Electric appliance communication control method and system

Abstract

The invention relates to the technical field of communication control, in particular to an electric appliance communication control method and system. The method comprises the following steps: acquiring user recording data; performing feature extraction on the user recording data, constructing a feature database, and generating a voice feature database; acquiring real-time user voice data; performing similarity matching on the real-time user voice data and the voice feature database to generate user audio judgment result data; the control center assembly generates a control instruction strategy based on the user audio judgment result data and generates an electric appliance communication control strategy, and the control center assembly comprises a main control center and a sub-control center; therefore, by constructing the intelligent recognition system based on the multi-level features, the problems of insufficient user voice understanding, response lag and the like in a traditional electric appliance control method are solved, and the intelligent level of electric appliance control and the convenience of operation are improved.

Description

Technical Field

[0001] The present invention relates to the field of communication control technology, and in particular to an electrical appliance communication control method and system. Background Art

[0002] Traditional electrical control systems often rely on fixed control instructions and simple trigger mechanisms, which leads to a lack of flexibility in handling complex scenarios. For example, when the user's instructions do not match the device status, the system cannot respond intelligently, resulting in a poor user experience. In addition, existing systems have problems with the accuracy of voice recognition and signal processing, and are easily disturbed by environmental noise, which affects the correct interpretation of instructions. Secondly, existing technologies are relatively weak in data processing and analysis capabilities, and cannot achieve real-time adaptation to user behavior and environmental changes. Many systems lack effective multi-dimensional data fusion technology, making it difficult to comprehensively monitor and analyze device status from different dimensions, resulting in information islands and affecting the accuracy of overall decision-making. In addition, the lack of an effective personalized instruction generation mechanism means that users cannot customize settings according to their own habits and needs, which limits the level of intelligence of the system. Finally, insufficient data sharing and system interoperability often lead to delayed information transmission and untimely responses. This makes it impossible for users to obtain device status in a timely manner or conduct effective remote control, limiting the application scenarios of the system. Summary of the invention

[0003] Based on this, it is necessary to provide an electrical appliance communication control method and system to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for controlling communication of an electrical appliance is provided, the method comprising the following steps:

[0005] Step S1: Obtain user recording data; extract features from the user recording data, build a feature database, and generate a voice feature database;

[0006] Step S2: acquiring real-time user voice data; performing similarity matching between the real-time user voice data and the voice feature database to generate user audio judgment result data; the control center component generates a control instruction strategy based on the user audio judgment result data to generate an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center;

[0007] Step S3: The sub-control center monitors the electrical equipment in real time based on the electrical communication control strategy, and generates a real-time monitoring report for the sub-control center; the real-time monitoring report of the sub-control center is sent to the main control center through the data exchange network for monitoring report analysis, and a main control center electrical equipment monitoring report is generated;

[0008] Step S4: Perform visual analysis based on the electrical appliance monitoring report of the main control center to generate a visual electrical appliance communication report, thereby completing the electrical appliance communication control operation.

[0009] The beneficial effect of the present invention is that by constructing a multi-level voice feature database, accurate recognition and analysis of user voice is achieved, thereby significantly improving the intelligent level of electrical control. The user recording data is obtained and the features are extracted to form a detailed voice feature database, so that the system can capture the personalized features of the user's tone, voice tone, etc. This multi-dimensional feature capture lays a solid foundation for subsequent similarity matching. By performing similarity matching between real-time user voice data and the voice feature database, user audio judgment result data is generated, ensuring accurate recognition and timely response of instructions. This precise matching mechanism can effectively distinguish between the user's real-time voice and recording, thereby generating corresponding electrical communication control strategies for different situations, and improving the flexibility and adaptability of the system. The sub-control center performs real-time monitoring according to the electrical communication control strategy, generates a detailed monitoring report, and sends the report to the main control center for analysis through the data exchange network. This process not only realizes efficient data transmission, but also provides data support for real-time monitoring, so that the status of electrical equipment can be fed back to the control center component in a timely manner, enhancing the real-time performance and response speed of the system. The main control center conducts visual analysis of the monitoring report and generates an intuitive visual electrical appliance communication report, which facilitates users and managers to quickly understand the system operation status and make corresponding decisions. Therefore, the present invention solves the problems of insufficient understanding of user voice and delayed response in traditional electrical appliance control methods by constructing an intelligent recognition system based on multi-level features, thereby improving the intelligent level of electrical appliance control and the convenience of operation.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: segment the user recording data into phrases and words, and segment the user's voice data;

[0012] Step S12: extracting speech features from the user speech segmentation data using a speech signal processing algorithm to generate user speech feature data, wherein the user speech feature data includes pitch feature data and tone feature data;

[0013] Step S13: constructing a database based on the user's voice feature data to generate a voice feature database.

[0014] The present invention ensures the structuring of voice data by segmenting user recording data into phrases and words, so that subsequent processing can focus more on the feature extraction of each voice unit. This segmentation strategy not only optimizes the data processing flow, but also reduces the risk of information loss, laying a foundation for subsequent feature analysis. The segmented user voice data is subjected to feature extraction using a voice signal processing algorithm, and the generated user voice feature data includes pitch feature data and tone feature data, which can fully reflect the user's personalized expression and emotional state. This feature extraction based on pitch and tone enables the system to not only capture the voice content but also perceive the change of tone when identifying the user's intention, thereby enhancing the system's contextual understanding ability. A database is constructed based on the extracted user voice feature data to generate a voice feature database, which provides strong data support for subsequent similarity matching and command recognition. This database not only stores multi-dimensional voice features, but also provides a dynamic learning platform for the system, so that as the user voice data continues to accumulate, the system can continuously optimize its recognition ability, thereby achieving a more personalized and intelligent user experience. In this way, the system can maintain efficient and accurate response capabilities when faced with diverse expressions of different users, thereby improving the overall performance of appliance communication control and user satisfaction.

[0015] Preferably, step S13 includes the following steps:

[0016] Step S131: obtaining control instructions; performing K-means clustering on the user's voice feature data to generate voice benchmark data;

[0017] Step S132: habitually associating the voice reference data with the control command to generate user personalized command data;

[0018] Step S133: constructing a first-level database using the tone feature data to generate a user basic voice database; sorting the tone feature data into a vector feature matrix and constructing a second-level database to generate a user tone feature database; storing the user personalized instruction data in a third-level database to generate a tone instruction matching database;

[0019] Step S134: The user basic voice database, the user tone feature database and the tone instruction matching database are stored and constructed according to a multi-layer structure database to generate a voice feature database.

[0020] The present invention clusters the user voice feature data by using the K-means clustering algorithm, and the generated voice benchmark data not only effectively reduces redundant information, but also provides a clear category framework for the subsequent generation of personalized instructions. This process enables the system to better understand the user's voice habits, form an effective benchmark, and help improve the accuracy of voice recognition. By habitually associating the voice benchmark data with the control instructions, the user's personalized instruction data is generated. This process not only combines the user's voice features with the actual application scenario, but also makes the control instructions more targeted, thereby improving the response efficiency of the system. The establishment of this habit association can significantly enhance the user experience, so that the system can understand and execute user instructions in a more humane way. Strengthen data storage and management capabilities by building a multi-level database. In step S133, the user basic voice database constructed using the tone feature data provides the system with basic voice data storage, and the user tone feature database generated by sorting the tone feature data into a vector feature matrix provides the system with more detailed user emotional expression information. The combination of the two enables the system to not only identify the user's instructions, but also gain insight into the user's emotional changes, providing more comprehensive data support for the system's intelligent response. By integrating the above multi-layer databases to generate a voice feature database, the system can quickly retrieve relevant information for processing when faced with complex voice input. The construction of this multi-level database not only improves the efficiency of data access, but also provides a good foundation for the system's intelligent learning and self-optimization, allowing it to continuously adapt to user needs while enhancing the overall interactive intelligence level.

