Information query method and system based on Internet of Things

Abstract

The invention provides an information query method and system based on the Internet of Things, and belongs to the field of information query of the Internet of Things, and the method comprises the following steps: S1, receiving multi-modal query input, and converting the multi-modal query input into structured query representation; s2, performing credibility evaluation on the Internet of Things data by adopting an improved data credibility evaluation algorithm to obtain a credibility score of each data item; s3, performing complexity calculation on the structured query representation based on a nonlinear evaluation model to obtain a query complexity score; s4, determining a query execution strategy according to the query complexity score and the Internet of Things resource state; s5, executing information query according to the query execution strategy to obtain an initial query result; and S6, performing fusion processing on the query result based on the credibility score to obtain a final information query result. According to the method, self-adaptive processing and quality optimization of information query in the Internet of Things environment are realized, and the optimal execution strategy can be dynamically selected according to the query complexity and the resource state.

Description

Technical Field

[0001] The present invention relates to the technical field of information query technology of the Internet of Things, and in particular to an information query method and system based on the Internet of Things. Background Art

[0002] The Internet of Things (IoT), a crucial component of next-generation information technology, is a network that connects any object to the internet through various information sensing devices, such as radio frequency identification (RFID), infrared sensors, global positioning systems, and laser scanners, according to agreed protocols, enabling information exchange and communication. This enables intelligent identification, location, tracking, monitoring, and management. IoT-based information querying utilizes the IoT architecture to extract, process, and present valuable information based on user needs from massive amounts of distributed, heterogeneous physical world sensor data. This type of query differs from traditional internet information querying in that its data source is more real-time, dynamic, and directly connected to the physical world. With the widespread adoption of IoT applications, efficiently, accurately, and intelligently extracting the required information from IoT big data has become a key technical challenge.

[0003] Existing IoT information query technologies primarily utilize a cloud-based centralized processing architecture. User query requests are transmitted over the network to cloud servers, which retrieve relevant information from databases and return the results. To improve efficiency, some utilize technologies such as data indexing, caching, and distributed storage. Regarding query understanding, most technologies only support keyword matching and simple structured query languages, limiting their ability to understand complex query intent. Regarding data security, existing technologies primarily rely on transmission encryption and access control, leaving behind relatively simple authentication of data sources and assessment of the credibility of data content.

[0004] Chinese invention patent application number 202411081388.2 discloses an IoT data processing method, system, and computer-readable storage medium. Based on a data credibility assessment algorithm component library, the method implements IoT data content analysis and identity recognition, blocks abnormal information, and enhances IoT information security protection capabilities. However, the method fails to take into account the complexity of multimodal query input in modern IoT environments and can only process structured data queries, failing to meet the increasingly complex intelligent query and analysis needs in modern IoT applications. Summary of the Invention

[0005] The present invention provides an information query method and system based on the Internet of Things, which are used to solve the defect of the existing technology that multimodal query cannot be performed, and realize adaptive processing and quality optimization of information query in the Internet of Things environment.

[0006] The present invention provides an information query method based on the Internet of Things, comprising: S1. Receive a multimodal query input and convert the multimodal query input into a structured query representation; S2. Use the improved data credibility assessment algorithm to conduct credibility assessment on IoT data and obtain the credibility score of each data item; S3. performing complexity calculation on the structured query representation based on a nonlinear evaluation model to obtain a query complexity score; S4. Determine a query execution strategy based on the query complexity score and IoT resource status; S5. Execute information query according to the query execution strategy to obtain initial query results; S6. Perform fusion processing on the query results based on the credibility score to obtain a final information query result.

[0007] According to an information query method based on the Internet of Things provided by the present invention, the structured query representation adopts a quintuple structure, including a query subject, a time constraint, a space constraint, context information, and a data credibility requirement.

[0008] According to an information query method based on the Internet of Things provided by the present invention, the improved data credibility assessment algorithm includes a feature extraction module, a feature learning module, a scoring module, an information verification module and an analysis module.

[0009] According to an information query method based on the Internet of Things provided by the present invention, step S2 specifically includes: Use the feature extraction module to extract features from IoT data to obtain device hardware fingerprint features, network behavior features, and data content features; The device hardware fingerprint features, network behavior features and data content features are encoded and decoded into feature vectors using a feature learning module to obtain data potential representation and reconstruction error; The scoring module calculates an initial credibility score based on the data potential representation and reconstruction error; Obtain external verification information and use the information verification module to calculate the external verification information to obtain the cross-validation strength; Obtain IoT historical data and use the analysis module to analyze the historical data to obtain a temporal consistency score; The confidence score is calculated based on the initial confidence score, the cross-validation strength and the temporal consistency score.

