of the speech text sequence word by word, separates verbs and target objects, extracts time and range conditions, associates semantic logic, and generates a task semantic description set; The task allocation module parses the key tasks and secondary tasks in the task semantic description set, analyzes resources and dependency order, prioritizes and groups them, allocates them, decomposes the chain, and generates a task scheduling list; The logic execution module loads the task attributes in the task scheduling list, calls the electronic student card to retrieve courses, parses dependencies and classifies and integrates them, executes query tasks, and generates a task execution result set; The dynamic response module analyzes the completed query content based on the task execution result set, marks the unfinished tasks, supplements the context into feedback text, converts the voice signal output, and obtains the user feedback audio; The voice interaction adjustment module extracts the conversation content and task execution records based on the user feedback audio, analyzes the unfinished instructions, adjusts the task chain and allocates the process, and generates a voice interaction task allocation data table.

2. The intelligent voice interaction system according to claim 1, characterized in that: The speech text sequence includes amplitude characteristics, frequency distribution characteristics, morpheme sequences, and time relationships. The task semantic description set includes time limitation conditions, scope limitation conditions, logical relationships, and key semantic objects. The task scheduling list includes key tasks, secondary tasks, task priorities, task dependency orders, and resource consumption assessments. The task execution result set includes query operation results, task classification data, and associated condition integration results. The feedback text includes context information, natural language feedback content, and unfinished task marks. The user feedback audio includes query content, unfinished instructions, and new instruction content. The voice interaction task allocation data table includes unfinished instructions, repeated call records, task chain adjustment data, and call process allocation information.

3. The intelligent voice interaction system according to claim 1, characterized in that: The speech input processing module comprises: The signal analysis submodule analyzes the frequency domain and time domain characteristics of the speech signal, performs quantitative analysis on the energy distribution of the signal, performs periodicity detection and amplitude analysis on the waveform, and adjusts the detailed parameters of the frequency domain analysis to obtain a description of the signal characteristics; The frame segmentation submodule uses the signal characteristic description to perform frame segmentation of the audio signal, adjust the time window and interval parameters of the segmentation, optimize the coherence and resolution of the data within the frame, extract the amplitude, frequency and energy of each frame, and obtain the frame characteristic data set through the analysis of the characteristic data within the frame; The morpheme integration submodule uses the frame characteristic data set to perform morpheme analysis and integration of continuous frames, strengthen the logical and structural relationship between morphemes through time series analysis, optimize the coherence of morphemes, and generate a speech text sequence.

4. The intelligent voice interaction system according to claim 1, characterized in that: The semantic decomposition module comprises: The part-of-speech analysis submodule performs part-of-speech tagging based on the speech text sequence, including recognition of verbs and nouns, uses corpus data for comparative analysis to verify the part-of-speech of each word, adjusts the analysis accuracy and matches the text complexity, and obtains part-of-speech relationship data; The syntactic reorganization submodule uses the part-of-speech relationship data to adjust the relationship between the verb and the target object according to syntactic rules, optimize the sentence structure, analyze key syntactic elements and reorganize sentence components to obtain syntactic structure data; The logical relationship submodule is based on the syntactic structure data and adopts conditional semantic nesting analysis to extract the time and scope limiting conditions in the sentence, associate the conditions with the key semantic objects of the sentence, integrate the key semantic elements using logical analysis methods, and generate a task semantic description set.

5. The intelligent voice interaction system according to claim 4, characterized in that: The formula of the conditional semantic nested analysis method is as follows: ； in, Represents the set value of the task semantic description, Represents the normalized value of the time qualification in the statement, represents the semantic density of the scope-qualifying conditions in the statement, Represents the correlation matching degree of key semantic objects in the sentence, Represents the sum of the weights of key semantic elements in the logical analysis process. represents the correction coefficient of the level in the syntactic structure data, represents the distribution complexity index of conditions and key semantic objects in the sentence, , is the adjustment coefficient, , is the normalization coefficient.

6. The intelligent voice interaction system according to claim 1, characterized in that: The task allocation module includes: The task analysis submodule identifies and classifies critical and non-critical tasks based on the task semantic description set, evaluates the resource and time consumption of each task, optimizes the accuracy of resource allocation and time allocation, adjusts the evaluation parameters to match the urgency of differentiated tasks, and obtains task resource consumption data; The dependency sorting submodule uses the task resource consumption data to analyze the dependencies and execution priorities between tasks, optimizes the task execution order by adjusting the priority sorting parameters, and generates a task dependency sequence; The task scheduling submodule formulates the task execution grouping and order according to the task dependency sequence, plans the scheduling of each task, adjusts the execution grouping parameters and scheduling strategy and matches the task requirements, and generates a task scheduling list.

7. The intelligent voice interaction system according to claim 1, characterized in that: The logic execution module includes: The task attribute loading submodule identifies the attributes of each task based on the task scheduling list, analyzes and loads the task attributes, refines the loading process using real-time adjustment technology, adjusts the loading rate and optimizes the task matching logic, and generates a task attribute data set; The course information retrieval submodule uses the task attribute data set to call the electronic student ID data to retrieve the target course information, including adjusting and optimizing the retrieval parameters, extracting key course dependency information, and obtaining course dependency data; The dependency parsing submodule integrates key tasks and associated conditional tasks through the course dependency data, adjusts query parameters, and organizes and executes them in sequence to generate a task execution result set.

8. The intelligent voice interaction system according to claim 1, characterized in that: The dynamic response module includes: The query result analysis submodule performs query result analysis based on the task execution result set, distinguishes completed and uncompleted query tasks by adjusting analysis parameters, optimizes data screening logic, and obtains voice query analysis data; The new instruction marking submodule uses the voice query analysis data to mark unfinished query tasks as new instructions, optimize the marking process, enhance the recognition response speed, adjust the classification parameters, and generate a new instruction task set; The natural language feedback submodule summarizes the natural language feedback for the user according to the new instruction task set, adjusts the feedback parameters, converts the feedback data into a voice signal, optimizes the voice conversion process, captures the user's feedback audio, and obtains the user feedback audio.

9. The intelligent voice interaction system according to claim 1, characterized in that: The voice interaction adjustment module includes: The conversation analysis submodule analyzes the conversation content, including data associated with the electronic student ID card task execution record, based on the user feedback audio, and generates a detailed conversation analysis result by optimizing the voice-to-text conversion accuracy, distinguishing and identifying unfinished and repeated instructions, and strengthening the analysis of detail processing; The task chain reorganization submodule uses the detailed conversation analysis results to reorder the tasks identified in the conversation, adjust the execution order of the tasks and reflect the priority of real-time user needs, fine-tune the task management logic to optimize the execution path, and obtain the reorganized task chain data; The process reallocation submodule reallocates the calling process of the electronic student card function according to the reorganized task chain data, adjusts the calling sequence and resource allocation of tasks, matches user interaction requirements, optimizes the calling process, and generates a voice interaction task allocation data table.

10. An electronic student ID card, comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor implements the intelligent voice interaction system according to any one of claims 1 to 9 when executing the computer program.

Images