[0021] Preferably, step S2 comprises the following steps:

[0022] Step S21: acquiring real-time user voice data; performing similarity matching between the real-time user voice data and the voice feature database to generate voice similarity data;

[0023] Step S22: Performing audio signal recording judgment on the voice similarity data to generate user audio judgment result data, wherein the user audio judgment result data includes recording status data and real-time recording data;

[0024] Step S23: The control center component generates a control instruction strategy based on the voice similarity data to generate an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center.

[0025] The present invention generates voice similarity data by acquiring real-time user voice data and performing similarity matching with a voice feature database. This process utilizes an advanced similarity algorithm, which can accurately identify the correlation between the user's voice command and the pre-stored voice features, thereby ensuring that the system can maintain a high recognition accuracy rate in various noise environments. This dynamic matching mechanism enables the system to flexibly adapt when facing complex user interactions, thereby improving the user's experience satisfaction. By performing audio signal recording judgment on the voice similarity data, user audio judgment result data is generated, and the user's input information is further subdivided. The construction of the user audio judgment result data includes recording status data and real-time recording data, so that the system can clearly distinguish the user's real-time voice input from the recording content. This judgment mechanism not only enhances the system's ability to understand user commands, but also provides an accurate basis for subsequent command execution. The control command strategy is generated based on the above analysis results. The control center component formulates a corresponding electrical communication control strategy by comprehensively analyzing the voice similarity data, which includes the coordination work of the main control center and the sub-control center. This mechanism effectively integrates the decision-making process of voice recognition and electrical control, ensuring the efficiency and accuracy of the system in responding to user commands in real time. By generating a clear control instruction path, the system can quickly and accurately execute user requests, thereby improving the overall system efficiency.

[0026] Preferably, step S22 includes the following steps:

[0027] Step S221: Calculate the recording duration of the voice similarity data based on a preset recording duration threshold, remove abnormal data, and generate normal recording duration data of the user;

[0028] Step S222: Perform time domain fluctuation stability detection based on the normal duration data of the user recording to generate user time domain fluctuation detection data; perform spectrum analysis on the user time domain fluctuation detection data using Fourier transform to generate user spectrum detection data; perform background low-frequency noise detection on the user spectrum detection data, and perform echo and reflection detection processing using phase difference analysis to generate user voice detection data;

[0029] Step S223: using the voice feature database as reference data to perform audio signal recording judgment on the user voice detection data, and generating user audio judgment result data, wherein the user audio judgment result data includes recording status data and real-time recording data.

[0030] The present invention analyzes the voice similarity data by setting a recording duration threshold, effectively eliminates abnormal data, and generates normal user recording duration data. This process ensures the validity of the input data, prevents recognition errors caused by data anomalies, and thus provides high-quality basic data for subsequent processing. The normal user recording duration data is used to perform time domain fluctuation stability detection, and further generate user time domain fluctuation detection data. This step can effectively identify the stability in the user's voice by analyzing the time domain features, and then filter out unstable audio signals. This process combines the spectrum analysis of the user's time domain fluctuation detection data by Fourier transform, so that the system can deeply understand the frequency composition of the sound and extract more accurate audio features. In addition, the detection of background low-frequency noise and the phase difference analysis of echoes and reflections enhance the system's voice recognition ability in a noisy environment, so that user commands can be clearly recognized in a complex environment. The user voice detection data is subjected to audio signal recording judgment based on the voice feature database to generate user audio judgment result data. This result includes not only recording status data, but also real-time recording data, providing a clear basis for command execution for the system. Through this rigorous analysis process, the system can accurately distinguish between the user's real-time voice input and the recorded content, further improving the accuracy of command recognition and reducing the risk of misoperation.

[0031] Preferably, step S23 includes the following steps:

[0032] Step S231: the control center component generates a control instruction strategy based on the user audio judgment result data, and generates an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center, and the electrical appliance communication control strategy includes a recording electrical appliance communication control strategy and a real-time voice electrical appliance communication strategy;

[0033] Step S232: When the user audio judgment result is recording status data, the real-time user voice data is recorded and marked to generate user recording mark data; the central control center generates a control instruction for the user recording mark data based on the voice feature database to generate a master recording control instruction; the master recording control instruction is transmitted to the sub-control center through a preset transmission protocol to generate a sub-control recording control instruction; the sub-control center issues a recording instruction to the electrical appliance based on the sub-control recording control instruction, and terminates the execution program of the electrical appliance, thereby completing the recording electrical appliance communication control strategy;

[0034] Step S233: When the user audio judgment result is real-time recording data, a strict voice match is performed on the real-time user voice data and the voice feature database to generate real-time user voice strict matching data; the main control center uses a preset multi-dimensional decision tree to predict user instructions for the real-time user voice strict matching data to generate a main control candidate control instruction; the main control candidate control instruction is sent to the sub-control center through a preset transmission protocol to generate a sub-control candidate control instruction; the electrical appliance is executed based on the sub-control candidate control instruction, and sub-control feedback execution data is generated; the main control center optimizes the evaluation instruction of the multi-dimensional decision tree based on the sub-control feedback execution data, generates a personalized multi-dimensional decision tree, and iterates the preset multi-dimensional decision tree, thereby completing the real-time voice electrical appliance communication strategy.

[0035] The present invention generates an electrical appliance communication control strategy by using the user audio judgment result data through the control center component, and clarifies two communication modes: recording electrical appliance communication control strategy and real-time voice electrical appliance communication strategy. The generation of this strategy not only provides a flexible response mechanism for the system, but also provides a customized solution for the user's operation requirements in different scenarios. When the system determines that the user audio is in a recording state, the real-time user voice data is recorded and marked to generate user recording mark data. The implementation of this process ensures that the system accurately captures the user's intention. At the same time, by combining with the voice feature database, the main control recording control instruction is generated and sent to the sub-control center through a preset transmission protocol to ensure the efficient transmission of the instruction. The sub-control center implements the recording instruction to the electrical appliance based on the received instruction, and can even terminate the current execution program to complete the recording electrical appliance communication control strategy. This series of steps enhances the system's response speed and accuracy to user instructions, thereby effectively improving the user experience. When the user audio judgment result is real-time recording data, the system implements strict voice matching to generate real-time user voice strict matching data. This step combines a multidimensional decision tree, uses a preset model to predict real-time user instructions, and generates a master control candidate control instruction. The instructions are sent to the sub-control center through the preset transmission protocol to ensure accurate execution and feedback of the instructions. Based on the execution data fed back by the sub-control, the main control center can evaluate and optimize the multi-dimensional decision tree, generate a personalized multi-dimensional decision tree, and achieve a deep understanding and adaptation to user needs.

[0036] Preferably, performing strict voice matching on the real-time user voice data and the voice feature database comprises the following steps:

[0037] The user basic voice database and real-time user voice data are calculated and processed according to the dynamic time warping algorithm to generate user voice dynamic calculation data;

[0038] According to the real-time user voice data, the user tone feature database is sorted into a vector feature matrix, and tone feature vector matching is performed to generate user tone vector matching data;

[0039] Perform context association based on real-time user voice data and tone command matching database to generate user tone command data;

[0040] The three-dimensional database is fused based on the user voice dynamic calculation data, the user voice vector matching data and the user voice command data to generate real-time user voice strict matching data.