[0010] According to an information query method based on the Internet of Things provided by the present invention, the calculation formula of the credibility score is: ; in, Represents a data item The credibility score of represents the i-th IoT data item to be evaluated, represents the index of the evaluation dimension, represents the total number of evaluation dimensions, represents the weight coefficient of the j-th evaluation dimension, Represents a data item The basic credibility score on the j-th evaluation dimension, represents the sensitivity parameter of cross validation, Represents a data item The cross-validation strength, represents the threshold parameter of cross validation, Represents the normalized information entropy function.

[0011] According to an information query method based on the Internet of Things provided by the present invention, the nonlinear evaluation model includes a query parsing module, a complexity calculation module, an analysis module and a comprehensive scoring module, wherein: The query parsing module is used to parse the structured query representation and extract basic factors, wherein the basic factors include the number of entities, relationship complexity, time span and spatial range; The complexity calculation module is used to perform nonlinear transformation on the basic factors and calculate the basic complexity; The analysis module is used to construct a query semantic network and calculate the mutual information and degree centrality of the semantic relationship based on the query semantic network; The comprehensive scoring module is used to fuse the basic complexity and the semantic network complexity to obtain the final complexity score.

[0012] According to an information query method based on the Internet of Things provided by the present invention, the query execution strategy includes a local processing strategy, an edge collaborative processing strategy and a cloud processing strategy, wherein: The local processing strategy is used to complete query processing within a single edge node; The edge collaborative processing strategy is used to collaboratively complete query processing across multiple edge nodes; The cloud processing strategy is used to report the query to the cloud service layer for processing.

[0013] According to an information query method based on the Internet of Things provided by the present invention, step S4 specifically includes: Obtain computing resource status based on the local edge node's CPU utilization, memory usage, remaining storage space, and network bandwidth usage. Evaluate data completeness by using structured queries to represent local availability, integrity, and timeliness. Set the first complexity threshold and the second complexity threshold based on the processing capacity of the local edge node and historical query statistics, where the first complexity threshold corresponds to the upper limit of queries that can be processed independently by local resources, and the second complexity threshold corresponds to the upper limit of queries that can be processed collaboratively by the edge; Selecting a local processing strategy when the query complexity score is lower than a first complexity threshold and the local data completeness meets the query requirements; When the complexity score is greater than the first complexity threshold but less than the second complexity threshold or the local data is incomplete, the preset neighboring node status table is queried to obtain the processing capacity, data type and network connection quality information of the surrounding edge nodes, and the edge collaborative processing strategy is executed; When the complexity score is higher than the second complexity threshold or the combination of neighboring edge nodes still cannot meet the query requirements, the cloud processing strategy is selected.

[0014] According to an information query method based on the Internet of Things provided by the present invention, step S6 specifically includes: Performing deduplication processing on the initial query results to obtain a deduplication data item set; Matching the data in the deduplicated data item set with the structured query representation to obtain a relevance score for each data item; Calculate the similarity and difference between the data items in the deduplicated data item set to obtain the information evaluation result of each data item; Based on the credibility score, data integrity index and measurement accuracy index of each data item, a weight distribution algorithm is used to calculate the data quality weight of each data item; Calculate a timeliness discount factor for each data item based on the data generation time and the query time, and calculate the contribution of each data item to the query result based on the relevance score, the information evaluation result, the data quality weight, and the timeliness discount factor; Based on the credibility score and contribution of each data item, weighted fusion processing is used to obtain the final information query result.

[0015] The present invention also provides an information query system based on the Internet of Things, which implements the information query method described above, including: A query input module, configured to receive a multimodal query input and convert the multimodal query input into a structured query representation; The credibility assessment module is used to perform credibility assessment on IoT data using an improved data credibility assessment algorithm to obtain a credibility score for each data item; A complexity calculation module, configured to perform complexity calculation on the structured query representation based on a nonlinear evaluation model to obtain a query complexity score; An execution strategy determination module, configured to determine a query execution strategy based on the query complexity score and IoT resource status; An information query module, configured to execute information query according to the query execution strategy and obtain initial query results; The fusion module is used to fuse the query results based on the credibility score to obtain a final information query result.