[0041] The present invention performs calculation processing of the user basic voice database and the real-time user voice data by the dynamic time warping algorithm, and the generated user voice dynamic calculation data provides accurate time alignment information for real-time voice recognition, thereby overcoming the time delay and inconsistency caused by factors such as speaking speed and intonation changes in voice input. This data processing process ensures that the system can quickly and accurately understand the user's intention in complex voice interaction scenarios. In addition, the user voice feature database is sorted by vector feature matrix based on the real-time user voice data, and the voice feature vector matching operation is performed to generate user voice vector matching data, which provides strong support for the understanding of the voice, so that the system not only pays attention to the content during the recognition process, but also can keenly capture the user's emotions and voice changes. The user voice command data generated by context association using the real-time user voice data and the voice command matching database further improves the accuracy of the command parsing. This process analyzes the voice features of the user in a specific context to ensure that the system can fully consider the context factors when executing the command, thereby optimizing the response strategy. This context association capability provides the system with a more humanized intelligent service in a complex interactive environment. By integrating the user voice dynamic calculation data, user voice vector matching data and user voice command data into a three-dimensional database, the real-time user voice strict matching data is generated, forming a comprehensive information representation form. This fusion not only improves the efficiency of data utilization, but also enhances the system's ability to process multi-dimensional information, enabling it to better adapt to the diverse needs of users.

[0042] Preferably, step S3 comprises the following steps:

[0043] Step S31: the sub-control center performs real-time monitoring of electrical equipment based on the electrical communication control strategy, and generates electrical equipment monitoring data of the sub-control center; generates an institutionalized report of the electrical equipment monitoring data of the sub-control center, and generates a real-time monitoring report of the sub-control center;

[0044] Step S32: Send the sub-control center real-time monitoring report to the main control center through the data exchange network, verify the file integrity, and generate a main control center verification electrical appliance monitoring report;

[0045] Step S33: Analyze the monitoring report of the main control center's electrical appliance verification report to generate a main control center electrical appliance monitoring report.

[0046] The present invention monitors electrical equipment in real time through a sub-control center based on an electrical communication control strategy, and the generated sub-control center electrical monitoring data provides the system with accurate equipment operation status information. This data not only includes the basic operating parameters of the equipment, but also covers potential fault warnings and operating efficiency evaluations, ensuring the safety and efficiency of electrical equipment under different working environments. The process of generating an institutionalized report for the electrical monitoring data of the sub-control center further enhances the readability and operability of the data, so that the monitoring results are presented in a structured form, which is convenient for subsequent data analysis and decision support. In the process of sending the real-time monitoring report of the sub-control center to the main control center through the data exchange network, the implementation of file integrity verification is a key step. This process ensures the accuracy and integrity of the data during the transmission process, prevents data loss or damage, and thus provides a reliable basis for subsequent analysis. The main control center verifies the electrical monitoring report, which is not only a confirmation of the transmitted data, but also provides a guarantee for the comprehensive monitoring of the electrical operation status, so that any abnormal situation can be discovered and handled in time. The monitoring report analysis of the main control center verifies the electrical monitoring report, and the main control center electrical monitoring report generated through systematic data processing and information extraction provides profound insights for management decisions. This analysis process not only reflects the current operating status of electrical equipment, but also provides a basis for subsequent maintenance and optimization strategies, ensuring the effective use of resources and efficient management.

[0047] Preferably, step S4 comprises the following steps:

[0048] Step S41: construct a report based on the time series dimension of the main control center electrical appliance monitoring report to generate a main control center time dimension report; construct a report based on the equipment type dimension of the main control center electrical appliance monitoring report to generate a main control center equipment dimension report; construct a report based on the operation status dimension of the main control center electrical appliance monitoring report to generate a main control center operation dimension report;

[0049] Step S42: The time dimension report of the main control center, the equipment dimension report of the main control center and the operation dimension report of the main control center are integrated into a multi-dimensional form to generate a visualized electrical appliance communication report;

[0050] Step S43: Upload the visualized electrical appliance communication report to a preset cloud platform through a data exchange network to make the electrical appliance communication control report public, thereby completing the electrical appliance communication control operation.

[0051] The present invention significantly improves the understanding and management efficiency of the operating status of electrical equipment through multi-dimensional analysis based on the electrical monitoring report of the main control center. The time dimension report of the main control center constructed based on the time series dimension can reveal the operating changes of electrical equipment in different time periods and provide dynamic operating trend analysis. This time dimension analysis not only helps to identify the periodic failure of the equipment, but also optimizes the maintenance strategy, thereby reducing the potential equipment downtime. In addition, the construction of the equipment type dimension and the operating status dimension enables the report to more carefully classify and analyze the performance and failure mode of different types of electrical appliances, thereby improving the pertinence and effectiveness of monitoring. The multi-dimensional form fusion of the various dimensional reports of the main control center generates a visualized electrical communication report that provides intuitive and comprehensive information support for decision-making. This visualization not only improves the readability of the data, but also enhances the correlation between various types of data, so that managers can quickly identify key issues and optimize resource allocation. In addition, through the presentation of the visualized report, relevant personnel can better grasp the operating efficiency and failure risk of the equipment, thereby improving the overall decision-making level. The visualized electrical communication report is uploaded to the preset cloud platform through the data exchange network, and the electrical communication control report is made public, realizing data sharing and transparency. This open data sharing not only improves the accessibility of information, but also promotes interaction and communication among all parties involved in electrical appliance control and management, thereby improving overall management efficiency and responsiveness.

[0052] In this specification, an electrical appliance communication control system is provided, which is used to execute the above-mentioned electrical appliance communication control method, and the electrical appliance communication control system includes:

[0053] Data collection module: used to obtain user recording data; extract features from user recording data, build a feature database, and generate a voice feature database;

[0054] Real-time recognition module: used to obtain real-time user voice data; perform similarity matching between real-time user voice data and voice feature database to generate user audio judgment result data; the control center component generates control instruction strategy based on user audio judgment result data and generates electrical appliance communication control strategy, wherein the control center component includes main control center and sub-control center;

[0055] Monitoring and reporting module: used by the sub-control center to monitor electrical equipment in real time based on the electrical communication control strategy and generate real-time monitoring reports for the sub-control center; the real-time monitoring reports of the sub-control center are sent to the main control center through the data exchange network for monitoring report analysis and to generate electrical equipment monitoring reports for the main control center;

[0056] Visual analysis module: used to perform visual analysis based on the electrical appliance monitoring report of the main control center, generate a visual electrical appliance communication report, and thus complete the electrical appliance communication control operation.

[0057] The beneficial effect of the present invention is that by constructing a multi-level voice feature database, accurate recognition and analysis of user voice is achieved, thereby significantly improving the intelligent level of electrical control. The user recording data is obtained and the features are extracted to form a detailed voice feature database, so that the system can capture the personalized features of the user's tone, voice tone, etc. This multi-dimensional feature capture lays a solid foundation for subsequent similarity matching. By performing similarity matching between real-time user voice data and the voice feature database, user audio judgment result data is generated, ensuring accurate recognition and timely response of instructions. This precise matching mechanism can effectively distinguish between the user's real-time voice and recording, thereby generating corresponding electrical communication control strategies for different situations, and improving the flexibility and adaptability of the system. The sub-control center performs real-time monitoring according to the electrical communication control strategy, generates a detailed monitoring report, and sends the report to the main control center for analysis through the data exchange network. This process not only realizes efficient data transmission, but also provides data support for real-time monitoring, so that the status of electrical equipment can be fed back to the control center component in a timely manner, enhancing the real-time performance and response speed of the system. The main control center conducts visual analysis of the monitoring report and generates an intuitive visual electrical appliance communication report, which facilitates users and managers to quickly understand the system operation status and make corresponding decisions. Therefore, the present invention solves the problems of insufficient understanding of user voice and delayed response in traditional electrical appliance control methods by constructing an intelligent recognition system based on multi-level features, thereby improving the intelligent level of electrical appliance control and the convenience of operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A schematic flow chart of the steps of an electrical appliance communication control method;

[0059] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0060] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0061] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0062] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0063] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0064] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0065] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0066] To achieve this, please refer to Figures 1 to 4 , an electrical appliance communication control method, the method comprising the following steps:

[0067] Step S1: Obtain user recording data; extract features from the user recording data, build a feature database, and generate a voice feature database;

[0068] Step S2: acquiring real-time user voice data; performing similarity matching between the real-time user voice data and the voice feature database to generate user audio judgment result data; the control center component generates a control instruction strategy based on the user audio judgment result data to generate an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center;

[0069] Step S3: The sub-control center monitors the electrical equipment in real time based on the electrical communication control strategy, and generates a real-time monitoring report for the sub-control center; the real-time monitoring report of the sub-control center is sent to the main control center through the data exchange network for monitoring report analysis, and a main control center electrical equipment monitoring report is generated;

[0070] Step S4: Perform visual analysis based on the electrical appliance monitoring report of the main control center to generate a visual electrical appliance communication report, thereby completing the electrical appliance communication control operation.

[0071] The beneficial effect of the present invention is that by constructing a multi-level voice feature database, accurate recognition and analysis of user voice is achieved, thereby significantly improving the intelligent level of electrical control. The user recording data is obtained and the features are extracted to form a detailed voice feature database, so that the system can capture the personalized features of the user's tone, voice tone, etc. This multi-dimensional feature capture lays a solid foundation for subsequent similarity matching. By performing similarity matching between real-time user voice data and the voice feature database, user audio judgment result data is generated, ensuring accurate recognition and timely response of instructions. This precise matching mechanism can effectively distinguish between the user's real-time voice and recording, thereby generating corresponding electrical communication control strategies for different situations, and improving the flexibility and adaptability of the system. The sub-control center performs real-time monitoring according to the electrical communication control strategy, generates a detailed monitoring report, and sends the report to the main control center for analysis through the data exchange network. This process not only realizes efficient data transmission, but also provides data support for real-time monitoring, so that the status of electrical equipment can be fed back to the control center component in a timely manner, enhancing the real-time performance and response speed of the system. The main control center conducts visual analysis of the monitoring report and generates an intuitive visual electrical appliance communication report, which facilitates users and managers to quickly understand the system operation status and make corresponding decisions. Therefore, the present invention solves the problems of insufficient understanding of user voice and delayed response in traditional electrical appliance control methods by constructing an intelligent recognition system based on multi-level features, thereby improving the intelligent level of electrical appliance control and the convenience of operation.

[0072] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of an electrical appliance communication control method of the present invention. In this example, the electrical appliance communication control method includes the following steps:

[0073] Step S1: Obtain user recording data; extract features from the user recording data, build a feature database, and generate a voice feature database;

[0074] In the embodiment of the present invention, a high-fidelity microphone system is used to realize real-time recording of user voices and generate original audio signals. These original signals are digitized by an analog-to-digital converter (ADC) to form digital audio files that can be used for subsequent analysis. In the feature extraction stage, audio signal processing algorithms are applied, including technologies such as short-time Fourier transform (STFT) and Mel-frequency cepstral coefficients (MFCC) to analyze the characteristics of audio signals in the time and frequency domains. These technologies can effectively capture key features in speech, such as pitch, intensity, rhythm and other audio attributes, thereby laying the foundation for subsequent speech recognition and analysis. During the feature extraction process, the generated feature vectors will be stored in a speech feature database. This database not only records the values ​​of various audio features, but also contains contextual information related to each feature, forming a multi-dimensional data structure for subsequent query and analysis. Through such a data storage structure, efficient data retrieval and fast matching can be achieved, and the response speed and accuracy of the speech recognition system can be improved. In addition, the construction of the feature database requires the use of data mining technology. By analyzing historical recording data, representative features are extracted so that the database can adapt to the speech characteristics of different users.

[0075] Step S2: acquiring real-time user voice data; performing similarity matching between the real-time user voice data and the voice feature database to generate user audio judgment result data; the control center component generates a control instruction strategy based on the user audio judgment result data to generate an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center;

[0076] In the embodiment of the present invention, the technical means for obtaining real-time user voice data mainly rely on audio signal processing and real-time data transmission technology. The user's real-time voice is collected by a high-precision microphone, and then the analog-to-digital conversion (ADC) is performed through the digital signal processing module to convert the analog audio signal into a digital signal. These digitized audio data are sent to the feature extraction module, and the audio features are extracted from them by applying algorithms such as short-time Fourier transform (STFT) or Mel frequency cepstral coefficient (MFCC). This process not only ensures the high-quality capture of audio data, but also effectively reduces the impact of noise and improves the identifiability of features. After the feature extraction is completed, the real-time user voice data will be matched with the previously constructed voice feature database for similarity. This process involves a variety of matching algorithms, such as dynamic time warping (DTW) and cosine similarity, etc., through which the similarity between real-time voice features and existing features in the database is calculated. The result of the similarity matching will generate user audio judgment result data, which not only contains the success or failure of the audio matching, but also provides matching accuracy information. The control center component generates a control instruction strategy based on the user audio judgment result data, and this process is achieved through a complex decision algorithm. For example, the control center component can use machine learning algorithms (such as support vector machines or decision trees) to analyze the user's voice input to generate an appliance communication control strategy. The generation process of this strategy also needs to consider contextual information, the user's historical voice data and their preferences to ensure that the strategy is personalized and intelligent. The control center components are divided into a main control center and a sub-control center. The main control center is responsible for comprehensive processing of user audio judgment results, while the sub-control center specifically executes control instructions.

[0077] Step S3: The sub-control center monitors the electrical equipment in real time based on the electrical communication control strategy, and generates a real-time monitoring report for the sub-control center; the real-time monitoring report of the sub-control center is sent to the main control center through the data exchange network for monitoring report analysis, and a main control center electrical equipment monitoring report is generated;

[0078] In the embodiment of the present invention, the specific technical means for the sub-control center to implement real-time monitoring for the electrical communication control strategy involves multi-level data collection, processing and transmission processes. The sub-control center collects the operating data of electrical equipment in real time through built-in sensors and Internet of Things devices, including key parameters such as power, temperature, and working status. These data are transmitted to the sub-control center through a wireless network or a wired network to ensure the timeliness and accuracy of the data. The data acquisition module adopts high-frequency sampling technology to obtain real-time dynamic information, thereby improving the timeliness of the monitoring data. Once the data is collected, the sub-control center uses a data processing algorithm to clean and extract features from the raw data in order to generate a sub-control center real-time monitoring report that is easy to analyze. This process uses a time series analysis method combined with a trend prediction algorithm (such as an ARIMA model) to identify abnormal patterns and potential faults in the operation of the equipment. This data-driven monitoring method not only improves the accuracy of the report, but also provides a reliable basis for subsequent decision-making. The generated sub-control center real-time monitoring report is then sent to the main control center through a data exchange network. At this stage, the design and implementation of the data exchange network is crucial, and advanced communication protocols (such as MQTT or HTTP / 2) are used to ensure fast and secure data transmission. Network-level optimization (such as data compression and encryption technology) is also extremely important to ensure the integrity and confidentiality of data during transmission. After receiving the monitoring report, the main control center uses data analysis tools and visualization technology to conduct in-depth analysis to generate the main control center electrical appliance monitoring report.