[0016] The present invention provides an information query method and system based on the Internet of Things. Through multimodal query input, an improved data credibility assessment algorithm, a nonlinear complexity assessment model, intelligent execution strategy decision-making and credibility fusion processing, it realizes adaptive processing and quality optimization of information query in the Internet of Things environment. It can dynamically select the optimal execution strategy according to the query complexity and resource status, switch between local processing, edge collaborative processing and cloud processing, effectively balance the relationship between query response time, resource utilization efficiency and result quality, and significantly improve the overall performance and user experience of Internet of Things information query. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a flow chart of the information query method based on the Internet of Things provided by the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0020] like Figure 1 As shown, the present invention provides an information query method based on the Internet of Things, comprising the following steps: S1. Receive a multimodal query input, and convert the multimodal query input into a structured query representation, wherein the structured query representation adopts a five-tuple structure, including a query subject, a time constraint, a space constraint, context information, and a data credibility requirement.

[0021] It is understandable that when a user initiates a query request through a terminal device, the multimodal query understanding module first classifies and identifies different types of input and preprocesses them.

[0022] In one embodiment of the present invention, for voice input, the user's voice signal is collected through a microphone array, and pre-processing operations including denoising, echo cancellation and volume normalization are performed to ensure the audio quality of subsequent processing; Automatic speech recognition technology based on deep neural networks is used to convert speech signals into corresponding text sequences. The deep neural network is trained using the Transformer architecture combined with the connectionist temporal classification (CTC) loss function.

[0023] In one embodiment of the present invention, for image input processing, image data captured by a user through a camera is received, and image preprocessing including operations such as resizing, brightness and contrast correction, and noise filtering is performed on the image data to ensure that the image quality meets the requirements of subsequent analysis; Use a convolutional neural network-based object detection algorithm to identify various IoT devices, sensors, or related physical objects in images. The convolutional neural network-based object detection algorithm uses a pre-trained network model fine-tuned on an IoT device dataset. Feature extraction and classification are performed on the detected targets to identify key information such as device type, status indicator color, instrument reading, etc., and the extracted visual features are converted into corresponding semantic labels.

[0024] In one embodiment of the present invention, for gesture input, the three-dimensional position and posture information of the user's hand is captured by a depth camera or an infrared sensor; Construct a 3D coordinate sequence of key hand points and use a gesture sequence analysis algorithm based on a long short-term memory network to identify the type of gesture performed by the user, including basic operations such as pointing, circling, zooming, and sliding; Based on the recognized gesture type, the corresponding parameter information is extracted, such as the direction vector of the pointing gesture, the area coordinates of the circle gesture, the scale factor of the zoom gesture, etc., and the gesture information is spatially mapped with the current display interface to determine the specific object or area the user is pointing to or operating, and the gesture recognition results are converted into query operation instructions.

[0025] In one embodiment of the present invention, the quintuple structure is: ,in, Represents the query subject, i.e., a specific device type, data attribute, or physical phenomenon; Represents a time constraint, defining the time range and granularity of the query, including a specific time point, time period, or relative time expression; Represents a spatial constraint, specifying the geographic location or area of ​​the query; Represents context information, including background information such as user identity, environment status, and device status; Indicates the data credibility requirement, which specifies the minimum credibility threshold required for the query result.

[0026] It can be understood that structured query representation can uniformly handle complex query requirements from different modalities, and can effectively support users to express query requirements through a variety of natural interaction methods, while ensuring the accuracy of query understanding and the efficiency of processing.

[0027] By converting multimodal input into a standardized five-tuple structured query representation, the present invention overcomes the limitation of traditional Internet of Things query systems that only support a single input mode, improves the naturalness and convenience of human-computer interaction, and improves the efficiency of Internet of Things information query functions.

[0028] S2. Use an improved data credibility assessment algorithm to perform credibility assessment on IoT data to obtain a credibility score for each data item, wherein the improved data credibility assessment algorithm includes a feature extraction module, a feature learning module, a scoring module, an information verification module, and an analysis module.

[0029] Among them, IoT data includes sensor data, device status data and network communication data, among which sensor data includes environmental monitoring data and location positioning data, device status data includes device identification information, device operating status and device configuration information, and network communication data includes communication protocol data, network performance data and data traffic statistics.

[0030] Specifically, step S2 includes: Use the feature extraction module to extract features from IoT data to obtain device hardware fingerprint features, network behavior features, and data content features; The device hardware fingerprint features, network behavior features and data content features are encoded and decoded into feature vectors using a feature learning module to obtain data potential representation and reconstruction error; The scoring module calculates an initial credibility score based on the data potential representation and reconstruction error; wherein the initial credibility score is calculated as follows: Based on the error value of the reconstruction error, calculate the overall error rate and feature similarity between the device hardware fingerprint features, network behavior features, and data content features and the reconstructed device hardware fingerprint features, network behavior features, and data content features; The initial credibility is obtained based on the error rate and feature similarity, that is, initial credibility = (1-error rate) × similarity × 100; Obtain external verification information and use the information verification module to calculate the external verification information to obtain the cross-validation strength; the calculation method is: Obtain external verification information and identify key data items; For each key data item, a reasonable range and an error tolerance of plus or minus 10% are set. The numerical deviation between the current data and the external verification information provided by each verification data source is calculated. The ratio of the number of verification sources with a value less than 10% to the total number of verification sources is calculated to obtain the consistency ratio. Based on the consistency ratio, the verification strength score is calculated, i.e., verification strength score = consistency ratio × number of verification sources × 20; Obtain IoT historical data and use the analysis module to analyze the historical data to obtain a temporal consistency score. The temporal consistency is calculated as follows: Get IoT data for the same period over the past 30 days and calculate the historical average and standard deviation. Set the upper and lower limits of the normal range based on the historical mean and historical standard deviation; Compare the current data value with the upper and lower limits of the normal range to determine the degree of deviation: If the current value is within the normal range: Timing consistency score = 100 points If the deviation is within 20% of the normal range: Timing consistency score = 80 points If the deviation is 20%-50% from the normal range: Temporal consistency score = 50 points If the deviation is more than 50% from the normal range: Temporal consistency score = 0 points The confidence score is calculated based on the initial confidence score, the cross-validation strength and the temporal consistency score.

[0031] In one embodiment of the present invention, a weighted average method is used to calculate the credibility, the weight coefficient of the initial credibility score is 0.4, the weight coefficient of the cross-validation strength is 0.35, and the weight coefficient of the temporal consistency score is 0.25.

[0032] The present invention realizes multi-dimensional credibility evaluation of IoT data by improving the data credibility evaluation algorithm, which significantly improves the accuracy and comprehensiveness of the credibility evaluation.

[0033] In one embodiment of the present invention, the processing steps of the feature extraction module are: Perform preprocessing operations on the input IoT data, including basic operations such as data format standardization, outlier detection, and missing value processing to ensure that the data quality meets the requirements of feature extraction; By analyzing the device's unique identifiers such as the MAC address, CPU serial number, hardware version information, and firmware version number, the device's digital fingerprint feature vector is constructed to obtain the device's hardware fingerprint features. Monitor the device's network communication patterns, including key indicators such as data transmission frequency, communication protocol usage, and the timing characteristics of network connection establishment and disconnection. Analyze the device's network-level behavioral characteristics, such as packet size distribution, transmission time interval statistics, and network latency trends, to identify the device's normal behavior baseline and abnormal behavior patterns, and obtain network behavior characteristics. Perform statistical analysis on sensor data, calculate statistical indicators such as data distribution characteristics, coefficient of variation, and time series stability, and identify the rationality and consistency of the data through comparative analysis with historical data and data from similar devices to obtain data content characteristics.

[0034] In one embodiment of the present invention, the feature learning module receives the multi-dimensional feature data output by the feature extraction module, and performs feature encoding learning and representation optimization through a deep neural network architecture, wherein the feature learning module adopts an autoencoder network structure, including an encoder and a decoder. The encoder is responsible for mapping the high-dimensional original features to a low-dimensional latent space, learning the compact representation and intrinsic structure of the data, while the decoder attempts to reconstruct the original features from the latent representation, and evaluates the quality of feature learning through the reconstruction error. During the encoding process, the system adopts a multi-layer perceptron or convolutional neural network structure, and selects a suitable network architecture according to the type and dimension of the input features. Each layer introduces expression capabilities through a nonlinear activation function, enabling the network to learn complex feature relationships and patterns. The decoder reconstructs the original features from the latent representation, and the accuracy of the reconstruction process reflects the quality and integrity of the latent representation.

[0035] Specifically, the feature learning module converts the features of MAC address, device model, transmission frequency and sensor data into numerical values, and performs feature standardization to obtain standardized feature values. All standardized feature values ​​are arranged in order to form a feature vector, and the feature vector is encoded using an encoder to obtain a latent representation. The latent representation is then decoded using a decoder to obtain reconstructed features. The reconstruction accuracy is evaluated based on the original features and the reconstructed features.