[0079] Step S4: Perform visual analysis based on the electrical appliance monitoring report of the main control center to generate a visual electrical appliance communication report, thereby completing the electrical appliance communication control operation.

[0080] In the embodiment of the present invention, the specific technical means for visual analysis based on the electrical appliance monitoring report of the main control center involves multiple data processing and analysis steps, aiming to convert complex electrical appliance monitoring data into information that is easy to understand and make decisions. First, after receiving the electrical appliance monitoring report, the main control center uses data preprocessing technology to clean and normalize the raw data in the report to ensure the consistency and accuracy of the data. Common technical means include missing value filling, outlier detection and standardization, which help to improve the quality of the data and make it suitable for subsequent analysis. The main control center uses data visualization tools (such as Tableau, Power BI or custom visualization libraries) to visualize the processed data. In this process, a variety of graphical display methods (such as line charts, bar charts, heat maps, etc.) are used to represent the operating status, energy consumption trends and fault detection results of electrical appliances. Through visualization, users can intuitively observe the changes in electrical appliance performance, identify potential abnormal behaviors and fault modes, and then support more scientific decision-making. The main control center also uses advanced data analysis technologies, such as machine learning and statistical models, to generate prediction models to predict the future status of electrical appliances. Through time series analysis and regression models, the system can identify trends and cyclical changes in historical data and provide future performance estimates for appliance use. This process not only enhances the depth of the visual report, but also makes the report forward-looking. The generated visual appliance communication report not only contains static monitoring results, but also combines dynamic prediction information to provide comprehensive support for appliance communication control operations.

[0081] Preferably, step S1 comprises the following steps:

[0082] Step S11: segment the user recording data into phrases and words, and segment the user's voice data;

[0083] Step S12: extracting speech features from the user speech segmentation data using a speech signal processing algorithm to generate user speech feature data, wherein the user speech feature data includes pitch feature data and tone feature data;

[0084] Step S13: constructing a database based on the user's voice feature data to generate a voice feature database.

[0085] In the embodiment of the present invention, the user recording data is segmented into phrases and words. This process uses a voice activity detection (VAD) algorithm to automatically identify valid voice segments in the recording and separate them from silent segments. By dividing the user voice data into different phrases or words, the information in the voice can be captured more accurately, and the accuracy of subsequent feature extraction can be improved. For the segmented user voice data, a voice signal processing algorithm is used to extract features to generate user voice feature data including pitch feature data and tone feature data. This process involves multiple technical means, such as linear predictive coding (LPC), Mel frequency cepstral coefficients (MFCC) and short-time Fourier transform (STFT). These algorithms can extract multidimensional feature information related to the voice signal, thereby capturing key information such as the pitch, timbre, sound intensity and intonation of the sound. The pitch feature data provides the frequency characteristics of the voice signal, while the tone feature data can reflect the speaker's emotions and attitudes. The two together constitute the user's voice features. Based on the voice feature data extracted by the user, a voice feature database is constructed. This process requires the use of a database management system (DBMS) for effective data storage and management. The feature database must not only consider the structured storage of data, but also ensure the fast access and query capabilities of the data. When building a database, the use of indexing technology can improve data retrieval efficiency, and at the same time, feature data can be organized through appropriate data models (such as relational models or document models) to facilitate subsequent speech recognition and processing tasks. The resulting speech feature database provides strong data support for subsequent user recognition, command recognition, and personalized interaction.

[0086] Preferably, step S13 includes the following steps:

[0087] Step S131: obtaining control instructions; performing K-means clustering on the user's voice feature data to generate voice benchmark data;

[0088] Step S132: habitually associating the voice reference data with the control command to generate user personalized command data;

[0089] Step S133: constructing a first-level database using the tone feature data to generate a user basic voice database; sorting the tone feature data into a vector feature matrix and constructing a second-level database to generate a user tone feature database; storing the user personalized instruction data in a third-level database to generate a tone instruction matching database;

[0090] Step S134: The user basic voice database, the user tone feature database and the tone instruction matching database are stored and constructed according to a multi-layer structure database to generate a voice feature database.

[0091] In an embodiment of the present invention, user voice feature data is processed by a K-means clustering algorithm. This algorithm divides voice feature data into several clusters to find the intrinsic relationship between features, thereby generating voice benchmark data. K-means clustering uses the method of minimizing the distance from the sample point to the cluster to achieve data grouping, which can effectively identify the voice features of users in different contexts and form a preliminary personalized instruction basis. The voice benchmark data is habitually associated with the control instructions, and the control instructions commonly used by users in specific contexts are identified by association rule learning (such as the Apriori algorithm or the FP-Growth algorithm). This process can generate personalized instruction data based on the user's historical behavior, enhance the system's adaptability to user preferences, and improve the accuracy and response speed of instruction execution. The technical means mainly involve the construction of a multi-level database. By processing the tone feature data, a user basic voice database is generated, which is based on feature extraction techniques such as LPC and MFCC to capture the spectral features of the sound. In addition, the tone feature data is sorted by vector feature matrix to achieve the construction of a second-level database. This process uses principal component analysis (PCA) or linear discriminant analysis (LDA) to reduce dimensions and optimize features to ensure the effectiveness and availability of tone features. Finally, the user's personalized instruction data is stored in the third-level database to form a tone instruction matching database, which is used to efficiently retrieve and match the user's personalized instructions. Through multi-layer database storage technology, the user's basic voice database, user tone feature database, and tone instruction matching database are integrated to generate a complete voice feature database.

[0092] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0093] Step S21: acquiring real-time user voice data; performing similarity matching between the real-time user voice data and the voice feature database to generate voice similarity data;

[0094] Step S22: Performing audio signal recording judgment on the voice similarity data to generate user audio judgment result data, wherein the user audio judgment result data includes recording status data and real-time recording data;

[0095] Step S23: The control center component generates a control instruction strategy based on the voice similarity data to generate an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center.

[0096] In the embodiment of the present invention, the process of acquiring real-time user voice data depends on audio acquisition equipment (such as microphones) and digital signal processing technology. These technologies ensure high-quality capture of audio data, and then the real-time voice data is processed by feature extraction algorithms (such as Mel-frequency cepstral coefficients MFCC) to extract its feature vectors. Subsequently, these feature vectors will be matched with the constructed voice feature database for similarity. At this time, the commonly used similarity calculation methods include cosine similarity or Euclidean distance, which helps to generate voice similarity data, thereby reflecting the degree of match between the real-time voice data and various samples in the database. The process of judging the recording of audio signals based on voice similarity data involves a series of signal processing technologies. By setting predetermined thresholds and conditions, the system can distinguish the user's recording status (such as recording status data) from real-time voice data. This step involves time domain analysis and frequency domain analysis to evaluate the integrity and quality of the voice signal, thereby generating user audio judgment result data. The control center component uses the user audio judgment result data and voice similarity data to generate an electrical communication control strategy. This process relies on machine learning algorithms (such as decision trees or support vector machines) to process the input data and formulate corresponding control instruction strategies based on the similarity and judgment results. The implementation of control strategy generation includes the application of rule engines to effectively distribute tasks between the main control center and sub-control centers and ensure the correct transmission of instructions.