[0036] In one embodiment of the present invention, the scoring module adopts a multi-factor fusion scoring strategy, which comprehensively considers indicators of multiple dimensions such as the intrinsic quality, source reliability, and timeliness of the data. First, the basic credibility score is calculated based on the quality and stability of the potential representation, and then adjusted according to the size of the reconstruction error. Data items with smaller reconstruction errors receive higher credibility scores, while data items with larger reconstruction errors are downgraded or marked as suspicious data.

[0037] In one embodiment of the present invention, the information verification module is responsible for acquiring and processing external verification information, and providing an independent verification data source for credibility evaluation.

[0038] In one embodiment of the present invention, the analysis module maintains a historical data archive of each device, recording the data characteristics, behavior patterns, and performance indicator change trends of the device in different time periods.

[0039] In one embodiment of the present invention, the calculation formula for the credibility score is: ; ; in, Represents a data item The credibility score of represents the i-th IoT data item to be evaluated, represents the index of the evaluation dimension, represents the total number of evaluation dimensions, represents the weight coefficient of the j-th evaluation dimension, Represents a data item The basic credibility score on the j-th evaluation dimension, represents the sensitivity parameter of cross validation, Represents a data item The cross-validation strength, represents the threshold parameter of cross validation, represents the normalized information entropy function, Is a data item The information entropy of is the theoretical maximum information entropy.

[0040] Understandably, According to the importance of different dimensions in the overall credibility assessment, Reflects the trust level of a data item in a specific dimension, Represents the weighted comprehensive credibility index. When this value is larger, The closer it is to 0, the The closer it is to 1, the higher the credibility, ensuring that the positive contributions of multiple dimensions can be superimposed in a nonlinear manner, while ensuring that the final score is in the interval [0,1]. It is used to adjust the influence of external verification information on the final score, which can be dynamically adjusted according to the reliability and completeness of the verification information. It reflects the quantity and quality of external verification information. The richer the verification information and the higher the consistency, the larger the value. hour, Greater than 0.5, it means that the verification information has a positive effect on credibility; when hour, Less than 0.5 indicates insufficient verification information, which has a negative impact on credibility. It reflects the richness and uncertainty level of the information content of the data item. Data items with higher information entropy usually contain more valid information and therefore obtain a higher credibility adjustment coefficient.

[0041] S3. Perform complexity calculation on the structured query representation based on a nonlinear evaluation model to obtain a query complexity score.

[0042] In one embodiment of the present invention, the nonlinear evaluation model includes a query parsing module, a complexity calculation module, an analysis module and a comprehensive scoring module, wherein: The query parsing module is used to parse the structured query representation and extract basic factors, wherein the basic factors include the number of entities, relationship complexity, time span and spatial range; The complexity calculation module is used to perform nonlinear transformation on the basic factors and calculate the basic complexity; The analysis module is used to construct a query semantic network and calculate the mutual information and degree centrality of the semantic relationship based on the query semantic network; The comprehensive scoring module is used to fuse the basic complexity and the semantic network complexity to obtain the final complexity score.

[0043] The present invention accurately quantifies the processing difficulty and resource requirements of queries through a nonlinear evaluation model, and more accurately predicts the time and resource overhead of query execution.

[0044] In one embodiment of the present invention, the query parsing module receives a query representation in the form of a five-tuple, performs entity recognition and classification analysis on the query subject, counts basic information such as the number of IoT device types, data attribute types, and physical object categories involved in the query, and calculates the entity quantity factor; By analyzing the associations between entities in the query, including semantic connections such as hierarchical relationships, dependency relationships, and aggregation relationships, the complexity and nesting depth of the relationships are evaluated to form a relationship complexity factor; Parse the time range, time granularity, and temporal relationship information contained in the time constraint T, calculate the query's time span and temporal complexity, and generate a time span factor. By analyzing the spatial information such as geographic scope, spatial accuracy, regional relationship in spatial constraints, the spatial coverage and spatial complexity are calculated to obtain the spatial scope factor.

[0045] In one embodiment of the present invention, the complexity calculation module receives the basic factors extracted by the query parsing module and performs nonlinear transformation and complexity quantification processing.

[0046] Among them, a nonlinear response function is used to transform each basic factor, and a power function form is used to perform nonlinear mapping on the basic factors.

[0047] In one embodiment of the present invention, the analysis module constructs a query semantic network with a directed graph structure based on the semantic information of entities and relationships in the query, wherein nodes represent conceptual entities involved in the query and edges represent semantic relationships between entities; By analyzing the topological structure characteristics of the semantic network, including graph-theoretic metrics such as node degree distribution, path length, clustering coefficient, and centrality index, the semantic complexity of the query is quantified. Calculate the mutual information between each edge and the query target, and evaluate the importance and information contribution of each semantic relationship to query processing.

[0048] In one embodiment of the present invention, the comprehensive scoring module combines multiple complexity factors through a nonlinear function to ensure that the complexity of each dimension can be reasonably reflected in the final score, and combines the basic factors in the form of a product to avoid the problem that the low complexity of a certain dimension masks the high complexity of other dimensions.

[0049] In one embodiment of the present invention, the calculation formula for the query complexity score is: in, represents the query complexity score, represents the index of the basis factor, represents the adjustment parameter of the kth basic factor, represents the normalized value of the kth basis factor, represents the nonlinear response parameter of the kth basis factor, represents the index of the semantic network edge, represents the number of edges in the query semantic network, Indicates the l The degree centrality of an edge in the semantic network, Indicates the l The mutual information between the edge and the query.

[0050] As you can understand, the query complexity score reflects the difficulty of query processing in multiple dimensions. The value range is usually between 1 and 100. The higher the value, the greater the query complexity, which requires more computing resources and processing time. The value of k ranges from 1 to 4, corresponding to the entity number factor, relationship complexity factor, time span factor, and spatial range factor, respectively. The relation complexity factor is obtained by dividing the number of different entity types involved in the query by the reference benchmark value, reflecting the richness of the entities involved in the query. Based on the diversity of types and nested hierarchical calculations between entities in the query, complex relationship structures will significantly increase the difficulty of query processing. Considering the time range length and time accuracy requirements of the query, long time span and high precision time query need to process more historical data. Spatial range factor Based on the query's geographic coverage and spatial accuracy calculation, large-scale and high-precision spatial queries consume more storage and computing resources.

[0051] Used to control the impact of each basic factor on the overall complexity. These parameters are set according to the characteristics of different types of IoT applications and historical statistical data. Control the nonlinear change characteristics of each factor. When , ,it will lead to a super-linear growth of complexity, reflecting the nonlinear ,characteristics of resource requirements in IoT query processing.

[0052] Using a logarithmic function to handle semantic network complexity effectively addresses the impact of exponential growth in the number of semantic relationships on complexity, preventing excessive impact on the overall score when the semantic network becomes too large. At the same time, the logarithmic function maintains sensitivity to changes in semantic complexity, ensuring that the increase in semantic relationships and changes in importance are appropriately reflected in the final score.

[0053] S4. Determine a query execution strategy based on the query complexity score and IoT resource status. The IoT resource status includes computing resource status, storage resource status, and network resource status. Computing resource status includes edge node computing power, memory resource status, and GPU acceleration resources. Storage resource status includes local storage capacity, data cache status, and data backup status. Network resource status includes network connection quality, communication protocol support, and network topology status.

[0054] In one embodiment of the present invention, the query execution strategy includes a local processing strategy, an edge collaborative processing strategy, and a cloud processing strategy, wherein: The local processing strategy is used to complete query processing within a single edge node; The edge collaborative processing strategy is used to collaboratively complete query processing across multiple edge nodes; The cloud processing strategy is used to report the query to the cloud service layer for processing.

[0055] Specifically, step S4 includes: Obtain computing resource status based on the local edge node's CPU utilization, memory usage, remaining storage space, and network bandwidth usage. Evaluate data completeness by using structured queries to represent local availability, integrity, and timeliness. Set the first complexity threshold and the second complexity threshold based on the processing capacity of the local edge node and historical query statistics, where the first complexity threshold corresponds to the upper limit of queries that can be processed independently by local resources, and the second complexity threshold corresponds to the upper limit of queries that can be processed collaboratively by the edge; Selecting a local processing strategy when the query complexity score is lower than a first complexity threshold and the local data completeness meets the query requirements; When the complexity score is greater than the first complexity threshold but less than the second complexity threshold or the local data is incomplete, the preset neighboring node status table is queried to obtain the processing capacity, data type and network connection quality information of the surrounding edge nodes, and the edge collaborative processing strategy is executed; When the complexity score is higher than the second complexity threshold or the combination of neighboring edge nodes still cannot meet the query requirements, the cloud processing strategy is selected.

[0056] As you can understand, CPU utilization monitoring uses a sliding window averaging method, and obtains the recent average load level and load change trend through continuous sampling calculations; memory usage evaluation includes the usage of physical memory and virtual memory; monitoring of remaining storage space includes not only overall available space statistics, but also analysis of the read and write performance of storage devices, data distribution characteristics, and access hotspot patterns.