[0097] Preferably, step S22 includes the following steps:

[0098] Step S221: Calculate the recording duration of the voice similarity data based on a preset recording duration threshold, remove abnormal data, and generate normal recording duration data of the user;

[0099] Step S222: Perform time domain fluctuation stability detection based on the normal duration data of the user recording to generate user time domain fluctuation detection data; perform spectrum analysis on the user time domain fluctuation detection data using Fourier transform to generate user spectrum detection data; perform background low-frequency noise detection on the user spectrum detection data, and perform echo and reflection detection processing using phase difference analysis to generate user voice detection data;

[0100] Step S223: using the voice feature database as reference data to perform audio signal recording judgment on the user voice detection data, and generating user audio judgment result data, wherein the user audio judgment result data includes recording status data and real-time recording data.

[0101] In the embodiment of the present invention, the voice similarity data is analyzed according to the preset recording duration threshold, and the recording duration is evaluated by programming logic to determine whether it meets the set standard. The elimination of abnormal data mainly relies on statistical methods. By defining the upper and lower limits to screen the recording data of normal duration, this process can effectively improve the accuracy and effectiveness of subsequent analysis, thereby generating the normal duration data of user recording. Time domain fluctuation stability detection is performed on the normal duration data of user recording. The technical means used include time domain analysis methods, such as the root mean square (RMS) value calculation of the signal, which helps to identify the stability of the audio signal. Subsequently, the time domain signal is converted to the frequency domain by Fourier transform for spectrum analysis. This process enables the system to identify the frequency components and their intensity distribution in the audio signal, and then generate user spectrum detection data. At the same time, the detection of background low-frequency noise involves the use of noise threshold technology, which filters the frequencies below this threshold by setting a threshold, thereby reducing the interference of background noise on the voice signal. The technical means of echo and reflection detection using phase difference analysis also play a role in this step, and the reflection and echo phenomena of the sound are identified by measuring the phase difference of the signal. These steps are combined to form user voice detection data, which covers the status information of various audio signals. The system uses the voice feature database as a benchmark and audio signal recording judgment technology to classify and match the user voice detection data. This process uses machine learning algorithms, such as support vector machines (SVM) or neural networks, to determine the user's audio status and generate user audio judgment result data. This result data includes recording status data and real-time recording data to ensure that the system can accurately feedback the user's audio input status.

[0102] Preferably, step S23 includes the following steps:

[0103] Step S231: the control center component generates a control instruction strategy based on the user audio judgment result data, and generates an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center, and the electrical appliance communication control strategy includes a recording electrical appliance communication control strategy and a real-time voice electrical appliance communication strategy;

[0104] Step S232: When the user audio judgment result is recording status data, the real-time user voice data is recorded and marked to generate user recording mark data; the central control center generates a control instruction for the user recording mark data based on the voice feature database to generate a master recording control instruction; the master recording control instruction is transmitted to the sub-control center through a preset transmission protocol to generate a sub-control recording control instruction; the sub-control center issues a recording instruction to the electrical appliance based on the sub-control recording control instruction, and terminates the execution program of the electrical appliance, thereby completing the recording electrical appliance communication control strategy;

[0105] Step S233: When the user audio judgment result is real-time recording data, a strict voice match is performed on the real-time user voice data and the voice feature database to generate real-time user voice strict matching data; the main control center uses a preset multi-dimensional decision tree to predict user instructions for the real-time user voice strict matching data to generate a main control candidate control instruction; the main control candidate control instruction is sent to the sub-control center through a preset transmission protocol to generate a sub-control candidate control instruction; the electrical appliance is executed based on the sub-control candidate control instruction, and sub-control feedback execution data is generated; the main control center optimizes the evaluation instruction of the multi-dimensional decision tree based on the sub-control feedback execution data, generates a personalized multi-dimensional decision tree, and iterates the preset multi-dimensional decision tree, thereby completing the real-time voice electrical appliance communication strategy.

[0106] In the embodiment of the present invention, the control center component uses the user audio judgment result data to generate the control instruction strategy, and this process mainly relies on pattern recognition and machine learning technology. By analyzing the user's audio input, the system can identify its intention, thereby generating a targeted electrical appliance communication control strategy, which includes a recording electrical appliance communication control strategy and a real-time voice electrical appliance communication strategy. The process of generating this strategy combines machine learning algorithms such as decision trees and support vector machines to ensure the accuracy and effectiveness of the generated instructions. When the judgment result is a recording state, the system will mark the real-time user voice data and generate user recording mark data. This marking process uses a timestamp-based recording method to ensure that the user's audio input is accurately captured. The main control center generates a main control recording control instruction for the user recording mark data based on the voice feature database, and transmits it to the sub-control center through a preset transmission protocol. This process needs to ensure the integrity and reliability of data transmission. Common technologies include data packet verification and encrypted transmission. After receiving the main control recording control instruction, the sub-control center will issue the recording instruction to the electrical appliance based on these instructions and terminate the execution program of the electrical appliance. This involves the control and response mechanism of the real-time data flow, and needs to cooperate with a microcontroller or embedded system to achieve precise control. When the user audio judgment result is real-time recording data, the system will perform strict voice matching on the real-time user voice data to generate real-time user voice strict matching data. This process uses the dynamic time warping (DTW) algorithm to ensure that the real-time data is accurately compared with the data in the feature database. Based on this data, the main control center uses the preset multidimensional decision tree to predict user commands and generate master control candidate control commands. The multidimensional decision tree construction process here involves multivariate statistical analysis and machine learning to capture the user's diverse command patterns. The master control candidate control command is sent to the sub-control center through a preset transmission protocol. Subsequently, the sub-control center executes the electrical operation according to the command and generates sub-control feedback execution data.

[0107] Preferably, performing strict voice matching on the real-time user voice data and the voice feature database comprises the following steps:

[0108] The user basic voice database and real-time user voice data are calculated and processed according to the dynamic time warping algorithm to generate user voice dynamic calculation data;

[0109] According to the real-time user voice data, the user tone feature database is sorted into a vector feature matrix, and tone feature vector matching is performed to generate user tone vector matching data;

[0110] Perform context association based on real-time user voice data and tone command matching database to generate user tone command data;

[0111] The three-dimensional database is fused based on the user voice dynamic calculation data, the user voice vector matching data and the user voice command data to generate real-time user voice strict matching data.

[0112] In the embodiment of the present invention, the user basic voice database and the real-time user voice data are calculated and processed according to the dynamic time warping algorithm. The core of this process is to compare the similarity of different voice signals through nonlinear time alignment, so as to generate user voice dynamic calculation data. The DTW algorithm dynamically adjusts the time series signal so that the similarity of two voice segments can be effectively compared even at different speech speeds, which is crucial for real-time speech recognition and processing. Using real-time user voice data to sort the vector feature matrix of the user voice feature database is a multidimensional data analysis process. In this step, the real-time user voice data is converted into a vector representation through a feature extraction algorithm. These features include information such as pitch, speech speed and stress. Then, these vector features are matched with the existing voice features, and the user voice vector matching data is generated by calculating the similarity. This process uses cosine similarity or Euclidean distance and other metrics to ensure the accuracy and reliability of the matching. The user voice command data is generated by context association based on the real-time user voice data and the voice command matching database. This link relies on contextual understanding technology, such as semantic analysis and syntactic analysis in natural language processing, in order to extract effective tone instructions from the voice information input by the user. This includes not only the understanding of the voice signal itself, but also the inference of the user's intention, so as to generate more accurate control instructions. According to the user's voice dynamic calculation data, the user's tone vector matching data and the user's tone instruction data, a three-dimensional database fusion is performed to generate real-time user voice strict matching data. This process involves multi-level data fusion technology, using weighted average, principal component analysis (PCA) or deep learning models to integrate data from different sources to achieve a high degree of information integration and analysis.