[0057] By analyzing the data type, data source, and data range involved in the query, and checking whether the local storage contains all the data items required for the query, a data availability assessment is obtained; by checking the completeness, accuracy, consistency, and relevance of the data, a data integrity assessment is obtained; and by analyzing the update time, data age, and degree of match between the local data and timeliness requirements, a data timeliness assessment is obtained.

[0058] The present invention achieves optimal configuration and load balancing of computing resources by intelligently selecting execution strategies based on query complexity scores and real-time resource status, avoiding resource waste or performance bottlenecks that may result from fixed strategy selection, ensuring that queries of different complexities can obtain appropriate processing resources and execution environments, and improving information query efficiency and stability.

[0059] S5. Execute information query according to the query execution strategy to obtain initial query results; S6. Perform fusion processing on the query results based on the credibility score to obtain a final information query result.

[0060] The present invention realizes adaptive processing and quality optimization of information query in the Internet of Things environment through multimodal query input, improved data credibility assessment algorithm, nonlinear complexity assessment model, intelligent execution strategy decision and credibility fusion processing. It can dynamically select the optimal execution strategy according to query complexity and resource status, switch between local processing, edge collaborative processing and cloud processing, effectively balance the relationship between query response time, resource utilization efficiency and result quality, and significantly improve the overall performance and user experience of the Internet of Things information query system.

[0061] Specifically, step S6 includes: Performing deduplication processing on the initial query results to obtain a deduplication data item set; Matching the data in the deduplicated data item set with the structured query representation to obtain a relevance score for each data item; Calculate the similarity and difference between the data items in the deduplicated data item set to obtain the information evaluation result of each data item; Based on the credibility score, data integrity index and measurement accuracy index of each data item, a weight distribution algorithm is used to calculate the data quality weight of each data item; Calculate a timeliness discount factor for each data item based on the data generation time and the query time, and calculate the contribution of each data item to the query result based on the relevance score, the information evaluation result, the data quality weight, and the timeliness discount factor; Based on the credibility score and contribution of each data item, weighted fusion processing is used to obtain the final information query result.

[0062] It can be understood that deduplication processing performs precise matching and deduplication based on the key identifiers of the data items, identifies identical duplicate data items, and obtains a set of deduplicated data items, where the similarity between the data items calculates the matching degree of each query element of the data items.

[0063] The present invention also provides an information query system based on the Internet of Things, which implements the information query method described above, including: A query input module, configured to receive a multimodal query input and convert the multimodal query input into a structured query representation; The credibility assessment module is used to perform credibility assessment on IoT data using an improved data credibility assessment algorithm to obtain a credibility score for each data item; A complexity calculation module, configured to perform complexity calculation on the structured query representation based on a nonlinear evaluation model to obtain a query complexity score; An execution strategy determination module, configured to determine a query execution strategy based on the query complexity score and IoT resource status; An information query module, configured to execute information query according to the query execution strategy and obtain initial query results; The fusion module is used to fuse the query results based on the credibility score to obtain a final information query result.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An information query method based on the Internet of Things, characterized in that: include: S1. Receive a multimodal query input and convert the multimodal query input into a structured query representation; S2. Use the improved data credibility assessment algorithm to conduct credibility assessment on IoT data and obtain the credibility score of each data item; S3. performing complexity calculation on the structured query representation based on a nonlinear evaluation model to obtain a query complexity score; S4. Determine a query execution strategy based on the query complexity score and IoT resource status; S5. Execute information query according to the query execution strategy to obtain initial query results; S6. Perform fusion processing on the query results based on the credibility score to obtain a final information query result.

2. The information query method based on the Internet of Things according to claim 1, characterized in that: The structured query representation adopts a five-tuple structure, including a query subject, a time constraint, a space constraint, context information, and a data credibility requirement.

3. The information query method based on the Internet of Things according to claim 1, characterized in that: The improved data credibility assessment algorithm includes a feature extraction module, a feature learning module, a scoring module, an information verification module and an analysis module.

4. The information query method based on the Internet of Things according to claim 3, characterized in that: Step S2 specifically includes: Use the feature extraction module to extract features from IoT data to obtain device hardware fingerprint features, network behavior features, and data content features; The device hardware fingerprint features, network behavior features and data content features are encoded and decoded into feature vectors using a feature learning module to obtain data potential representation and reconstruction error; The scoring module calculates an initial credibility score based on the data potential representation and reconstruction error; Obtain external verification information and use the information verification module to calculate the external verification information to obtain the cross-validation strength; Obtain IoT historical data and use the analysis module to analyze the historical data to obtain a temporal consistency score; The confidence score is calculated based on the initial confidence score, the cross-validation strength and the temporal consistency score.

5. The information query method based on the Internet of Things according to claim 4, characterized in that: The calculation formula of the credibility score is: ； in, Represents a data item The credibility score of represents the i-th IoT data item to be evaluated, represents the index of the evaluation dimension, represents the total number of evaluation dimensions, represents the weight coefficient of the j-th evaluation dimension, Represents a data item The basic credibility score on the j-th evaluation dimension, represents the sensitivity parameter of cross validation, Represents a data item The cross-validation strength, represents the threshold parameter of cross validation, Represents the normalized information entropy function.

6. The information query method based on the Internet of Things according to claim 1, characterized in that: The nonlinear evaluation model includes a query parsing module, a complexity calculation module, an analysis module and a comprehensive scoring module, wherein: The query parsing module is used to parse the structured query representation and extract basic factors, wherein the basic factors include the number of entities, relationship complexity, time span and spatial range; The complexity calculation module is used to perform nonlinear transformation on the basic factors and calculate the basic complexity; The analysis module is used to construct a query semantic network and calculate the mutual information and degree centrality of the semantic relationship based on the query semantic network; The comprehensive scoring module is used to fuse the basic complexity and the semantic network complexity to obtain the final complexity score.

7. The information query method based on the Internet of Things according to claim 6, characterized in that: The query execution strategy includes local processing strategy, edge collaborative processing strategy and cloud processing strategy, wherein, The local processing strategy is used to complete query processing within a single edge node; The edge collaborative processing strategy is used to collaboratively complete query processing across multiple edge nodes; The cloud processing strategy is used to report the query to the cloud service layer for processing.

8. The information query method based on the Internet of Things according to claim 7, characterized in that: Step S4 specifically includes: Obtain computing resource status based on the local edge node's CPU utilization, memory usage, remaining storage space, and network bandwidth usage. Evaluate data completeness by using structured queries to represent local availability, integrity, and timeliness. Set the first complexity threshold and the second complexity threshold based on the processing capacity of the local edge node and historical query statistics, where the first complexity threshold corresponds to the upper limit of queries that can be processed independently by local resources, and the second complexity threshold corresponds to the upper limit of queries that can be processed collaboratively by the edge; Selecting a local processing strategy when the query complexity score is lower than a first complexity threshold and the local data completeness meets the query requirements; When the complexity score is greater than the first complexity threshold but less than the second complexity threshold or the local data is incomplete, the preset neighboring node status table is queried to obtain the processing capacity, data type and network connection quality information of the surrounding edge nodes, and the edge collaborative processing strategy is executed; When the complexity score is higher than the second complexity threshold or the combination of neighboring edge nodes still cannot meet the query requirements, the cloud processing strategy is selected.

9. The information query method based on the Internet of Things according to claim 1, characterized in that: Step S6 specifically includes: Performing deduplication processing on the initial query results to obtain a deduplication data item set; Matching the data in the deduplicated data item set with the structured query representation to obtain a relevance score for each data item; Calculate the similarity and difference between the data items in the deduplicated data item set to obtain the information evaluation result of each data item; Based on the credibility score, data integrity index and measurement accuracy index of each data item, a weight distribution algorithm is used to calculate the data quality weight of each data item; Calculate a timeliness discount factor for each data item based on the data generation time and the query time, and calculate the contribution of each data item to the query result based on the relevance score, the information evaluation result, the data quality weight, and the timeliness discount factor; Based on the credibility score and contribution of each data item, weighted fusion processing is used to obtain the final information query result.

10. An information query system based on the Internet of Things, characterized in that: Implementing the information query method according to any one of claims 1 to 9, comprising: A query input module, configured to receive a multimodal query input and convert the multimodal query input into a structured query representation; The credibility assessment module is used to perform credibility assessment on IoT data using an improved data credibility assessment algorithm to obtain a credibility score for each data item; A complexity calculation module, configured to perform complexity calculation on the structured query representation based on a nonlinear evaluation model to obtain a query complexity score; An execution strategy determination module, configured to determine a query execution strategy based on the query complexity score and IoT resource status; An information query module, configured to execute information query according to the query execution strategy and obtain initial query results; The fusion module is used to fuse the query results based on the credibility score to obtain a final information query result.

Images