[0113] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0114] Step S31: the sub-control center performs real-time monitoring of electrical equipment based on the electrical communication control strategy, and generates electrical equipment monitoring data of the sub-control center; generates an institutionalized report of the electrical equipment monitoring data of the sub-control center, and generates a real-time monitoring report of the sub-control center;

[0115] Step S32: Send the sub-control center real-time monitoring report to the main control center through the data exchange network, verify the file integrity, and generate a main control center verification electrical appliance monitoring report;

[0116] Step S33: Analyze the monitoring report of the main control center's electrical appliance verification report to generate a main control center electrical appliance monitoring report.

[0117] In an embodiment of the present invention, the sub-control center performs real-time monitoring of electrical equipment based on the electrical communication control strategy. This process relies on the application of Internet of Things (IoT) technology and sensor networks. The sensor collects data such as the working status, energy consumption and fault information of the electrical appliances, and performs preliminary processing of the real-time monitoring data through edge computing to generate electrical appliance monitoring data of the sub-control center. These data not only provide the real-time operating status of the electrical appliances, but also provide a basis for subsequent data analysis and decision-making. In the process of generating the real-time monitoring report of the sub-control center, the structured report generation technology is used to convert the monitoring data into structured information for easy storage, analysis and display. This step involves data formatting and data visualization technology, and presents the electrical appliance monitoring data in the form of charts, dashboards, etc., to improve the readability of the information and decision support capabilities. The real-time monitoring report of the sub-control center is sent to the main control center through the data exchange network. In this process, a data transmission protocol (such as MQTT, HTTP or WebSocket) is used to ensure the secure transmission of data between different systems. At the same time, the integrity of the file is verified to ensure that the data has not been tampered with or damaged during the transmission process, and a hash algorithm (such as SHA-256) is used to verify the data integrity to generate a verification electrical appliance monitoring report for the main control center. The monitoring report of the main control center calibration electrical appliance monitoring report is analyzed to generate the main control center electrical appliance monitoring report. This analysis process uses data mining technology and statistical analysis methods to identify abnormal patterns and trends by comparing historical data and real-time data, providing a basis for the maintenance and optimization of electrical equipment.

[0118] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0119] Step S41: construct a report based on the time series dimension of the main control center electrical appliance monitoring report to generate a main control center time dimension report; construct a report based on the equipment type dimension of the main control center electrical appliance monitoring report to generate a main control center equipment dimension report; construct a report based on the operation status dimension of the main control center electrical appliance monitoring report to generate a main control center operation dimension report;

[0120] Step S42: The time dimension report of the main control center, the equipment dimension report of the main control center and the operation dimension report of the main control center are integrated into a multi-dimensional form to generate a visualized electrical appliance communication report;

[0121] Step S43: Upload the visualized electrical appliance communication report to a preset cloud platform through a data exchange network to make the electrical appliance communication control report public, thereby completing the electrical appliance communication control operation.

[0122] In an embodiment of the present invention, a time series dimension is constructed based on the electrical appliance monitoring report of the main control center. This process uses time series analysis technology, uses statistical methods (such as autoregressive moving average model ARIMA) to perform time series analysis on the monitoring data, identifies the trend and periodicity of data changes over time, and generates a time dimension report of the main control center. In addition, by classifying the electrical appliance monitoring data, combining the equipment type and operating status, a multidimensional database design (such as OLAP technology) is used to construct an equipment type dimension report and an operating status dimension report. This process ensures the availability and interpretability of the monitoring data in a multidimensional space, so that data of various types of equipment and status can be efficiently queried and analyzed. The multiple dimensional reports of the main control center are integrated to generate a visualized electrical appliance communication report, and data integration and processing technologies, such as ETL (extraction, transformation, loading) processes, are used to integrate data sources of different dimensions. By using data visualization tools (such as Tableau, Power BI, etc.), the integrated data is converted into charts, graphs or dashboards, so that users can intuitively understand the monitoring results and equipment performance. This process not only improves the readability of the data, but also enhances the decision support capability. The generated visual electrical communication report is uploaded to the preset cloud platform through the data exchange network. This process uses data transmission protocols (such as HTTP / HTTPS or FTP) for secure network data transmission, and uses API interfaces to interact with the cloud platform to ensure that the report can be accessed and made public in real time.

[0123] In this specification, an electrical appliance communication control system is provided, which is used to execute the above-mentioned electrical appliance communication control method. The electrical appliance communication control system:

[0124] Data collection module: used to obtain user recording data; extract features from user recording data, build a feature database, and generate a voice feature database;

[0125] Real-time recognition module: used to obtain real-time user voice data; perform similarity matching between real-time user voice data and voice feature database to generate user audio judgment result data; the control center component generates control instruction strategy based on user audio judgment result data and generates electrical appliance communication control strategy, wherein the control center component includes main control center and sub-control center;

[0126] Monitoring and reporting module: used by the sub-control center to monitor electrical equipment in real time based on the electrical communication control strategy and generate real-time monitoring reports for the sub-control center; the real-time monitoring reports of the sub-control center are sent to the main control center through the data exchange network for monitoring report analysis and to generate electrical equipment monitoring reports for the main control center;

[0127] Visual analysis module: used to perform visual analysis based on the electrical appliance monitoring report of the main control center, generate a visual electrical appliance communication report, and thus complete the electrical appliance communication control operation.

[0128] The beneficial effect of the present invention is that by constructing a multi-level voice feature database, accurate recognition and analysis of user voice is achieved, thereby significantly improving the intelligent level of electrical control. The user recording data is obtained and the features are extracted to form a detailed voice feature database, so that the system can capture the personalized features of the user's tone, voice tone, etc. This multi-dimensional feature capture lays a solid foundation for subsequent similarity matching. By performing similarity matching between real-time user voice data and the voice feature database, user audio judgment result data is generated, ensuring accurate recognition and timely response of instructions. This precise matching mechanism can effectively distinguish between the user's real-time voice and recording, thereby generating corresponding electrical communication control strategies for different situations, and improving the flexibility and adaptability of the system. The sub-control center performs real-time monitoring according to the electrical communication control strategy, generates a detailed monitoring report, and sends the report to the main control center for analysis through the data exchange network. This process not only realizes efficient data transmission, but also provides data support for real-time monitoring, so that the status of electrical equipment can be fed back to the control center component in a timely manner, enhancing the real-time performance and response speed of the system. The main control center conducts visual analysis of the monitoring report and generates an intuitive visual electrical appliance communication report, which facilitates users and managers to quickly understand the system operation status and make corresponding decisions. Therefore, the present invention solves the problems of insufficient understanding of user voice and delayed response in traditional electrical appliance control methods by constructing an intelligent recognition system based on multi-level features, thereby improving the intelligent level of electrical appliance control and the convenience of operation.

[0129] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0130] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An electrical appliance communication control method, characterized in that: The following steps are involved: Step S1: Obtain user recording data; extract features from the user recording data, build a feature database, and generate a voice feature database; Step S2: acquiring real-time user voice data; performing similarity matching between the real-time user voice data and the voice feature database to generate user audio judgment result data; the control center component generates a control instruction strategy based on the user audio judgment result data to generate an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center; Step S3: The sub-control center monitors the electrical equipment in real time based on the electrical communication control strategy, and generates a real-time monitoring report for the sub-control center; the real-time monitoring report of the sub-control center is sent to the main control center through the data exchange network for monitoring report analysis, and a main control center electrical equipment monitoring report is generated; Step S4: Perform visual analysis based on the electrical appliance monitoring report of the main control center to generate a visual electrical appliance communication report, thereby completing the electrical appliance communication control operation.

2. The electrical appliance communication control method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: segment the user recording data into phrases and words, and segment the user's voice data; Step S12: extracting speech features from the user speech segmentation data using a speech signal processing algorithm to generate user speech feature data, wherein the user speech feature data includes pitch feature data and tone feature data; Step S13: constructing a database based on the user's voice feature data to generate a voice feature database.

3. The electrical appliance communication control method according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: obtaining a control instruction; performing K-means clustering on the user's voice feature data to generate voice benchmark data; Step S132: habitually associating the voice reference data with the control command to generate user personalized command data; Step S133: constructing a first-level database using the tone feature data to generate a user basic voice database; sorting the tone feature data into a vector feature matrix and constructing a second-level database to generate a user tone feature database; storing the user personalized instruction data in a third-level database to generate a tone instruction matching database; Step S134: The user basic voice database, the user tone feature database and the tone instruction matching database are stored and constructed according to a multi-layer structure database to generate a voice feature database.

4. The electrical appliance communication control method according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: acquiring real-time user voice data; performing similarity matching between the real-time user voice data and the voice feature database to generate voice similarity data; Step S22: Performing audio signal recording judgment on the voice similarity data to generate user audio judgment result data, wherein the user audio judgment result data includes recording status data and real-time recording data; Step S23: The control center component generates a control instruction strategy based on the voice similarity data to generate an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center.

5. The electrical appliance communication control method according to claim 4, characterized in that: Step S22 includes the following steps: Step S221: Calculate the recording duration of the voice similarity data based on a preset recording duration threshold, remove abnormal data, and generate normal recording duration data of the user; Step S222: Perform time domain fluctuation stability detection based on the normal duration data of the user recording to generate user time domain fluctuation detection data; perform spectrum analysis on the user time domain fluctuation detection data using Fourier transform to generate user spectrum detection data; perform background low-frequency noise detection on the user spectrum detection data, and perform echo and reflection detection processing using phase difference analysis to generate user voice detection data; Step S223: using the voice feature database as reference data to perform audio signal recording judgment on the user voice detection data, and generating user audio judgment result data, wherein the user audio judgment result data includes recording status data and real-time recording data.

6. The electrical appliance communication control method according to claim 4, characterized in that: Step S23 includes the following steps: Step S231: the control center component generates a control instruction strategy based on the user audio judgment result data, and generates an electrical appliance communication control strategy, wherein the control center component includes a main control center and a sub-control center, and the electrical appliance communication control strategy includes a recording electrical appliance communication control strategy and a real-time voice electrical appliance communication strategy; Step S232: When the user audio judgment result is recording status data, the real-time user voice data is recorded and marked to generate user recording mark data; the central control center generates a control instruction for the user recording mark data based on the voice feature database to generate a master recording control instruction; the master recording control instruction is transmitted to the sub-control center through a preset transmission protocol to generate a sub-control recording control instruction; the sub-control center issues a recording instruction to the electrical appliance based on the sub-control recording control instruction, and terminates the execution program of the electrical appliance, thereby completing the recording electrical appliance communication control strategy; Step S233: When the user audio judgment result is real-time recording data, a strict voice match is performed on the real-time user voice data and the voice feature database to generate real-time user voice strict matching data; the main control center uses a preset multi-dimensional decision tree to predict user instructions for the real-time user voice strict matching data to generate a main control candidate control instruction; the main control candidate control instruction is sent to the sub-control center through a preset transmission protocol to generate a sub-control candidate control instruction; the electrical appliance is executed based on the sub-control candidate control instruction, and sub-control feedback execution data is generated; the main control center optimizes the evaluation instruction of the multi-dimensional decision tree based on the sub-control feedback execution data, generates a personalized multi-dimensional decision tree, and iterates the preset multi-dimensional decision tree, thereby completing the real-time voice electrical appliance communication strategy.

7. The electrical appliance communication control method according to claim 6, characterized in that: The strict voice matching of real-time user voice data and voice feature database includes the following steps: The user basic voice database and real-time user voice data are calculated and processed according to the dynamic time warping algorithm to generate user voice dynamic calculation data; According to the real-time user voice data, the user tone feature database is sorted into a vector feature matrix, and tone feature vector matching is performed to generate user tone vector matching data; Perform context association based on real-time user voice data and tone command matching database to generate user tone command data; The three-dimensional database is fused based on the user voice dynamic calculation data, the user voice vector matching data and the user voice command data to generate real-time user voice strict matching data.

8. The electrical appliance communication control method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: the sub-control center performs real-time monitoring of electrical equipment based on the electrical communication control strategy, and generates electrical equipment monitoring data of the sub-control center; generates an institutionalized report of the electrical equipment monitoring data of the sub-control center, and generates a real-time monitoring report of the sub-control center; Step S32: sending the sub-control center real-time monitoring report to the main control center through the data exchange network, verifying the integrity of the file, and generating a main control center verification electrical appliance monitoring report; Step S33: Analyze the monitoring report of the main control center's electrical appliance verification report to generate a main control center electrical appliance monitoring report.

9. The electrical appliance communication control method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: construct a report based on the time series dimension of the main control center electrical appliance monitoring report to generate a main control center time dimension report; construct a report based on the equipment type dimension of the main control center electrical appliance monitoring report to generate a main control center equipment dimension report; construct a report based on the operation status dimension of the main control center electrical appliance monitoring report to generate a main control center operation dimension report; Step S42: The time dimension report of the main control center, the equipment dimension report of the main control center and the operation dimension report of the main control center are integrated into a multi-dimensional form to generate a visualized electrical appliance communication report; Step S43: Upload the visualized electrical appliance communication report to a preset cloud platform through a data exchange network to make the electrical appliance communication control report public, thereby completing the electrical appliance communication control operation.

10. An electrical appliance communication control system, characterized in that: A control center component is included for executing the electrical appliance communication control method according to claim 1, and the electrical appliance communication control system includes: Data collection module: used to obtain user recording data; extract features from user recording data, build a feature database, and generate a voice feature database; Real-time recognition module: used to obtain real-time user voice data; perform similarity matching between real-time user voice data and voice feature database to generate user audio judgment result data; the control center component generates control instruction strategy based on user audio judgment result data and generates electrical appliance communication control strategy, wherein the control center component includes main control center and sub-control center; Monitoring and reporting module: used by the sub-control center to monitor electrical equipment in real time based on the electrical communication control strategy and generate real-time monitoring reports for the sub-control center; the real-time monitoring reports of the sub-control center are sent to the main control center through the data exchange network for monitoring report analysis and to generate electrical equipment monitoring reports for the main control center; Visual analysis module: used to perform visual analysis based on the electrical appliance monitoring report of the main control center, generate a visual electrical appliance communication report, and thus complete the electrical appliance communication control operation.

Images